Compare commits

..

11 Commits

Author SHA1 Message Date
mohitagw15856 f23c3a7e10 Update README.md 2026-04-09 00:24:18 +05:30
mohitagw15856 7db88b1a2d feat: add pm-figma bundle — 10 Figma skills for PMs and designers (v5.1.0, 90 skills total) 2026-04-08 19:48:07 +01:00
mohitagw15856 7720d236ce Add custom skills section to README
Added a section on custom skills tailored for specific teams, highlighting their benefits and providing examples.
2026-04-06 01:47:16 +05:30
mohitagw15856 14d191cda0 chore: remove shell scripts from repo
Internal bash scripts don't need to be public — removed from tracking.
.gitignore already excludes *.sh going forward.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-05 13:11:44 +01:00
mohitagw15856 fd5b9daa43 Add files via upload 2026-04-05 13:10:04 +01:00
mohitagw15856 adb742a187 Create config.yml 2026-04-05 13:10:04 +01:00
mohitagw15856 dd33b0d416 Add files via upload 2026-04-05 13:10:04 +01:00
mohitagw15856 1fafb44dc2 Update README.md 2026-04-05 17:31:57 +05:30
mohitagw15856 27d8363f28 Update README.md 2026-04-05 17:29:18 +05:30
mohitagw15856 2e17d68eaa feat: add 27 new skills across 7 professions — 80 skills, 21 plugins (v5.0.0) 2026-04-05 12:48:16 +01:00
mohitagw15856 380a1dde21 docs: add CODE_OF_CONDUCT and SECURITY policy 2026-04-02 10:37:30 +01:00
103 changed files with 10351 additions and 27 deletions
Vendored
BIN
View File
Binary file not shown.
+65
View File
@@ -0,0 +1,65 @@
---
name: "🐛 Bug Report"
about: "A skill isn't triggering correctly, producing wrong output, or something else is broken"
title: "[BUG] "
labels: ["bug"]
assignees: ""
---
## Which skill is affected?
<!-- e.g. plugins/pm-gtm/skills/go-to-market -->
**Skill path:**
---
## What's the problem?
<!-- Tick all that apply -->
- [ ] Skill isn't triggering when it should
- [ ] Skill is triggering when it shouldn't
- [ ] Output is missing a section
- [ ] Output format is wrong
- [ ] Skill description is incorrect or misleading
- [ ] Plugin isn't showing in the marketplace
- [ ] Installation issue
- [ ] Other: ___________
---
## What did you expect to happen?
---
## What actually happened?
<!-- Paste the output or describe what went wrong -->
---
## How to reproduce
<!-- Step by step:
1. Trigger phrase used: "..."
2. Claude Code version: ...
3. What happened: ... -->
1.
2.
3.
---
## Environment
- **Claude Code version:**
- **OS:**
- **Install method:** marketplace / manual / symlink
---
## Any additional context?
<!-- Screenshots, logs, or anything else helpful -->
+8
View File
@@ -0,0 +1,8 @@
blank_issues_enabled: false
contact_links:
- name: 📚 Read the article series
url: https://medium.com/product-powerhouse/claude-skills-the-ai-feature-thats-quietly-changing-how-product-managers-work-aad5d8d0640a
about: Full background on the Claude Skills Library and how to use it
- name: 💬 Start a Discussion
url: https://github.com/mohitagw15856/pm-claude-skills/discussions
about: For open-ended conversations, ideas, and community skill sharing
@@ -0,0 +1,21 @@
---
name: "💬 Question or Feedback"
about: "Ask a question about using the skills, or share feedback on the library"
title: "[QUESTION] "
labels: ["question"]
assignees: ""
---
## What's your question or feedback?
---
## Context
<!-- Which skill or bundle are you asking about? Any relevant details about your setup? -->
---
## What have you already tried?
<!-- If it's a question about getting something working — what have you attempted? -->
+70
View File
@@ -0,0 +1,70 @@
---
name: "💡 Skill Request"
about: "Suggest a new skill you'd like to see added to the library"
title: "[SKILL REQUEST] "
labels: ["skill-request"]
assignees: ""
---
## What skill are you requesting?
<!-- A short name for the skill, e.g. "Legal Contract Review" or "Sales Battlecard Builder" -->
**Skill name:**
---
## What profession or role is this for?
<!-- Who would use this skill day-to-day? -->
- [ ] Product Management
- [ ] Marketing & GTM
- [ ] Engineering & Tech
- [ ] Data & Analytics
- [ ] Leadership & People
- [ ] Design & UX
- [ ] Business & Strategy
- [ ] Legal
- [ ] Finance
- [ ] HR
- [ ] Sales
- [ ] Other: ___________
---
## What workflow does this skill solve?
<!-- Describe the specific task or document this skill should produce.
Be as concrete as possible — what do you do today that takes too long? -->
---
## What should the output look like?
<!-- What does a good output from this skill contain?
E.g. "A structured contract review with flagged clauses, risk rating, and plain English summary" -->
---
## Example trigger phrases
<!-- How would you naturally ask Claude to use this skill?
E.g. "Review this contract", "Flag the key risks in this NDA" -->
-
-
---
## Are you willing to build this skill yourself?
- [ ] Yes — I'll raise a PR with the SKILL.md
- [ ] Maybe — I'd like guidance first
- [ ] No — I'm suggesting it for someone else to build
---
## Any additional context?
<!-- Links, examples, or anything else that would help someone build this skill -->
+92
View File
@@ -0,0 +1,92 @@
## What does this PR add or change?
<!-- One sentence summary -->
---
## Type of change
- [ ] New skill
- [ ] Improvement to an existing skill
- [ ] Bug fix (skill not triggering / wrong output)
- [ ] Documentation update (README, CONTRIBUTING, etc.)
- [ ] Marketplace / plugin config change
- [ ] Other: ___________
---
## New skill checklist
<!-- If you're adding a new skill, tick all of these before requesting review.
If this isn't a new skill PR, delete this section. -->
**Skill file**
- [ ] Skill is in the correct folder: `plugins/[bundle-name]/skills/[skill-name]/SKILL.md`
- [ ] Frontmatter includes `name` and `description` fields
- [ ] `description` clearly states when Claude should activate this skill (trigger condition)
- [ ] `description` clearly states what the skill produces (output description)
**Content quality**
- [ ] Skill solves a real, recurring professional workflow (not a one-off task)
- [ ] Output structure is clearly defined with sections and format
- [ ] Required inputs are listed (what Claude should ask for if not provided)
- [ ] Quality checks section is included
- [ ] Example trigger phrases are included (at least 2)
**Safety**
- [ ] Skill contains no prompt injection attempts or instructions to override Claude's guidelines
- [ ] Skill does not instruct Claude to collect, store, or transmit personal data
- [ ] Skill does not contain hardcoded credentials, API keys, or PII
**Testing**
- [ ] I have tested this skill locally in Claude Code
- [ ] The skill triggers correctly on the example trigger phrases
- [ ] The output matches the structure defined in the SKILL.md
---
## What does this skill do?
<!-- 2-3 sentences. What workflow does it solve? Who is it for? -->
---
## Example output
<!-- Paste a real sample output from Claude when this skill was triggered, or describe what it produces.
This is the most useful thing you can include for review. -->
---
## Which bundle does this belong in?
<!-- Which existing plugin bundle should this skill be added to?
Or are you proposing a new bundle? -->
- [ ] pm-essentials
- [ ] pm-discovery
- [ ] pm-planning
- [ ] pm-delivery
- [ ] pm-analytics
- [ ] pm-strategy
- [ ] pm-advanced
- [ ] pm-rituals
- [ ] pm-gtm
- [ ] pm-engineering
- [ ] pm-data
- [ ] pm-people
- [ ] pm-design
- [ ] pm-business
- [ ] New bundle: ___________
---
## Related issue
<!-- If this PR addresses a skill request issue, link it here: "Closes #123" -->
---
## Anything else the reviewer should know?
<!-- Edge cases, limitations, or anything that might need discussion -->
+39
View File
@@ -0,0 +1,39 @@
# Code of Conduct
## Our Pledge
This is an open-source community built around sharing useful Claude Skills across professions. Everyone who contributes, raises issues, or participates in discussions is expected to make this a welcoming and constructive space.
We pledge to make participation in this project a harassment-free experience for everyone, regardless of age, background, disability, ethnicity, gender identity, level of experience, nationality, personal appearance, race, religion, or sexual identity.
## Our Standards
**Behaviour that helps this community thrive:**
- Sharing skills that solve real workflows, with honest descriptions of what they do
- Giving constructive feedback on PRs — specific, actionable, and respectful
- Acknowledging other contributors' work
- Being direct about limitations or gaps in a skill without being dismissive
- Helping newcomers get their first PR merged
**Behaviour that is not acceptable:**
- Harassment, personal attacks, or dismissive comments on contributions
- Submitting skills that contain malicious instructions or prompt injection attempts
- Spamming issues or PRs with low-effort or off-topic content
- Claiming credit for someone else's skill file
- Any form of discrimination
## Scope
This Code of Conduct applies to all spaces managed by this project — GitHub Issues, Pull Requests, Discussions, and any other forums linked from this repo.
## Reporting
If you experience or witness unacceptable behaviour, contact the maintainer directly at **mohit15856@gmail.com**. All reports will be reviewed and responded to promptly and confidentially.
## Enforcement
The maintainer reserves the right to remove comments, close PRs, or ban contributors who violate this Code of Conduct. Decisions will be made fairly and explained where possible.
## Attribution
This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org), version 2.1.
+223 -27
View File
@@ -1,8 +1,8 @@
# 🧠 Claude Skills Library — 53 Skills for Every Professional
# 🧠 Claude Skills Library — 90 Skills for Every Profession
> **Save 810 hours per week across any profession. Install in 2 minutes.**
> **Save 810 hours per week across 14 professions. Install in 2 minutes.**
A community-built library of Claude Skills covering product management, marketing, engineering, data, design, leadership, and business strategy. Each skill is a structured SKILL.md file that teaches Claude how to produce professional-grade outputs for your specific workflows.
A community-built library of Claude Skills covering product management, marketing, engineering, data, design, Figma, leadership, legal, finance, HR, sales, operations, research, and more. Each skill is a structured SKILL.md file that teaches Claude how to produce professional-grade outputs for your specific workflows.
---
@@ -10,7 +10,20 @@ A community-built library of Claude Skills covering product management, marketin
In Claude Code, run:
/plugin marketplace add mohitagw15856/pm-claude-skills
/plugin marketplace add https://github.com/mohitagw15856/pm-claude-skills
Or install by profession:
claude plugin install pm-essentials@pm-claude-skills # Core PM
claude plugin install pm-legal@pm-claude-skills # Legal
claude plugin install pm-finance@pm-claude-skills # Finance
claude plugin install pm-hr@pm-claude-skills # HR
claude plugin install pm-sales@pm-claude-skills # Sales
claude plugin install pm-operations@pm-claude-skills # Operations
claude plugin install pm-research@pm-claude-skills # Research & Healthcare
claude plugin install pm-cross@pm-claude-skills # Cross-profession
claude plugin install pm-figma@pm-claude-skills # Figma
Or clone and symlink for auto-updates:
@@ -20,8 +33,6 @@ mkdir -p ~/.claude/skills
ln -s ~/pm-claude-skills/skills/* ~/.claude/skills/
That's it. All 53 skills are now available in every Claude Code session.
---
## 📚 The Article Series
@@ -37,55 +48,71 @@ This repo was built alongside a published article series. Read the full story:
| Part 5 | What Google, Meta and Anthropic Want From PMs — And the Claude Skills That Deliver It | [Read →](https://medium.com/@mohit15856/what-google-meta-and-anthropic-want-from-pms-and-the-claude-skills-that-deliver-it-b0f2b6cd9340) |
| Part 6 | I Tested Anthropic's Skill Creator Plugin on My Own Skills | [Read →](https://medium.com/all-about-claude/i-tested-anthropics-skill-creator-plugin-on-my-own-skills-here-s-what-i-found-23ad406b0825) |
| Part 7 | 33 Claude Skills for PMs Are Now in the Claude Code Marketplace | [Read →](https://medium.com/product-powerhouse/33-claude-skills-for-pms-are-now-in-the-claude-code-marketplace-heres-how-to-install-them-7968ab6bb1e1) |
| Part 8 | I Added 20 New Claude Skills Beyond Product Management | *Latest — link TBC* |
| Part 8 | I Added 20 New Claude Skills Beyond Product Management | [Read →](https://medium.com/product-powerhouse/i-built-20-new-claude-skills-for-every-profession-heres-the-full-library-50278e00bf72) |
| Part 9 | 80 Claude Skills for Every Profession — Lawyers, Doctors, Finance, HR, Sales and More | [Read →](https://medium.com/@mohit15856/80-claude-skills-for-every-profession-lawyers-doctors-finance-hr-sales-and-more-3dfde9ec0033) |
| Part 10 | A Day in the Life With 80 Claude Skills — What Actually Gets Triggered | [Read →](https://medium.com/@mohit15856/80-claude-skills-for-every-profession-lawyers-doctors-finance-hr-sales-and-more-3dfde9ec0033)|
| Part 11 | 10 Figma Claude Skills for PMs and Designers — The Complete Figma Toolkit | *Latest — Link TBC* |
---
## 🗂️ All 53 Skills
## 🗂️ All 90 Skills
### 🛠️ Product Management (Skills 133)
**Bundles:** `pm-essentials` · `pm-discovery` · `pm-planning` · `pm-delivery` · `pm-analytics` · `pm-strategy` · `pm-advanced` · `pm-rituals`
> The original toolkit. Discovery, prioritisation, delivery, strategy, stakeholder comms, and more.
> The original toolkit covering the full PM lifecycle — discovery, prioritisation, delivery, strategy, stakeholder comms, and weekly rituals.
| # | Skill | What It Does |
|---|---|---|
| 133 | *[Original 33 PM skills]* | See [Part 7 article](https://medium.com/product-powerhouse/33-claude-skills-for-pms-are-now-in-the-claude-code-marketplace-heres-how-to-install-them-7968ab6bb1e1) for full list |
| 15 | **pm-essentials** | PRD Template, Meeting Notes, Stakeholder Update, User Research Synthesis, Competitive Analysis |
| 69 | **pm-discovery** | Discovery Interview Guide, Job Story Mapper, User Interview Synthesis, Assumption Mapper |
| 1015 | **pm-planning** | OKR Builder, Feature Prioritisation (RICE/MoSCoW/Kano/ICE), Roadmap Presentation, Pricing Strategy |
| 1622 | **pm-delivery** | Sprint Planning, Technical Spec, A/B Test Planner, Go-to-Market Planner, Launch Checklist, Sprint Brief, Retro |
| 2325 | **pm-analytics** | Data Analysis Standard, Retention Analysis, Product Health Analysis |
| 2631 | **pm-strategy** | Competitor Signal Tracker, Competitive Intelligence Monitor, Stakeholder Influence Mapper, Strategic Narrative, Executive Update, Ambiguity Resolver |
| 3233 | **pm-advanced** | AI Product Canvas, Multi-Source Signal Synthesiser, Experiment Designer, Design Handoff Brief |
> See [Part 7 article](https://medium.com/product-powerhouse/33-claude-skills-for-pms-are-now-in-the-claude-code-marketplace-heres-how-to-install-them-7968ab6bb1e1) for full PM skills detail.
---
### 📣 Marketing & Growth (Skills 3437)
### 📣 Marketing & GTM (Skills 3437)
**Bundle:** `pm-gtm`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 34 | **Go-To-Market** | `skills/go-to-market/` | Positioning statements, messaging pillars, feature/benefit mapping, and role-specific use cases |
| 35 | **Content Calendar** | `skills/content-calendar/` | Multi-channel content calendars with hooks, formats, and repurposing map |
| 34 | **Go-To-Market** | `skills/go-to-market/` | Positioning statements, messaging pillars, feature/benefit mapping, role-specific use cases |
| 35 | **Content Calendar** | `skills/content-calendar/` | Multi-channel content calendars with opening hooks, formats, and repurposing map |
| 36 | **Competitor Teardown** | `skills/competitor-teardown/` | Full competitive analysis: positioning map, feature comparison, messaging gaps, SWOT, recommendations |
| 37 | **Email Campaign** | `skills/email-campaign/` | Sequenced email campaigns with subject lines, preview text, body copy, and CTAs |
---
### 👩‍💻 Engineering & Tech (Skills 3841)
**Bundle:** `pm-engineering`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 38 | **Code Review Checklist** | `skills/code-review-checklist/` | Tailored PR review checklists by language, type, and risk level |
| 39 | **Incident Postmortem** | `skills/incident-postmortem/` | Blameless postmortems with timeline, RCA, impact, and action items |
| 40 | **API Docs Writer** | `skills/api-docs-writer/` | Developer-facing API docs from raw specs: endpoints, parameters, response schemas, code examples |
| 41 | **Architecture Decision Record** | `skills/architecture-decision-record/` | ADRs with context, options, decision, consequences, and risks |
| 40 | **API Docs Writer** | `skills/api-docs-writer/` | Developer-facing API docs: endpoints, parameters, response schemas, code examples |
| 41 | **Architecture Decision Record** | `skills/architecture-decision-record/` | ADRs with context, options considered, decision, consequences, and risks |
---
### 📊 Data & Analytics (Skills 4244)
**Bundle:** `pm-data`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 42 | **Metrics Framework** | `skills/metrics-framework/` | North Star + metric tree, dashboard tiers, counter-metrics |
| 43 | **SQL Query Explainer** | `skills/sql-query-explainer/` | Explain, optimise, write, and document SQL in plain English |
| 43 | **SQL Query Explainer** | `skills/sql-query-explainer/` | Explain, optimise, write, and document SQL in plain English |
| 44 | **Dashboard Brief** | `skills/dashboard-brief/` | Complete dashboard spec: KPIs, charts, filters, layout, data requirements |
---
### 🧑‍💼 Leadership & Management (Skills 4547)
### 🧑‍💼 Leadership & People (Skills 4547)
**Bundle:** `pm-people`
| # | Skill | Folder | What It Does |
|---|---|---|---|
@@ -96,6 +123,7 @@ This repo was built alongside a published article series. Read the full story:
---
### 🎨 Design & UX (Skills 4850)
**Bundle:** `pm-design`
| # | Skill | Folder | What It Does |
|---|---|---|---|
@@ -106,6 +134,7 @@ This repo was built alongside a published article series. Read the full story:
---
### 🏢 Business & Strategy (Skills 5153)
**Bundle:** `pm-business`
| # | Skill | Folder | What It Does |
|---|---|---|---|
@@ -113,6 +142,114 @@ This repo was built alongside a published article series. Read the full story:
| 52 | **Board Deck Narrative** | `skills/board-deck-narrative/` | Slide-by-slide board presentation structure with narrative beats and talking points |
| 53 | **Job Application** | `skills/job-application/` | Tailored CV summary, ATS keyword optimisation, and cover letter for any JD |
---
### ⚖️ Legal (Skills 5457)
**Bundle:** `pm-legal`
> ⚠️ All legal skills include a disclaimer. Not a substitute for qualified legal advice.
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 54 | **Contract Review** | `skills/contract-review/` | Structured review with key terms, flagged clauses, risk rating, and plain English summary |
| 55 | **NDA Analyser** | `skills/nda-analyser/` | Clause-by-clause NDA analysis with risk flags and negotiation checklist |
| 56 | **Legal Brief** | `skills/legal-brief/` | Legal memos and argument outlines in IRAC format (Issue, Rule, Application, Conclusion) |
| 57 | **Compliance Checklist** | `skills/compliance-checklist/` | GDPR, SOC 2, ISO 27001, FCA, HIPAA compliance checklists with prioritised gap analysis |
---
### 💰 Finance (Skills 5861)
**Bundle:** `pm-finance`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 58 | **Financial Model Narrative** | `skills/financial-model-narrative/` | Turns P&L and model outputs into board-ready written narratives |
| 59 | **Budget Variance Analysis** | `skills/budget-variance-analysis/` | Variance table with root cause commentary and management summary |
| 60 | **Investor Pitch Deck** | `skills/investor-pitch-deck/` | Slide-by-slide pitch deck structure with what each slide must prove |
| 61 | **Financial Due Diligence** | `skills/financial-due-diligence/` | DD document request list, analytical questions, and red flags checklist |
---
### 👥 HR (Skills 6265)
**Bundle:** `pm-hr`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 62 | **Job Description Writer** | `skills/job-description-writer/` | Inclusive, structured JDs with built-in language review and salary range nudge |
| 63 | **Onboarding Plan** | `skills/onboarding-plan/` | 30/60/90-day plans with week-by-week structure, milestones, and manager checklist |
| 64 | **Employee Engagement Survey** | `skills/employee-engagement-survey/` | Survey design + results analysis mode with eNPS and action planning template |
| 65 | **Redundancy Consultation** | `skills/redundancy-consultation/` | Process timeline, at-risk letter, consultation script, and confirmation letter — UK law |
---
### 🤝 Sales (Skills 6669)
**Bundle:** `pm-sales`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 66 | **Sales Battlecard** | `skills/sales-battlecard/` | One-page competitive battlecard with objection responses and landmine questions |
| 67 | **Discovery Call Prep** | `skills/discovery-call-prep/` | Call brief with research summary, hypothesis, structured questions, and success criteria |
| 68 | **Proposal Writer** | `skills/proposal-writer/` | Commercial proposals structured around the prospect's problem, not the product |
| 69 | **Account Plan** | `skills/account-plan/` | Strategic account plan with relationship map, whitespace analysis, risks, and 90-day actions |
---
### ⚙️ Operations (Skills 7073)
**Bundle:** `pm-operations`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 70 | **Process Documentation** | `skills/process-documentation/` | Clear process docs with steps, roles, edge cases — followable by a new starter |
| 71 | **SOP Writer** | `skills/sop-writer/` | Formal, audit-ready SOPs with version control, quality checks, and non-conformance process |
| 72 | **Vendor Evaluation** | `skills/vendor-evaluation/` | Weighted vendor scorecard, RFP questions, reference check template, and recommendation |
| 73 | **Project Status Report** | `skills/project-status-report/` | RAG status reports with milestone progress, issues, risks, and decisions required |
---
### 🏥 Research & Healthcare (Skills 7477)
**Bundle:** `pm-research`
> ⚠️ Healthcare skills are for documentation and educational purposes only. All clinical content must be reviewed by a qualified professional.
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 74 | **Clinical Case Summary** | `skills/clinical-case-summary/` | SBAR handovers, SOAP notes, and case reports for educational and documentation use |
| 75 | **Research Protocol** | `skills/research-protocol/` | Complete study protocols with objectives, methodology, ethics, and analysis plan |
| 76 | **Patient Communication** | `skills/patient-communication/` | Plain English patient letters, leaflets, and results communications at Grade 6 reading level |
| 77 | **Literature Review** | `skills/literature-review/` | Thematically organised literature reviews with synthesis, critical analysis, and gap identification |
---
### 🌐 Cross-Profession (Skills 7880)
**Bundle:** `pm-cross`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 78 | **Press Release** | `skills/press-release/` | Journalist-ready press releases with headline rules, boilerplate, and journalist test |
| 79 | **Grant Proposal** | `skills/grant-proposal/` | Complete grant applications aligned to funder priorities with budget narrative |
| 80 | **Executive Summary** | `skills/executive-summary/` | Decision-ready executive summaries with bottom line upfront, adapted for any audience |
---
### 🖼️ Figma (Skills 8190)
**Bundle:** `pm-figma`
| # | Skill | Folder | What It Does |
|---|---|---|---|
| 81 | **Figma Component Audit** | `skills/figma-component-audit/` | Audit component library for naming issues, coverage gaps, and variant completeness |
| 82 | **Figma Design Brief** | `skills/figma-design-brief/` | Convert PRDs and feature requests into structured Figma design briefs |
| 83 | **Figma Annotation Guide** | `skills/figma-annotation-guide/` | Generate complete developer handoff annotations covering all states and edge cases |
| 84 | **Figma Design Review** | `skills/figma-design-review/` | PM design review against requirements with explicit approval status |
| 85 | **Figma User Flow Planner** | `skills/figma-user-flow-planner/` | Map all screens, states, and decision points before opening Figma |
| 86 | **Figma Variant Matrix** | `skills/figma-variant-matrix/` | Define all component variants, properties, and states before building |
| 87 | **Figma Spacing System** | `skills/figma-spacing-system/` | Design a complete spacing scale, grid, and token system |
| 88 | **Figma Prototype Plan** | `skills/figma-prototype-plan/` | Plan prototype scope, interactions, and test task scripts for user testing |
| 89 | **Figma Design QA** | `skills/figma-design-qa/` | Pre-handoff QA checklist covering file hygiene, states, accessibility, and handoff readiness |
| 90 | **Figma Design Critique (PM)** | `skills/figma-design-critique-pm/` | PM-perspective design critique focused on product outcomes, not aesthetics |
claude plugin install pm-figma@pm-claude-skills
---
## 🤝 Contributing — Add Your Skill
@@ -129,7 +266,7 @@ This is an open-source community library. If you've built a skill that saves you
**SKILL.md template:**
---
name: your-skill-name
description: "One sentence description. Use when [trigger condition]. Does [output description]."
description: "One sentence. Use when [trigger condition]. Produces [output description]."
---
# Skill Title
@@ -144,12 +281,17 @@ description: "One sentence description. Use when [trigger condition]. Does [outp
- Works without needing extensive setup or context
**Skills wishlist** (most requested — up for grabs):
- `legal-contract-review` — Flag key clauses and risks in contracts
- `financial-model-narrative` — Turn a spreadsheet into a board-ready narrative
- `hr-job-description` — Write inclusive, structured JDs from a role brief
- `onboarding-plan` — 30/60/90-day plan for new hires
- `press-release` — Structured press releases from product announcements
- `seo-content-brief` — Content briefs with keyword strategy and outline
| Skill | Profession | Use Case |
|---|---|---|
| `teaching-lesson-plan` | Education | Structured lesson plans from curriculum objectives |
| `seo-content-brief` | Marketing | Content briefs with keyword strategy and outline |
| `grant-report` | Non-profit | Funder progress reports against grant objectives |
| `architectural-spec` | Architecture | Project specifications and technical drawing briefs |
| `media-pitch` | Journalism | Story pitches to editors and commissioning briefs |
| `clinical-guideline-summary` | Healthcare | Plain English summaries of clinical guidelines |
| `tax-planning-checklist` | Finance | Year-end tax planning checklist by entity type |
| `sales-forecasting-model` | Sales | Structured pipeline forecasting and commentary |
Have a skill idea? [Open an issue](../../issues) or raise it in [Discussions](../../discussions).
@@ -157,13 +299,67 @@ Have a skill idea? [Open an issue](../../issues) or raise it in [Discussions](..
---
## 📦 All Plugin Bundles
Install the whole library or just the bundles you need:
# Install everything
/plugin marketplace add https://github.com/mohitagw15856/pm-claude-skills
# Install by profession
claude plugin install pm-essentials@pm-claude-skills
claude plugin install pm-discovery@pm-claude-skills
claude plugin install pm-planning@pm-claude-skills
claude plugin install pm-delivery@pm-claude-skills
claude plugin install pm-analytics@pm-claude-skills
claude plugin install pm-strategy@pm-claude-skills
claude plugin install pm-advanced@pm-claude-skills
claude plugin install pm-rituals@pm-claude-skills
claude plugin install pm-gtm@pm-claude-skills
claude plugin install pm-engineering@pm-claude-skills
claude plugin install pm-data@pm-claude-skills
claude plugin install pm-people@pm-claude-skills
claude plugin install pm-design@pm-claude-skills
claude plugin install pm-business@pm-claude-skills
claude plugin install pm-legal@pm-claude-skills
claude plugin install pm-finance@pm-claude-skills
claude plugin install pm-hr@pm-claude-skills
claude plugin install pm-sales@pm-claude-skills
claude plugin install pm-operations@pm-claude-skills
claude plugin install pm-research@pm-claude-skills
claude plugin install pm-cross@pm-claude-skills
claude plugin install pm-figma@pm-claude-skills
---
## 🛠️ Custom Skills for Your Team
The 90 skills in this library are built for general professional workflows. But the most powerful version of Claude Skills is one built specifically for *your* team — your templates, your terminology, your processes, your quality standards.
**What custom skills look like in practice:**
- A law firm's contract review skill trained on their specific clause library and risk tolerance
- A SaaS company's sprint brief skill that knows their engineering conventions and definition of done
- A finance team's board pack skill that follows their exact narrative structure and slide format
- An HR team's job description skill that reflects their values language and includes their specific benefits
The difference between a generic skill and one built for your context is significant. Generic skills eliminate the blank page. Custom skills eliminate the rework.
**If you want skills built for your team's specific workflows — [get in touch](mailto:mohit15856@gmail.com).**
Include a brief description of your team, the workflows you want to automate, and the tools you use. I'll come back to you within 48 hours.
---
## 📖 How Skills Work
Skills are markdown files in `~/.claude/skills/` that Claude reads dynamically. When you describe a task, Claude scans available skill descriptions (~100 tokens) and loads the full skill only when it's relevant. This means:
Skills are markdown files that Claude reads dynamically. When you describe a task, Claude scans available skill descriptions (~100 tokens) and loads the full skill only when relevant. This means:
- Skills are efficient — they only use tokens when triggered
- Multiple skills can coexist without slowing Claude down
- Personal skills (`~/.claude/skills/`) work across all your projects
- Plugin skills install via the Claude Code marketplace with one command
Learn more: [Anthropic's Skills documentation](https://code.claude.com/docs/en/skills)
@@ -171,8 +367,8 @@ Learn more: [Anthropic's Skills documentation](https://code.claude.com/docs/en/s
## ⭐ If this is useful
Star the repo so others can find it. And if you build something with these skills, share it — raise a PR, open a discussion, or tag me in your article.
Star the repo so others can find it. And if you build something with these skills — raise a PR, open a discussion, or tag me in your article.
---
*Built and maintained by [Mohit Aggarwal](https://medium.com/@mohit15856) | [Product Powerhouse publication](https://medium.com/product-powerhouse)*
*Built and maintained by [Mohit Aggarwal](https://medium.com/@mohit15856) | [Product Notes publication](https://medium.com/product-powerhouse)*
+55
View File
@@ -0,0 +1,55 @@
# Security Policy
## Overview
This repository contains Claude Skill files — plain markdown instruction files that teach Claude how to perform professional tasks. There are no backend services, APIs, authentication systems, or databases in this repo.
That said, security matters here in two specific ways: **skill file safety** and **prompt injection risks**.
## Supported Versions
| Version | Supported |
|---|---|
| v4.0.0 (latest) | ✅ Active |
| v3.0.0 | ✅ Security fixes only |
| < v3.0.0 | ❌ No longer supported |
## Skill File Safety
All skills in this repo are reviewed before merging to ensure they:
- Do not contain instructions designed to manipulate Claude into ignoring its guidelines
- Do not attempt prompt injection (e.g. hidden instructions to override system behaviour)
- Do not instruct Claude to request, store, or transmit personal or sensitive data
- Do not contain malicious commands disguised as skill instructions
- Do not include hardcoded credentials, API keys, or personally identifiable information
**If you are installing skills from this repo:** skills are plain text markdown files. They do not execute code, make network requests, or access your file system on their own. Review any skill file before installing if you have concerns.
## Reporting a Vulnerability
If you discover a skill file in this repo that contains malicious instructions, a prompt injection attempt, or any content that could cause harm to users of Claude Code, please report it **privately** before raising a public issue.
**How to report:**
Email: **mohit15856@gmail.com**
Subject line: `[SECURITY] pm-claude-skills — <brief description>`
Include:
- The skill file path (e.g. `plugins/pm-gtm/skills/go-to-market/SKILL.md`)
- A description of the issue
- Why you believe it is a security concern
**Response time:** You will receive an acknowledgement within 48 hours and a resolution or update within 7 days.
Please do not open a public GitHub Issue for security vulnerabilities — use the email above. Public disclosure before a fix is in place puts other users at risk.
## Community Contributions
All pull requests adding new skill files are reviewed for the safety criteria listed above before merging. If you are submitting a skill, ensure it:
- Only contains instructions relevant to the stated professional workflow
- Does not include any attempt to override Claude's built-in guidelines
- Does not ask Claude to collect or relay user data
See [CONTRIBUTING.md](CONTRIBUTING.md) for full contribution guidelines.
+36
View File
@@ -0,0 +1,36 @@
#!/bin/bash
# =============================================================================
# create-plugin-json-pm-figma.sh
# Run from the ROOT of your pm-claude-skills repo.
# Creates the .claude-plugin/plugin.json for the pm-figma bundle.
# =============================================================================
set -e
if [ ! -d "$(pwd)/plugins" ]; then
echo "ERROR: Run from the root of pm-claude-skills"
exit 1
fi
mkdir -p plugins/pm-figma/.claude-plugin
cat > plugins/pm-figma/.claude-plugin/plugin.json << 'EOF'
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-figma",
"version": "1.0.0",
"description": "Figma skills for product managers and designers: Component Audit, Design Brief, Annotation Guide, Design Review, User Flow Planner, Variant Matrix, Spacing System, Prototype Plan, Design QA, PM Design Critique. Work smarter in Figma across the full design lifecycle.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["figma", "design", "product-management", "design-system", "components", "prototype", "handoff", "ux"]
}
EOF
echo "✓ plugins/pm-figma/.claude-plugin/plugin.json created"
echo ""
echo "Next: run setup-pm-figma.sh then update-marketplace.sh"
+136
View File
@@ -0,0 +1,136 @@
# Examples: pm-figma Skills
## What this bundle does
10 Figma skills covering the full design lifecycle for product managers and designers — from planning what to design, through building components and prototypes, to QA before handoff.
---
## figma-component-audit
### Example 1 — Messy legacy library
**You say:**
> "Audit our Figma component library. We have buttons, inputs, cards, modals, and navigation components but the naming is all over the place and developers keep asking for states we haven't designed."
**Claude produces:**
**Audit Summary**
| Dimension | Status | Score |
|---|---|---|
| Naming consistency | 🔴 Poor | 3/10 |
| Component coverage | 🟡 Partial | 6/10 |
| Variant completeness | 🔴 Poor | 4/10 |
| Overall health | 🟡 Partial | 5/10 |
**Issue: Mixed capitalisation conventions**
- What's happening: `button-primary`, `Button/Primary`, `btn_primary` all exist in the same library
- Fix: Adopt PascalCase for components (`Button`), lowercase slash-separated for variants (`type/primary`, `size/large`, `state/default`)
- Before: `btn_primary_large_hover` → After: `Button` with variants `type/primary`, `size/large`, `state/hover`
**Missing states developers are asking for:**
| Component | Missing | Priority |
|---|---|---|
| Button | Active/pressed state | 🔴 High |
| Input | Error state with helper text | 🔴 High |
| Card | Skeleton loading state | 🟡 Medium |
---
## figma-design-brief
### Example 1 — PRD to design brief
**You say:**
> "Write a design brief for our new notification preferences feature. Users need to control which emails and push notifications they receive. Platform is iOS and Android. We need design ready in 2 weeks."
**Claude produces:**
**Feature:** Notification Preferences
**Platform:** iOS + Android | **Design due:** [2 weeks from today] | **Dev handoff:** [3 weeks]
**The goal:** Users can control their notification preferences without contacting support.
**Success looks like:** >80% of users who visit settings can update their preferences without a support ticket.
**Flows to design:**
1. Entry from Settings > Notifications
2. Toggle individual notification types on/off
3. Save preferences with confirmation
4. Error state if save fails
**Missing from current brief — open questions:**
- [ ] Are email and push controlled separately or together? (PM to confirm)
- [ ] What's the default state for new users? (PM to confirm)
---
## figma-design-qa
### Example 1 — Pre-handoff check
**You say:**
> "QA the checkout flow design before we hand it off to engineering. Web, using our custom design system, standard 30-minute QA."
**Claude produces:**
**Design QA Report: Checkout Flow**
**Overall status:** 🟡 Minor fixes needed
**Section 1: File Hygiene**
- All layers named semantically ✅
- No unused layers ✅
- Components from library ❌ — Order summary card is a detached copy
- Text uses text styles ✅
- Colours use variables ❌ — Button label in step 3 uses hardcoded #FFFFFF instead of `color.text.on-primary`
**Issues Found:**
- **Detached card component — 🟡 Fix before handoff**
- What: Order summary card (frame "Step 2 / Summary") is not linked to library
- Fix: Re-attach to `Card/Summary` library component
- Owner: Designer
---
## figma-design-critique-pm
### Example 1 — PM reviewing a dashboard design
**You say:**
> "Give me a PM critique of our new analytics dashboard design. User goal is to understand their campaign performance at a glance. Business goal is to reduce support tickets about 'why are my numbers down'."
**Claude produces:**
**PM Critique Summary**
Verdict: 🟡 Mostly on track with one significant gap
"The design successfully surfaces the top-line metrics above the fold and the date range selector is prominent. However, the design currently shows no contextual explanation for metric changes — a user whose conversions dropped 40% last week will still need to contact support because there's nothing in the design helping them understand why."
**Goal Alignment Check:**
| Goal | Status | Evidence |
|---|---|---|
| Understand performance at a glance | ✅ Yes | Top 4 KPIs are above fold, well-contrasted |
| Reduce "why are my numbers down" tickets | 🟡 Partial | Metrics shown but no context or anomaly explanation |
**PM Feedback:**
**Missing: Metric change context — 🔴 High impact**
- Observation: Metric cards show current value and % change vs prior period but no explanation of what drove the change
- User impact: A user seeing -40% conversions still has no information to act on without contacting support
- Business impact: Does not address the core support ticket driver — the "why"
- Evidence basis: Hypothesis (we should validate with support ticket analysis)
- Question for designer: Is there data available to surface top contributing factors? Even "top declining campaign" would help.
---
## Tips for best results
- For `figma-design-brief`: paste the actual PRD snippet or ticket — the more specific the requirement, the more useful the brief
- For `figma-design-qa`: describe the platform and design system explicitly — the checklist adapts to iOS vs Android vs Web
- For `figma-design-critique-pm`: always state the business metric — without it, feedback stays generic
- For `figma-variant-matrix`: name the component exactly as it will appear in Figma — Claude uses this for layer naming recommendations
- For `figma-user-flow-planner`: state the starting point and user type — these determine which edge cases are most likely
## Related skills
- `design-critique` — General UX critique using Gestalt and Nielsen heuristics (pm-design bundle)
- `ux-research-plan` — Full research plan for user testing (pm-design bundle)
- `figma-prototype-plan` — Plan what to prototype before building it (this bundle)
BIN
View File
Binary file not shown.
BIN
View File
Binary file not shown.
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-cross",
"version": "1.0.0",
"description": "Cross-profession skills: Press Release, Grant Proposal, Executive Summary. Write journalist-ready press releases, structure grant applications aligned to funder priorities, and produce decision-ready executive summaries for any audience.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["communications", "press-release", "grant", "executive-summary", "briefing", "funding", "media"]
}
@@ -0,0 +1,98 @@
---
name: executive-summary
description: "Write an executive summary for any document, report, or proposal. Use when asked to write an executive summary, management summary, briefing paper, or one-pager for senior stakeholders. Produces a structured summary that busy executives can read in under 3 minutes and act on."
---
# Executive Summary Skill
Writes executive summaries that busy decision-makers actually read — front-loaded with conclusions, structured for skimming, ruthless about what to include.
## Required Inputs
- **Source document or topic** (paste or describe)
- **Audience** (CEO / board / investor / minister / client / committee)
- **Decision or action needed** (what should the reader do after reading?)
- **Length limit** (1 page / 2 pages / 500 words)
- **Format** (formal report / slide / email / briefing paper)
## Core Principle
An executive summary is NOT a summary of the document. It is a standalone document that:
- States the conclusion upfront — not at the end
- Contains only what the reader needs to make a decision
- Can be understood without reading anything else
- Recommends a specific action
## Output Structure
---
### [Title]
**Executive Summary**
*Prepared for: [Audience] | Date: [Date] | Author: [Name]*
---
**Bottom line up front:**
[The most important thing. The recommendation or finding. 2-3 sentences. A reader who only reads this should know what you are asking or telling them.]
---
**Background (why this matters):**
[2-3 sentences. Minimum context to understand the bottom line. Not the history — just what the reader needs now.]
---
**Key findings / analysis:**
- **[Finding 1]:** [One sentence — specific and evidence-based]
- **[Finding 2]:** [One sentence]
- **[Finding 3]:** [One sentence]
---
**Options considered:** (include only if a decision is being presented)
| Option | Benefit | Risk | Recommendation |
|---|---|---|---|
| [Option A] | [Benefit] | [Risk] | Recommended |
| [Option B] | [Benefit] | [Risk] | Not recommended |
---
**Recommendation:**
[Specific. "We recommend [action] because [reason]. This will [outcome]." Not "we suggest consideration of options."]
---
**Immediate next steps:**
- [Action 1 — specific, with owner and date]
- [Action 2]
---
**Risks of inaction:** [What happens if the reader does nothing]
**Full report:** [Reference to where the full document can be found]
---
## Adapting for Different Audiences
**CEO/MD:** Lead with financial or strategic impact. 1 page. Make the decision binary. Ask in sentence one.
**Board:** Lead with governance or risk. Frame against organisational objectives. State specifically what you need from them.
**Investor:** Lead with return or opportunity. Specific numbers. 1 page. Anticipate "why now."
**Minister/senior public sector:** Lead with public benefit or policy alignment. Include cost-benefit framing.
**Client:** Lead with their problem. Show you understand before presenting recommendation.
## Quality Checks
- Bottom line in first 3 sentences
- Standalone — no need to read full document
- Recommendation is specific
- Fits length limit
- Written for audience priorities not author priorities
- Next steps have owners and dates
## Example Trigger Phrases
- "Write an executive summary of this report: [paste]"
- "Summarise this document for the board: [paste]"
- "Create a one-pager from this proposal for the CEO"
- "Turn these findings into an exec summary"
@@ -0,0 +1,99 @@
---
name: grant-proposal
description: "Write a structured grant proposal or funding application for any grant type. Use when asked to write a grant proposal, funding application, research grant, charitable grant, or innovation fund application. Produces a complete proposal with project summary, rationale, methodology, impact, and budget narrative."
---
# Grant Proposal Skill
Produces structured grant proposals tailored to the funder priorities — the most common reason grants fail is writing about what you want to do rather than what the funder wants to fund.
## Required Inputs
- **Funder name and grant programme**
- **Grant amount sought**
- **Project description** (rough notes are fine)
- **Your organisation** (type, track record, capacity)
- **Funder stated priorities** (copy from their guidance — essential)
- **Word or page limits**
- **Deadline**
## Output Structure
---
### Project Title
[Informative and memorable. Should convey the problem being solved and the approach.]
### 1. Project Summary / Abstract (200-300 words — written last, placed first)
[What you will do, why it matters, who will benefit, measurable outcomes. Every sentence earns its place.]
### 2. Problem Statement / Need
- **The problem:** [Specific, evidenced — use data]
- **Who is affected:** [Population, scale, geography]
- **Current situation:** [What exists and why it is insufficient]
- **Consequence of inaction:** [What happens if not funded]
- **Why your organisation:** [Track record, relationships, expertise]
Funder test: does this problem align with [funder] stated priorities? Make the connection explicit.
### 3. Project Objectives
3-5 SMART objectives:
- **Objective 1:** [Specific, Measurable, Achievable, Relevant, Time-bound]
### 4. Methodology / Approach
**Phase 1: [Name]** (Months 1-X)
[What will happen, who will do it, what is produced]
**Key activities:**
- [Activity — specific]
**What makes this approach innovative or effective:** [Why this over alternatives]
### 5. Impact and Outcomes
| Level | Description | Measure |
|---|---|---|
| Output | [Tangible deliverable] | [How counted] |
| Short-term outcome | [Immediate change] | [How measured] |
| Medium-term outcome | [Behaviour change] | [How measured] |
| Long-term impact | [Systemic change] | [How evidenced] |
**Direct beneficiaries:** [Who and how many]
**Sustainability:** [How work continues beyond grant period]
### 6. Evaluation Plan
- Who evaluates, how, when, what is measured, how findings are shared
### 7. Budget Narrative
| Budget line | Amount | Justification |
|---|---|---|
| Staff costs | £[amount] | [Role, % FTE, duration, salary] |
| Travel | £[amount] | [Specific journeys named] |
| Equipment | £[amount] | [Itemised] |
| Indirect costs | £[amount] | [[X]% of direct — check policy] |
| **Total** | **£[total]** | |
**Value for money:** [Cost per beneficiary. What could not be done without this grant]
### 8. Organisational Capacity
[Track record of similar projects, governance, financial management. Name previous grants and outputs — be specific]
### 9. Risk Register
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| [Risk] | H/M/L | H/M/L | [Specific mitigation] |
---
## Funder Alignment Check
- Every section explicitly references funder stated priorities
- Word limits respected
- Budget aligns with eligible costs policy
- Required attachments prepared
## Example Trigger Phrases
- "Write a grant proposal for [project] applying to [funder]"
- "Help me write a funding application for [grant programme]"
- "Turn these project notes into a grant proposal: [paste]"
@@ -0,0 +1,71 @@
---
name: press-release
description: "Write a professional press release for any announcement. Use when asked to write a press release, media announcement, news release, or press statement. Produces a structured press release with headline, dateline, body, boilerplate, and media contact — ready to send to journalists."
---
# Press Release Skill
Writes press releases that journalists actually read — structured around the news angle, not the desire to promote.
## Required Inputs
- **The news** (what is actually happening — be specific)
- **Company name**
- **Date of announcement / embargo date**
- **Key quote** (from which executive and approximately what they want to say)
- **Why this matters** (to the reader, not the company)
- **Target media** (trade / national / local / consumer / investor)
- **Media contact details**
## Output Structure
---
FOR IMMEDIATE RELEASE / EMBARGOED UNTIL: [Date and time]
---
# [Headline — active verb, specific news, under 10 words]
## [Subheadline — the so-what in one sentence, adds context not repetition]
**[City, Date]** — [Opening paragraph: Who, What, When, Where, Why in 2-3 sentences. A journalist should be able to run this paragraph alone. No background, no context, no company history.]
[Second paragraph: the significance. Why does this matter? What does it mean for customers or the industry?]
[Third paragraph: quote from executive. Human and specific. Not a restatement of the headline.]
"[Quote text — specific, adds something the facts do not say]," said [Name], [Title] at [Company]. "[Second sentence extending the thought]."
[Fourth paragraph: supporting detail — data, customer names with permission, additional context]
[Fifth paragraph optional: what happens next, when it goes live, what people can do]
---
ENDS
---
**Notes to editors:**
**About [Company]**
[Boilerplate: 3-4 sentences. What the company does, when founded, where based, key facts. Factual not promotional.]
**Media contact:**
[Name] | [Title] | [Email] | [Phone] | [Hours/timezone]
---
## Headline Rules
- Active voice: "Company launches X" not "X is launched by Company"
- Specific: "raises 5M" not "secures significant investment"
- Under 10 words
- Never start with the company name — lead with the news
## Journalist Test
Would a journalist care? Is the headline the full story? Is there a human angle? Is the quote something a human would say? Can the first paragraph stand alone?
## Example Trigger Phrases
- "Write a press release announcing [news]"
- "Draft a media statement about [event]"
- "We are launching [product] — write the press release"
- "Turn this announcement into a press release: [paste notes]"
BIN
View File
Binary file not shown.
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-figma",
"version": "1.0.0",
"description": "Figma skills for product managers and designers: Component Audit, Design Brief, Annotation Guide, Design Review, User Flow Planner, Variant Matrix, Spacing System, Prototype Plan, Design QA, PM Design Critique. Work smarter in Figma across the full design lifecycle.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["figma", "design", "product-management", "design-system", "components", "prototype", "handoff", "ux"]
}
@@ -0,0 +1,64 @@
---
name: figma-annotation-guide
description: "Generate structured developer handoff annotations for a Figma screen or component. Use when asked to write Figma annotations, create dev handoff notes, document a Figma design for developers, or write specs for a screen. Produces a complete annotation set covering interactions, states, spacing, accessibility, and edge cases."
---
# Figma Annotation Guide Skill
Produces a complete set of developer handoff annotations for a Figma screen or component — the notes that turn a visual design into a buildable spec.
## Required Inputs
- **Screen or component description** (describe or summarise what was designed)
- **Platform** (iOS / Android / Web / React Native)
- **Interaction type** (static / interactive / animated / form)
- **Developer audience** (mobile / frontend / full-stack)
## Output Structure
### 1. Screen/Component Overview
Name, purpose, entry points, exit points.
### 2. Interaction Annotations
**[Element name]**
- Default state: [Visual description]
- On tap/click: [Exact action — API call, state change, navigation]
- Loading state: [Description]
- Success state: [What happens after]
- Error state: [What error looks like and user options]
- Disabled condition: [When and why]
### 3. State Inventory
| Element | States Required |
|---|---|
| [Element] | Default, Hover, Active, Disabled, Loading, Error, Empty |
Flag missing designs: "Warning: Error state not designed — needed before build"
### 4. Spacing and Layout Notes
Fixed vs fluid elements, scroll behaviour, breakpoints, safe areas.
### 5. Content and Copy Rules
Character limits, dynamic vs static content, truncation rules, empty states.
### 6. Accessibility Annotations
Touch targets, screen reader labels, focus order, colour contrast, motion preferences.
### 7. Edge Cases and Developer Questions
- [ ] [Unresolved question for developer to flag]
## Quality Checks
- [ ] Every interactive element has all states defined
- [ ] State inventory flags missing designs
- [ ] Accessibility covers touch targets and screen reader labels
- [ ] Empty states specified
- [ ] Edge cases listed as actionable questions
## Example Trigger Phrases
- "Write dev annotations for this Figma screen"
- "Create developer handoff notes for [screen/component]"
- "Document this design for the engineering team"
- "Write the Figma spec for [feature]"
- "What should I annotate before handing off this design?"
@@ -0,0 +1,74 @@
---
name: figma-component-audit
description: "Audit a Figma component library for consistency, coverage gaps, and naming issues. Use when asked to audit components, review a design system, check component consistency, identify missing components, or assess Figma library health. Produces a structured audit report with issues prioritised by impact, naming recommendations, and a fix plan."
---
# Figma Component Audit Skill
Produces a structured audit of a Figma component library — identifying inconsistencies, naming problems, coverage gaps, and prioritised recommendations.
## Required Inputs
- **Component list or description** (paste component names or describe what exists)
- **Product type** (mobile app / web app / desktop / multi-platform)
- **Design system maturity** (new / growing / mature / legacy)
- **Primary concern** (optional)
## Output Structure
### 1. Audit Summary
| Dimension | Status | Score |
|---|---|---|
| Naming consistency | Red/Amber/Green | /10 |
| Component coverage | | /10 |
| Variant completeness | | /10 |
| Documentation | | /10 |
| Overall health | | /10 |
**Verdict:** What is the state of this library and the single most important thing to fix?
### 2. Naming Issues
For each problem:
**Issue: [Problem type]**
- What is happening: [Specific examples]
- Why it matters: [Impact on designers and developers]
- Fix: [Exact naming convention to adopt]
- Examples: Before / After
Naming convention to enforce:
- Components: PascalCase (NavigationBar)
- Variants: Lowercase with slashes (size/large, state/hover)
- Pages: All caps (COMPONENTS, FOUNDATIONS)
### 3. Coverage Gaps
| Missing Component | Priority | Why Needed |
|---|---|---|
| [Component] | High/Medium/Low | [Use case] |
### 4. Variant Completeness Check
| Component | Default | Hover | Active | Disabled | Error | Missing |
|---|---|---|---|---|---|---|
| [Button] | Yes | Yes | No | Yes | No | Active, Error |
### 5. Prioritised Fix Plan
| # | Fix | Effort | Impact | Do First? |
|---|---|---|---|---|
| 1 | [Fix] | Low/Med/High | High | Yes |
## Quality Checks
- [ ] Naming recommendations have before/after examples
- [ ] Coverage gaps are relevant to the product type
- [ ] Fix plan is ordered by impact-to-effort ratio
- [ ] Variant completeness covers all interactive states
## Example Trigger Phrases
- "Audit my Figma component library"
- "Review our design system for consistency issues"
- "What components are we missing in our Figma library?"
- "Our component naming is a mess — help me fix it"
- "Do a health check on our Figma components"
@@ -0,0 +1,68 @@
---
name: figma-design-brief
description: "Write a structured design brief for a Figma design task from a product requirement or feature request. Use when asked to write a design brief, create a design spec for Figma, turn a PRD into design requirements, or brief a designer on what to build in Figma. Produces a brief with goals, scope, user flows, components needed, constraints, and success criteria."
---
# Figma Design Brief Skill
Converts a product requirement or feature request into a structured design brief — everything a designer needs to open Figma and start building confidently.
## Required Inputs
- **Feature or requirement** (paste PRD snippet, ticket, or describe the feature)
- **User goal** (what is the user trying to accomplish?)
- **Platform** (iOS / Android / Web / Responsive / All)
- **Existing components available** (optional)
- **Timeline** (when does design need to be ready?)
## Output Structure
### 1. Brief Header
Feature, PM, Designer, Platform, Design due, Dev handoff dates.
### 2. What We Are Designing and Why
- **The goal:** [One sentence — user problem being solved]
- **Context:** [2-3 sentences. Why now? What triggers this?]
- **Success looks like:** [Specific observable outcome]
### 3. User Flows to Design
**Flow N: [Flow name]**
- Entry point: [Where user starts]
- Steps: [Numbered key steps]
- Exit point: [Where flow ends]
- Edge cases: [empty state, error state, loading state]
### 4. Screens Required
| Screen | New / Update | Notes |
|---|---|---|
| [Screen] | New | [Key requirement] |
### 5. Components Needed
| Component | In library? | Action |
|---|---|---|
| [Component] | Yes/No/Needs variant | Use/Create/Extend |
### 6. Constraints and Requirements
- Must haves: [Non-negotiable constraints]
- Must avoid: [Design patterns to not use]
- Accessibility: [WCAG level, touch target sizes]
### 7. Open Questions
- [ ] [Question — with owner]
## Quality Checks
- [ ] Goal is outcome-focused (not "design the feature")
- [ ] All flows include edge cases
- [ ] Components table identifies create vs reuse
- [ ] Constraints include accessibility requirements
- [ ] Open questions have owners
## Example Trigger Phrases
- "Write a design brief for [feature]"
- "Turn this PRD into a Figma design brief"
- "Brief the designer on what to build for [requirement]"
- "Create a design spec for [feature] for Figma"
- "What does the designer need to know to design [feature]?"
@@ -0,0 +1,76 @@
---
name: figma-design-critique-pm
description: "Run a PM-perspective design critique focused on product outcomes, user goals, and business requirements — not aesthetics. Use when asked for a PM design critique, a product review of a design, feedback on a Figma design from a product perspective, or when you want to critique a design without being a designer. Produces structured outcome-based feedback tied to user goals and business metrics."
---
# Figma Design Critique — PM Perspective Skill
This skill is specifically for product managers critiquing designs — focused on whether the design achieves the user goal and business outcome, not whether it looks good. Different from the general design-critique skill which covers UX aesthetics; this one centres product thinking.
## Required Inputs
- **Design description or screen summary**
- **User goal** (what is the user trying to accomplish?)
- **Business goal** (what outcome does the product need?)
- **Original requirements** (what was this supposed to do?)
- **Key metric** (what would move if this design works?)
## Output Structure
### 1. PM Critique Summary
User goal, business goal restated.
**Verdict:** On track / Mostly on track / Needs rethinking
One-paragraph summary: what works from a product perspective, and the single most important thing to address.
### 2. Goal Alignment Check
| Goal | Design supports it? | Evidence |
|---|---|---|
| [User goal] | Yes/Partial/No | [Specific observation] |
| [Business goal] | Yes/Partial/No | [Observation] |
| [Key requirement] | Yes/Partial/No | [Observation] |
### 3. PM Feedback (Outcome-Focused)
Every concern must tie to an outcome. "I do not like this layout" is not PM feedback. "This layout puts the primary action below the fold, which will reduce mobile conversion" is PM feedback.
**[Concern] — High/Medium/Low impact**
- Observation: [Neutral description of what the design does]
- User impact: [What this means for the user goal]
- Business impact: [What this means for the metric]
- Evidence basis: [Research/data/analogous patterns/hypothesis — be honest]
- Question for designer: [What to explore — not a directive]
### 4. What the Design Does Well
2-4 specific things working well from a product perspective — with evidence. Not "colours are nice" but "primary CTA is the most prominent element, aligning with conversion goal." Always include this section.
### 5. Questions Before Next Iteration
| Question | Who answers | Why it matters |
|---|---|---|
| [Question] | Designer/PM/Eng | [Impact] |
### 6. PM Recommendation
Approve / Approve with changes (list) / Revise and re-review (one focus area only)
## PM Critique Rules
- Never reference aesthetics as reason for feedback — only outcomes
- "I prefer" is not feedback — "users are likely to" is feedback
- Lead with what is working before what is not
- Ask questions before giving directives
- One primary recommendation — not a redesign in bullets
## Quality Checks
- [ ] Every concern tied to user or business outcome
- [ ] What is working section is genuine and specific
- [ ] Questions section included (not just directives)
- [ ] PM recommendation is explicit
- [ ] Evidence basis stated honestly
## Example Trigger Phrases
- "Give me a PM critique of this design"
- "Review this design from a product perspective"
- "What product feedback do I have on this Figma design?"
- "Critique this design without being a designer"
- "Does this design achieve the user goal?"
@@ -0,0 +1,88 @@
---
name: figma-design-qa
description: "Run a pre-handoff QA checklist on any Figma design before it goes to engineering. Use when asked to QA a Figma design, do a pre-handoff check, review a design before engineering, or validate a Figma file is ready to build. Produces a structured QA checklist covering file hygiene, component usage, accessibility, and handoff readiness with pass/fail status."
---
# Figma Design QA Skill
Runs a systematic pre-handoff QA check on a Figma design — catching issues that cause engineering back-and-forth before they become expensive.
## Required Inputs
- **Feature or screen being QA-d**
- **Platform** (iOS / Android / Web)
- **Design system** (custom / Material / HIG / None)
- **Handoff tool** (Figma Inspect / Zeplin / Storybook / Direct link)
- **QA depth** (quick 15 min / standard 30 min / thorough 60 min)
## Output Structure
QA Report: [Feature] | [Date] | [Platform]
**Overall status:** Ready / Minor fixes needed / Not ready
### Section 1: File Hygiene
- All layers named semantically (no "Rectangle 12")
- No unused/hidden layers in final frames
- Components from library (not detached copies)
- All text uses text styles (not manual font settings)
- All colours use styles or variables (not hex overrides)
- Frames named to match screen map
- No leftover prototype wires to wrong frames
### Section 2: Component Usage
- All buttons use library component
- All inputs use library component
- All icons from approved icon library
- No custom components that should be in library
- Variants used correctly (right size, state, type)
### Section 3: Content and Copy
- No placeholder text (Lorem ipsum) in final designs
- All copy reviewed and approved
- Realistic content used (not "User Name")
- Long text edge cases tested
- Error messages are human-readable
- Empty states have copy and CTA
### Section 4: States and Coverage
- Default, Loading, Empty, Error, Success states
- Interactive elements have hover/active (web)
- Disabled states designed where applicable
### Section 5: Accessibility
- All text meets WCAG AA contrast (4.5:1 body, 3:1 large)
- UI components meet 3:1 contrast against background
- Touch targets minimum 44x44pt iOS / 48x48dp Android
- Focus states for keyboard/switch navigation (web)
- Information not conveyed by colour alone
- Icons have text labels or accessible names annotated
### Section 6: Handoff Readiness
- Dev annotations on non-obvious interactions
- Spacing uses Auto Layout (not absolute positioning)
- Images/assets exported at correct resolutions
- Design matches approved requirements
- Link to prototype included
### Issues Found
For each fail:
**[Issue] — Blocking / Fix before handoff / Fix in next iteration**
- What: [Specific layer/screen/element]
- Fix: [Exact action needed]
- Owner: [Designer/PM/Both]
### Handoff Decision
Status, signed off by, date.
## Quality Checks
- [ ] All 6 sections completed
- [ ] Every fail has a specific description and fix action
- [ ] Blocking issues separated from minor ones
- [ ] Handoff decision is explicit
## Example Trigger Phrases
- "QA this Figma design before handoff"
- "Run a pre-handoff check on [feature] design"
- "Is this Figma design ready for engineering?"
- "Do a design QA on [screen/feature]"
- "What needs fixing before we hand this off?"
@@ -0,0 +1,68 @@
---
name: figma-design-review
description: "Run a structured PM design review against product requirements. Use when asked to review a Figma design, check a design against requirements, do a PM design review, or assess whether a design meets the product spec. Produces a requirements coverage check, UX concerns, open questions, and explicit approval status."
---
# Figma Design Review Skill
Runs a structured PM design review — checking that a design meets product requirements, covers all user flows, and is ready for engineering. This is a requirements-and-outcomes review, not an aesthetic critique.
## Required Inputs
- **Design description or screen summary**
- **Original requirements** (PRD snippet, ticket, or acceptance criteria)
- **User flow being designed**
- **Review stage** (concept / mid-fidelity / pre-handoff final)
## Output Structure
### 1. Review Header
Feature, review stage, reviewed by, date.
**Overall status:** Approved / Approved with changes / Needs revision
### 2. Requirements Coverage Check
| Requirement | Covered? | Notes |
|---|---|---|
| [Requirement from PRD] | Yes/No/Partial | [Specific observation] |
Missing coverage summary: [Requirements not addressed — must resolve before approval]
### 3. User Flow Completeness
| Flow step | Designed? | Issues |
|---|---|---|
| [Step] | Yes/No/Partial | [Issue] |
| Error state | Yes/No | |
| Empty state | Yes/No | |
| Loading state | Yes/No | |
### 4. PM Concerns
**[Concern] — Blocking / Should fix / Nice to fix**
- What: [Specific observation]
- Why it matters: [Business or user impact — not aesthetic preference]
- Suggested resolution: [What PM wants to see]
### 5. Open Questions
| Question | Owner | Needed by |
|---|---|---|
| [Question] | Designer/Eng/PM | [Date] |
### 6. Approval Decision
Approved / Approved with changes (list) / Needs revision (focus area + next review date)
## Quality Checks
- [ ] Every requirement assessed
- [ ] All flow states checked (error, empty, loading)
- [ ] Concerns are outcome-focused not aesthetic
- [ ] Open questions have owners
- [ ] Approval status is explicit
## Example Trigger Phrases
- "Review this Figma design against the requirements"
- "Do a PM design review for [feature]"
- "Check if this design meets the product spec"
- "Is this design ready to hand off to engineering?"
- "What is missing from this design before we can build it?"
@@ -0,0 +1,84 @@
---
name: figma-prototype-plan
description: "Plan prototype interactions and flows for user testing in Figma. Use when asked to plan a Figma prototype, set up prototype interactions, define what to prototype for a user test, or prepare a Figma prototype for usability testing. Produces a prototype scope, interaction specification, test task scripts, and Figma setup guide."
---
# Figma Prototype Plan Skill
Plans what to prototype in Figma and how — scoping to what the user test needs, defining every interaction, and setting up the test scenarios. Prevents over-building and ensures the prototype answers the research question.
## Required Inputs
- **Research question** (what are you trying to learn?)
- **Feature or flow being prototyped**
- **Prototype fidelity** (low wireframe / mid functional / high pixel-perfect)
- **Testing method** (moderated in-person / moderated remote / unmoderated)
- **Number of test tasks**
## Output Structure
### 1. Prototype Scope
**In scope:** [Flows with real interactions — specific screens listed]
**Out of scope:** [Screens to show as static — not worth building as interactive]
**Rationale:** Prototypes should be the minimum needed to test the hypothesis.
### 2. Interaction Specification
**Interaction N: [Description]**
- Trigger: Tap/Swipe/Hover/Form submit
- Element: [Figma layer name]
- Destination: [Figma frame name]
- Animation: Instant/Dissolve/Push left/Push right/Slide up
- Timing: [ms]
- Reset after: Yes/No
### 3. Prototype Flow Diagram
```
[Start frame]
-> Tap "Action"
[Next frame]
-> Tap "Complete" -> [Success frame]
-> Tap "Cancel" -> [Back to start]
```
### 4. Test Task Scripts
**Task N: [Title]**
Scenario (read to participant):
"[Realistic scenario giving context without directing the click path]"
Observing:
- [What to watch for]
Success when: [Specific trigger]
### 5. Figma Setup Guide
- Starting frame: [Name]
- Device preview: [Device]
- Prototype settings: background colour, show device, type
- Sharing: Can view link, reset process between participants
### 6. Build vs Fake Table
| Element | Build | Fake | Notes |
|---|---|---|---|
| Primary CTA flow | Yes | | Core to research |
| Secondary nav | | Yes | Not being tested |
| Error state | Yes | | Testing recovery |
## Quality Checks
- [ ] Scope limited to what the research question requires
- [ ] Every interaction has a named destination frame
- [ ] Task scripts are scenario-based (not "click on X")
- [ ] Success criteria defined for each task
- [ ] Reset process defined for between participants
## Example Trigger Phrases
- "Plan the Figma prototype for our user test on [feature]"
- "What interactions do I need to build for this prototype?"
- "Help me set up a Figma prototype for [research question]"
- "Write the test task scripts for our [feature] prototype"
- "What should I prototype vs leave as static screens?"
@@ -0,0 +1,77 @@
---
name: figma-spacing-system
description: "Design a spacing and layout token system for a Figma design system. Use when asked to create a spacing system, define layout tokens, set up a grid system, build a spacing scale, or establish layout foundations for a Figma file. Produces a complete spacing scale, grid definition, component spacing conventions, and Figma implementation guide."
---
# Figma Spacing System Skill
Produces a complete spacing and layout token system — the foundation that makes a design system consistent and developer handoff unambiguous.
## Required Inputs
- **Platform** (iOS / Android / Web / Multi-platform)
- **Base unit** (4px / 8px — default to 8px)
- **Design system name** (for token naming)
- **Component density** (compact / standard / comfortable)
- **Grid requirements** (or "derive from platform standard")
## Output Structure
### 1. Base Unit
[4px or 8px] with rationale. All values must be multiples.
### 2. Spacing Scale
| Token | Value | Use case |
|---|---|---|
| spacing.none | 0px | Removing space intentionally |
| spacing.xs | 4/8px | Icon padding, tight labels |
| spacing.sm | 8/12px | Internal component padding compact |
| spacing.md | 12/16px | Internal component padding standard |
| spacing.lg | 16/24px | Section padding, card internal |
| spacing.xl | 24/32px | Between components |
| spacing.2xl | 32/48px | Section separation |
| spacing.3xl | 48/64px | Page-level breaks |
| spacing.4xl | 64/96px | Hero sections |
### 3. Layout Grid
Mobile (375px): 4 columns, margin [value], gutter [value]
Tablet (768px): 8 columns, margin [value], gutter [value]
Desktop (1440px): 12 columns, margin [value], gutter [value], max content width [value]
### 4. Component Spacing Conventions
| Context | Token | Example |
|---|---|---|
| Button horizontal padding | spacing.md | Left/right |
| Button vertical padding | spacing.sm | Top/bottom |
| Card internal padding | spacing.lg | All sides |
| Input padding | spacing.sm vertical, spacing.md horizontal | |
| Icon gap from label | spacing.xs | |
| Section gap | spacing.xl | |
### 5. Figma Implementation
1. Create SPACING page documenting each token visually
2. Resources > Variables > create Number collection named Spacing
3. Apply variables to Auto Layout padding/gap values
4. Share token names with engineers as-is or via Tokens Studio
### 6. Anti-Patterns to Avoid
- Values not on the scale (13px, 22px) — round to nearest token
- Absolute pixel values in components instead of tokens
- Mixing 4px and 8px base units in the same product
## Quality Checks
- [ ] All token values are multiples of the base unit
- [ ] Scale covers xs through 4xl
- [ ] Grid defined for all relevant breakpoints
- [ ] Component conventions cover common decisions
- [ ] Figma implementation steps included
## Example Trigger Phrases
- "Create a spacing system for our Figma design system"
- "Define our spacing tokens for Figma"
- "Set up a grid and spacing scale for [product]"
- "What spacing values should we use in our design system?"
- "Help me build the layout foundation for our Figma file"
@@ -0,0 +1,76 @@
---
name: figma-user-flow-planner
description: "Plan user flows and screen states for a Figma design before any designing starts. Use when asked to plan a user flow, map out screens for a feature, define screen states, plan a Figma file structure, or work out what needs to be designed before opening Figma. Produces a complete flow map with all screens, states, entry/exit points, and a suggested Figma page structure."
---
# Figma User Flow Planner Skill
Plans what needs to be designed before a pixel is touched — mapping all screens, states, entry points, and edge cases so designers do not discover missing states mid-build.
## Required Inputs
- **Feature or task being designed**
- **User type** (who performs this flow?)
- **Platform** (iOS / Android / Web / Multi-platform)
- **Starting point** (where does the user begin?)
- **Known edge cases** (optional)
## Output Structure
### 1. Flow Overview
Feature, user, goal, entry points, success exit, failure exits.
### 2. Screen Map
| # | Screen name | Type | Triggered by | Notes |
|---|---|---|---|---|
| 1 | [Screen] | New/Modal/Drawer/Toast | [What triggers] | [Considerations] |
Screen types to cover: entry, happy path, loading, success, error (network/validation/permission), empty, first-time/onboarding, edge cases.
### 3. State Matrix
**[Screen name]**
| State | Trigger | Visual change | Action available |
|---|---|---|---|
| Default | Page load | [Description] | [What user can do] |
| Loading | User taps action | Skeleton/spinner | None |
| Error | API failure | Error message | Retry/Go back |
| Empty | No data | Empty state | [CTA] |
### 4. Decision Points
**Decision: [Name]**
- If yes: [Screen N]
- If no: [Screen X]
### 5. Suggested Figma File Structure
```
Feature name/
- Cover
- Flow Map
- Happy Path
- Error States
- Empty States
- Edge Cases
- Handoff
```
### 6. What Not to Design Yet
[Explicit out-of-scope items — prevents scope creep]
## Quality Checks
- [ ] All three state types covered: loading, error, empty
- [ ] All decision points mapped with both branches
- [ ] Entry points include all realistic user paths
- [ ] Out-of-scope section is explicit
- [ ] Figma file structure matches screen map
## Example Trigger Phrases
- "Plan the user flow for [feature] in Figma"
- "What screens do I need to design for [feature]?"
- "Map out the states for [feature] before we start designing"
- "Help me structure my Figma file for [feature]"
- "What do we need to design before handing this to the developer?"
@@ -0,0 +1,78 @@
---
name: figma-variant-matrix
description: "Define component variants and states systematically for Figma. Use when asked to plan component variants, define states for a component, set up a Figma variant matrix, or work out what properties a component needs before building it. Produces a complete variant matrix with all properties, values, and combinations needed."
---
# Figma Variant Matrix Skill
Defines all variants, properties, and states a component needs before building it in Figma — preventing missing variants discovered after the component is already used across 40 screens.
## Required Inputs
- **Component name** (Button, Card, Input, Badge, Navigation item, etc.)
- **Component purpose** (what does it do, where is it used?)
- **Platform** (iOS / Android / Web / Multi-platform)
- **Design system context** (standalone / part of existing system)
## Output Structure
### 1. Component Overview
Name, category (Interactive/Display/Layout/Form/Navigation/Feedback), used in contexts.
### 2. Variant Properties
| Property | Values | Notes |
|---|---|---|
| Type | Primary, Secondary, Tertiary, Destructive | |
| Size | Large, Medium, Small | |
| State | Default, Hover, Active, Disabled, Loading | |
| Icon | None, Leading, Trailing, Only | |
Total combinations: [N]. Flag if over 50 — consider splitting into multiple components.
### 3. State Definitions
For each state, list only what changes from Default:
- Default: [Full visual spec]
- Hover (web): [Delta from default]
- Active/Pressed: [Delta]
- Disabled: [Delta — use layer-level properties, not opacity on whole component]
- Loading: [What replaces label, interactive during loading?]
- Error (forms): [Border colour, helper text, icon changes]
### 4. Anatomy Breakdown
| Layer name | Purpose | Required? | Notes |
|---|---|---|---|
| container | Background and bounds | Yes | |
| label | Text | Conditional | Hide when icon-only |
| icon-leading | Leading icon slot | No | |
### 5. Token Mapping
| Property | Token | Fallback |
|---|---|---|
| Background default | color.brand.primary | #hex |
| Border radius | radius.medium | 8px |
### 6. Build Order
1. Default state, most common variant
2. Convert to component, add properties
3. Size variants
4. State variants
5. Type variants
6. Icon slot variants last
## Quality Checks
- [ ] All interactive states defined
- [ ] Total variant count calculated, flagged if over 50
- [ ] Every layer named semantically
- [ ] Token mapping covers all visual properties
- [ ] Disabled state uses layer-level properties not opacity
## Example Trigger Phrases
- "Define the variants for a [component] in Figma"
- "What states does my [component] need?"
- "Help me plan the variant matrix for [component]"
- "Set up the Figma properties for a [button/card/input]"
- "What are all the combinations I need for my [component]?"
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-finance",
"version": "1.0.0",
"description": "Finance skills: Financial Model Narrative, Budget Variance Analysis, Investor Pitch Deck, Financial Due Diligence. Turn numbers into board-ready narratives, explain variances, structure pitch decks, and generate DD checklists.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["finance", "financial-model", "budget", "variance", "pitch-deck", "due-diligence", "investor"]
}
@@ -0,0 +1,60 @@
---
name: budget-variance-analysis
description: "Produce a structured budget variance analysis from actual vs budget figures. Use when asked to analyse budget variances, explain underspend or overspend, write a variance commentary, or investigate why actuals differ from plan. Produces a categorised variance table with root cause analysis and management commentary."
---
# Budget Variance Analysis Skill
Produces a complete variance analysis from numbers through to root cause explanation and management commentary.
## Required Inputs
- **Actuals and budget figures** (paste as table or describe line by line)
- **Period** (month / quarter / YTD)
- **Materiality threshold** (e.g. £10k or 5%)
- **Known reasons for variances** (if any)
- **Audience** (CFO / board / management / auditor)
## Output Structure
### 1. Variance Summary Table
| Line Item | Budget | Actual | Variance £ | Variance % | F/A |
|---|---|---|---|---|---|
| Revenue | | | | | |
| Cost of Sales | | | | | |
| Gross Profit | | | | | |
| Opex | | | | | |
| EBITDA | | | | | |
F = Favourable | A = Adverse
### 2. Material Variance Commentary
For each variance above threshold:
**[Line item] — £[amount] F/A ([%])**
- **Root cause:** [Specific explanation — not "timing" without detail]
- **Permanent or timing?** Will this reverse next period?
- **Management action:** What is being done
- **Forecast impact:** Does this change full-year outlook?
### 3. Top 3 Variances Requiring Attention
Ranked by materiality and strategic significance.
### 4. Forecast Revision
Does the full-year forecast need updating? State revised expectation and key assumptions.
### 5. Executive Summary
3-4 sentences of management commentary suitable for a board pack.
## Quality Checks
- All variances above threshold explained
- Root causes specific (not vague)
- Favourable/Adverse correctly labelled
- Forecast impact stated for material variances
## Example Trigger Phrases
- "Write a variance analysis for these actuals vs budget: [paste]"
- "Explain why we are over budget on [cost line]"
- "Write the variance commentary for our finance review"
- "Produce a budget vs actual analysis for Q[N]"
@@ -0,0 +1,76 @@
---
name: financial-due-diligence
description: "Generate a financial due diligence checklist and analysis framework for any investment, acquisition, or partnership. Use when asked for a due diligence checklist, M&A financial review, investment analysis framework, or vendor financial assessment."
---
# Financial Due Diligence Skill
Produces a structured financial due diligence framework — document request list and analytical questions — for any investment, acquisition, or significant commercial relationship.
## Required Inputs
- **Transaction type** (acquisition / investment / partnership / supplier / fundraise)
- **Stage of diligence** (initial screening / full DD / confirmatory)
- **Target company type** (startup / SME / listed / subsidiary)
- **Key concerns** (optional — e.g. revenue recognition, customer concentration)
## Output Structure
### 1. Document Request List
**Financial Statements**
- Audited accounts for last 3 years
- Management accounts for current year (monthly)
- Board-approved budget and latest reforecast
- 3-year financial model with assumptions
**Revenue**
- Revenue by customer (top 20, % of total)
- Revenue by product/segment
- Contracted vs recurring vs one-off breakdown
- Churn and renewal data
**Costs**
- Cost of sales breakdown
- Headcount by department with compensation detail
- Top 10 supplier contracts
**Cash and Debt**
- Bank statements (12 months)
- Debt schedule with covenants and maturity
- Working capital analysis
**Tax**
- Last 3 years tax returns
- Any open enquiries
- R&D tax credit claims
### 2. Key Analytical Questions
**Revenue quality:** Is revenue growing organically? What % is truly recurring? Customer concentration risk?
**Margin analysis:** Gross margin trend over 3 years? One-off items inflating EBITDA? Normalised EBITDA?
**Cash conversion:** Does profit convert to cash? Cash conversion cycle? Working capital red flags?
**Debt and liabilities:** Net debt position? Contingent liabilities? Covenant headroom?
### 3. Red Flags Checklist
- Revenue concentration over 30% in one customer
- Declining gross margins without explanation
- EBITDA-to-cash conversion below 70%
- Auditor qualifications or emphasis of matter
- Related party transactions not at arm length
- Aggressive revenue recognition
- Growing debtor days with no explanation
### 4. Summary Output Template
- Revenue quality: [Assessment]
- Margin sustainability: [Assessment]
- Cash generation: [Assessment]
- Balance sheet risk: [Assessment]
- Overall: Green Strong / Amber Acceptable / Red Material concerns
## Example Trigger Phrases
- "Give me a financial due diligence checklist for [company type]"
- "What documents should I request for financial DD?"
- "Build a DD framework for our Series A investment"
@@ -0,0 +1,62 @@
---
name: financial-model-narrative
description: "Turn financial model outputs into a clear written narrative. Use when asked to write a financial narrative, explain a financial model, summarise a P&L, or translate spreadsheet numbers into a board-ready story. Produces an executive narrative with key insights, drivers, and forward-looking commentary."
---
# Financial Model Narrative Skill
Turns financial model outputs into a clear, structured written narrative suitable for board packs, investor updates, or management reporting.
## Required Inputs
- **Financial data** (paste key figures: revenue, costs, margins, EBITDA, cash)
- **Period covered** (month / quarter / annual / multi-year)
- **Audience** (board / investors / management / bank / internal)
- **Key message** (what is the headline story?)
- **Actuals vs budget / prior period?** (comparison context)
## Output Structure
### 1. Headline Summary
3-5 sentences. The financial story in plain English. Lead with the most important insight — not "revenue was X" but what that figure means.
### 2. Revenue
- Performance vs prior period / budget
- Key drivers: what caused the movement
- Risks or opportunities in the revenue line
### 3. Costs and Margins
- Gross margin: % and trend
- Key cost movements and why
- EBITDA performance and drivers
- One-off items clearly flagged
### 4. Cash and Balance Sheet
- Cash position and movement
- Runway (for startups)
- Key working capital movements
### 5. Variance Analysis
For each significant variance:
**[Line item] — Over/Under by [amount]**
- **Cause:** [Plain English explanation]
- **Permanent or temporary?** One-time / Structural
- **Action being taken:** [If applicable]
### 6. Forward-Looking Commentary
- Expected next period
- Key risks to forecast
- Key opportunities
- Any reforecast or guidance change
## Writing Rules
- Never just restate a number — always explain what it means
- Flag variances over 10% automatically
- Use past tense for actuals, conditional for forecast
- One insight per paragraph
## Example Trigger Phrases
- "Write a financial narrative for these results: [paste numbers]"
- "Turn this P&L into a board narrative"
- "Write the finance section of our board pack"
- "Explain these financial results in plain English"
@@ -0,0 +1,48 @@
---
name: investor-pitch-deck
description: "Build the narrative and slide structure for an investor pitch deck. Use when asked to create a pitch deck, investor presentation, fundraising deck, or startup pitch. Produces a slide-by-slide structure with narrative beats, key messages, and what each slide must prove to an investor."
---
# Investor Pitch Deck Skill
Builds the complete narrative and slide structure for an investor pitch deck — focused on what investors need to see, not what founders want to show.
## Required Inputs
- **Company name and one-line description**
- **Stage** (Pre-seed / Seed / Series A / Series B)
- **Ask** (how much raising and what for)
- **Key metrics** (revenue, growth, users, retention)
- **Target investors** (generalist / sector-specific / angels)
- **Deck length** (10 / 12 / 15 slides)
## Output Structure
For each slide:
- **What this slide must prove** (the investor question it answers)
- **Content guidance** (specific, not generic)
- **Common mistake to avoid**
---
**Slide 1: Cover** — Proves you can say what you do in one sentence.
**Slide 2: Problem** — Proves the problem is real, painful, and large. Lead with the human problem, not market size.
**Slide 3: Solution** — Proves your solution is meaningfully better. Focus on outcome, not features.
**Slide 4: Product** — Proves this is real and works. Show the actual product.
**Slide 5: Traction** — Proves people want this. Show retention and revenue, not signups.
**Slide 6: Market** — Proves the market is large enough. Use bottoms-up TAM where possible.
**Slide 7: Business Model** — Proves you understand unit economics. Include CAC and LTV.
**Slide 8: Go-To-Market** — Proves you can acquire customers efficiently. Focus on what is actually working.
**Slide 9: Competition** — Proves you understand the landscape. Never say "no competitors."
**Slide 10: Team** — Proves this team can execute this opportunity. One sentence per person, specific.
**Slide 11: Financials** — Proves you understand your business. Show assumptions, not just projections.
**Slide 12: The Ask** — Proves you know exactly what you need. Specific use of funds and 18-month milestones.
## Narrative Principles
- Every slide answers one investor question
- Investors decide go/no-go on slides 1-5 — front-load evidence
- Keep to 10-12 slides for a first meeting
## Example Trigger Phrases
- "Build a pitch deck structure for [company]"
- "Help me structure my Series A deck"
- "What slides should my investor pitch have?"
BIN
View File
Binary file not shown.
+13
View File
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-hr",
"version": "1.0.0",
"description": "HR skills: Job Description Writer, Onboarding Plan, Employee Engagement Survey, Redundancy Consultation. Write inclusive JDs, build 30/60/90-day plans, design engagement surveys, and structure legally compliant redundancy processes.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["hr", "people", "job-description", "onboarding", "engagement", "redundancy", "recruitment"]
}
@@ -0,0 +1,86 @@
---
name: employee-engagement-survey
description: "Design an employee engagement survey and analyse results. Use when asked to create an employee survey, engagement questionnaire, pulse survey, or eNPS survey. Also use when asked to analyse survey results. Produces a complete survey with questions, rating scales, and an analysis framework."
---
# Employee Engagement Survey Skill
Designs complete employee engagement surveys and provides a framework for analysing and acting on results.
## Mode Detection
- User provides survey results -> Analysis mode
- User wants to create a survey -> Design mode
---
## Design Mode
### Required Inputs
- Survey type (annual / quarterly pulse / post-onboarding / exit / specific topic)
- Company size and stage
- Key areas of concern (optional)
- Anonymity approach
- Length target (short: 5-10 / standard: 15-25 / comprehensive: 30+)
### Opening Statement (always include)
"This survey is anonymous. Your responses help us understand what is working and what to improve. Results will be shared with [who] and we will communicate actions taken by [date]."
### Core Questions
**Overall Engagement**
1. On a scale of 0-10, how likely are you to recommend [Company] as a great place to work? (eNPS)
2. I feel proud to work at [Company]. [1-5]
3. I intend to still be working here in 12 months. [1-5]
**Role and Clarity**
4. I understand how my work contributes to company goals. [1-5]
5. I have the tools and resources I need to do my job. [1-5]
6. My workload is manageable. [1-5]
**Manager and Team**
7. My manager gives useful feedback. [1-5]
8. My manager cares about my development. [1-5]
9. I feel part of a team that works well together. [1-5]
**Culture and Belonging**
10. I feel I can be myself at work. [1-5]
11. People treat each other with respect. [1-5]
12. [Company] lives by its stated values. [1-5]
**Growth and Recognition**
13. I have opportunities to grow and develop. [1-5]
14. My contributions are recognised. [1-5]
15. I have had a meaningful career conversation in the last 6 months. [Yes/No]
**Open questions (always include)**
- What is one thing [Company] should start doing?
- What is one thing [Company] should stop doing?
- Anything else to share?
---
## Analysis Mode
### Analysis Output
**1. Headline Scores**
| Metric | Score | Benchmark | Trend |
|---|---|---|---|
| eNPS | [-100 to +100] | Industry avg | vs last survey |
eNPS: Below 0 = Concerning / 0-30 = Good / 30-70 = Great / 70+ = Excellent
**2. Strengths** — Top scoring areas with evidence.
**3. Improvement Areas** — 3 lowest scoring areas with verbatim comment themes.
**4. Action Planning Template**
| Improvement area | Action | Owner | Timeline | Measure |
|---|---|---|---|---|
**5. Communication Template** — Draft message to share results with employees.
## Example Trigger Phrases
- "Create an employee engagement survey for our team"
- "Design a pulse survey for [topic]"
- "Analyse these engagement survey results: [paste]"
@@ -0,0 +1,74 @@
---
name: job-description-writer
description: "Write a clear, inclusive, and structured job description for any role. Use when asked to write a job description, job posting, JD, or job advert. Produces a complete JD with role summary, responsibilities, requirements, and inclusive language review."
---
# Job Description Writer Skill
Writes complete, inclusive job descriptions that attract the right candidates and reduce bias in the hiring process.
## Required Inputs
- **Job title and level**
- **Team and reporting line**
- **Top 5 things this person will actually do**
- **Must-have requirements** (be ruthless — only what is truly required)
- **Nice-to-have requirements**
- **Salary range** (JDs with salary ranges get 30% more applicants)
- **Location and remote policy**
- **Company description** (2-3 sentences)
## Output Structure
### [Job Title]
**[Company] | [Location] | [Remote policy] | [Salary range]**
**About [Company]**
[2-3 sentences. Specific and honest — not marketing copy.]
**The Role**
[3-4 sentences. What this person will own, why the role exists now, what success looks like in year one.]
**What You Will Do**
[6-8 bullet points. Outcomes and responsibilities, not activities. Start each with an action verb. Most important first.]
**What We Are Looking For**
Must have (4-6 items only):
- [Requirement]
Nice to have (3-4 items):
- [Nice to have]
**What We Offer**
[Compensation, benefits, development. Be specific.]
**How to Apply**
[Clear instructions. What to send, where, timeline.]
---
### Inclusive Language Review
**Words to remove or replace:**
| Original | Replace with | Why |
|---|---|---|
| "rockstar" | "experienced" | Gendered connotation |
| "ninja" | "skilled" | Same issue |
| "must have degree" | "relevant experience or qualification" | Excludes qualified non-graduates |
**Requirement audit:**
- Years of experience requirements flagged (screen out women and underrepresented groups disproportionately)
- Any requirements potentially discriminating against protected characteristics
## Quality Checks
- Salary range included
- Must-haves genuinely essential (6 items max)
- Each responsibility starts with action verb
- Inclusive language review completed
- No years-of-experience requirements unless legally required
## Example Trigger Phrases
- "Write a job description for a [role]"
- "Create an inclusive job posting for [role]"
- "Review and rewrite this JD: [paste]"
@@ -0,0 +1,89 @@
---
name: onboarding-plan
description: "Create a structured 30/60/90-day onboarding plan for any new hire. Use when asked to write an onboarding plan, new hire plan, 30-60-90 day plan, or first 90 days roadmap. Produces a week-by-week plan with milestones, meetings, learning goals, and success criteria."
---
# Onboarding Plan Skill
Creates a complete, structured onboarding plan tailored to a specific role — covering the first 90 days with clear milestones and success criteria.
## Required Inputs
- **Role and level** of the new hire
- **Team and manager**
- **Key stakeholders** they will work with
- **Top 3 priorities** for their first 90 days
- **Tools and systems** they will need access to
- **Company stage** (startup / scaleup / enterprise)
## Output Structure
### Onboarding Plan: [Name] — [Role]
**Start date:** [Date] | **Manager:** [Name] | **Buddy:** [Name]
---
### Before Day 1 (Manager checklist)
- IT setup: laptop, accounts, email, Slack, key tools
- Access provisioned to key systems
- First week calendar blocked with key meetings
- Buddy assigned and briefed
- Welcome message sent with Day 1 logistics
---
### Week 1: Orient
Theme: Listen, learn, do not act yet.
| Day | Focus | Key activities |
|---|---|---|
| Day 1 | IT setup, team intro | 1:1 with manager, team lunch |
| Day 2 | Product deep dive | Demo, key docs to read |
| Day 3 | Process and tools | Shadow key workflows |
| Day 4 | Stakeholder intros | 3-4 intro 1:1s |
| Day 5 | Week 1 debrief | Check-in, questions logged |
**Week 1 milestone:** Can describe what the company does, the team role, and their top 3 priorities.
---
### Days 8-30: Learn
Learning goals:
- Deep understanding of product from customer perspective
- Know key metrics the team is measured on
- Understand current projects and status
- Map key stakeholder relationships
- Complete all compliance/HR training
**30-day milestone:** All stakeholder 1:1s complete. 2-3 early observations shared with manager.
---
### Days 31-60: Contribute
Goals:
- Own at least one project end-to-end
- Make one meaningful contribution
- Build cross-functional relationships
- Identify one process improvement
**60-day milestone:** Delivered one tangible output. Manager says "this person is contributing."
---
### Days 61-90: Lead
Goals:
- Operating independently on core responsibilities
- Has formed and shared a point of view on priorities
- Building reputation with key stakeholders
**90-day milestone:** Ready for formal review. Clear 6-month plan in place.
---
### 90-Day Review Questions
Manager: Meeting expectations? What to double down on? What to develop?
New hire: Have the clarity, tools, support needed? What surprised you? What would you change about onboarding?
## Example Trigger Phrases
- "Create a 30/60/90 day plan for a new [role]"
- "Write an onboarding plan for [name] starting as [role]"
- "Build a first 90 days roadmap for our new hire"
@@ -0,0 +1,68 @@
---
name: redundancy-consultation
description: "Structure a redundancy consultation process and draft key communications. Use when asked to plan a redundancy process, write a redundancy letter, structure a consultation, or manage a reduction in force. UK employment law focus. Always recommend qualified HR/legal advice before proceeding."
---
# Redundancy Consultation Skill
Structures redundancy processes and drafts communications. Significant legal and human risk — always flag that employment legal advice is essential before proceeding.
WARNING: Defaults to UK employment law (Employment Rights Act 1996). Always recommend qualified HR/legal advice before any redundancy action.
## Required Inputs
- **Number of roles affected** (1-19 = individual; 20+ = collective consultation required)
- **Reason for redundancy** (genuine business reason)
- **Jurisdiction** (UK / US / EU / Other)
- **Timeline constraints**
- **Selection pool** (if multiple people in similar roles)
## Output Structure
### 1. Process Overview
**Individual redundancy (fewer than 20):**
| Stage | Action | Minimum timeline |
|---|---|---|
| 1 | Confirm business case internally | Before any communication |
| 2 | At-risk notification meeting | Day 1 |
| 3 | Individual consultation | Minimum 1 meaningful meeting |
| 4 | Redundancy confirmed or alternative found | After genuine consideration |
| 5 | Notice period begins | Per contract |
| 6 | Final day and payment | Per contract + statutory |
**Collective redundancy (20+ roles — UK):**
- Minimum 45 days consultation before first dismissal
- Must notify BEIS (HR1 form) before consultation begins
- Employee representatives must be elected if no union recognised
- Failure = unlimited protective award per employee
### 2. Selection Criteria (if pool exists)
Objective, non-discriminatory only: skills/qualifications, performance (documented evidence), attendance (exclude disability/pregnancy-related absences), length of service (tiebreaker only).
NEVER select on: age, disability, pregnancy/maternity, part-time status, trade union membership.
### 3. At-Risk Letter Draft
"Dear [Name], I am writing to inform you that your role of [Job Title] is at risk of redundancy. This is because [specific business reason]. We would like to meet on [date] to discuss the situation and explore alternatives. You have the right to be accompanied by a colleague or trade union representative. No decision has been made. Yours sincerely, [Manager]"
### 4. Consultation Meeting Script
Opening: "No decision has been made. This meeting is to explain the situation and listen to your views."
Key questions: Any ways to avoid this? Alternative roles of interest? Anything about selection to challenge?
### 5. Redundancy Confirmation Letter Draft
Issued only after genuine consultation. Must include: statutory pay calculated, notice period, payment for accrued holiday, right of appeal.
### 6. Statutory Redundancy Pay Guide (UK)
- Under 22: 0.5 week per year of service
- 22-40: 1 week per year of service
- 41+: 1.5 weeks per year of service
- Weekly pay capped (verify current rate)
- Maximum 20 years counts
---
WARNING: Take advice from an employment lawyer or qualified HR professional before beginning any redundancy process.
## Example Trigger Phrases
- "Help me structure a redundancy consultation"
- "Draft an at-risk letter for [role]"
- "What is the process for making someone redundant in the UK?"
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-legal",
"version": "1.0.0",
"description": "Legal skills: Contract Review, NDA Analyser, Legal Brief, Compliance Checklist. Flag risks in contracts and NDAs, draft legal memos in IRAC format, and generate GDPR, SOC 2, FCA and other compliance checklists. Not a substitute for qualified legal advice.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["legal", "contract-review", "nda", "compliance", "gdpr", "legal-brief", "risk"]
}
@@ -0,0 +1,54 @@
---
name: compliance-checklist
description: "Generate a compliance checklist for any regulation, standard, or policy. Use when asked to create a compliance checklist, regulatory review, audit checklist, or policy adherence review. Covers GDPR, ISO 27001, FCA, HIPAA, SOC 2, and other frameworks. Produces a prioritised checklist with pass/fail assessment and remediation actions."
---
# Compliance Checklist Skill
Generates a structured compliance checklist for any regulatory framework with a prioritised gap analysis and remediation actions.
## Required Inputs
- **Framework or regulation** (e.g. GDPR, HIPAA, SOC 2, ISO 27001, FCA Consumer Duty, PCI DSS)
- **Organisation type** (e.g. SaaS company, financial services, NHS trust, law firm)
- **Scope** (e.g. data handling, customer onboarding, IT security, HR processes)
- **Known gaps or concerns** (optional)
## Output Structure
### 1. Framework Overview
- **Regulation/Standard:** [Name and version]
- **Enforcement body:** [Regulator]
- **Overall compliance status:** Red Gaps / Amber Partial / Green Compliant
### 2. Compliance Checklist
| # | Requirement | Status | Priority | Action Required |
|---|---|---|---|---|
| 1 | [Plain English requirement] | Met / Gap / Partial / Unknown | Critical / High / Low | [Specific action] |
Priority definitions:
- Critical: Regulatory breach risk. Remediate immediately.
- High: Significant gap. Address within 30 days.
- Low: Best practice. Address in next review cycle.
### 3. Critical Gaps Summary
List only Critical items with: what is missing, regulatory requirement breached, recommended remediation and owner.
### 4. Recommended Remediation Plan
| Action | Owner | Timeline | Effort |
|---|---|---|---|
| [Specific action] | [Team/role] | [Timeframe] | Low/Med/High |
### 5. Documentation Gaps
Policies, records, or evidence needed to demonstrate compliance.
---
WARNING: This checklist is a starting point based on publicly available guidance. It does not constitute legal or compliance advice.
## Example Trigger Phrases
- "Create a GDPR compliance checklist for our SaaS product"
- "Generate a SOC 2 audit checklist"
- "Review our compliance against FCA Consumer Duty"
- "Build an ISO 27001 gap analysis"
@@ -0,0 +1,64 @@
---
name: contract-review
description: "Review and summarise any contract or legal agreement. Use when asked to review a contract, check an agreement, flag legal risks, or summarise key clauses. Produces a structured review with key terms, flagged clauses, risk rating, and plain English summary. Not a substitute for qualified legal advice."
---
# Contract Review Skill
This skill produces a structured contract review identifying key terms, unusual or high-risk clauses, and a plain English summary. Always include the disclaimer that this is not legal advice.
## Required Inputs
- **Contract text or description** (paste or describe)
- **Reviewer role** (e.g. the party signing, their legal team, a business owner)
- **Contract type** (e.g. SaaS agreement, employment contract, NDA, supplier contract)
- **Key concerns** (optional — e.g. "focus on IP ownership and termination clauses")
## Output Structure
### 1. Contract Overview
- **Type:** [Contract type]
- **Parties:** [Party A and Party B]
- **Effective date / duration:** [If stated]
- **Governing law:** [Jurisdiction]
- **Overall risk rating:** Green Low / Amber Medium / Red High
### 2. Key Terms Summary
| Term | Detail |
|---|---|
| Payment / fees | |
| Term and renewal | |
| Termination rights | |
| Liability cap | |
| IP ownership | |
| Confidentiality | |
| Dispute resolution | |
### 3. Flagged Clauses
For each flagged clause:
**[Risk level] — [Clause name]**
- **What it says:** [Plain English summary]
- **Why it matters:** [Risk or implication]
- **Suggested action:** [Negotiate / Accept / Seek legal advice / Query]
### 4. Missing Clauses
List any standard clauses absent but normally expected for this contract type.
### 5. Plain English Summary
3-5 sentences. What does this contract mean for the party signing it?
### 6. Recommended Next Steps
- [Action 1]
- [Action 2]
---
WARNING: This review is for informational purposes only and does not constitute legal advice. Always consult a qualified solicitor or lawyer before signing any legally binding agreement.
## Example Trigger Phrases
- "Review this contract: [paste]"
- "Flag the key risks in this agreement"
- "Summarise this SaaS contract in plain English"
- "What should I watch out for in this supplier agreement?"
@@ -0,0 +1,63 @@
---
name: legal-brief
description: "Draft a structured legal brief, case summary, or legal argument outline. Use when asked to write a legal brief, case note, legal memo, argument outline, or position paper. Produces a structured document using IRAC format (Issue, Rule, Application, Conclusion)."
---
# Legal Brief Skill
This skill drafts structured legal briefs and memos using IRAC format — the standard structure for legal writing.
## Required Inputs
- **Brief type** (legal memo / case summary / argument outline / position paper / letter before action)
- **Legal issue or question**
- **Jurisdiction** (England & Wales / US / EU / Other)
- **Relevant facts**
- **Relevant law or cases** (if known — otherwise flagged as [RESEARCH NEEDED])
- **Audience** (internal memo / court submission / client letter)
## Output Structure
### Header
- **To:** [Recipient]
- **From:** [Author]
- **Date:** [Date]
- **Re:** [Matter reference]
- **Confidential:** Subject to legal professional privilege
### Issue(s)
One sentence per legal question:
- Issue 1: Whether X constitutes Y under [law]
### Brief Answer
One sentence per issue — conclusion upfront before analysis.
### Facts
Concise relevant facts only. Flag disputed facts.
### Law (Rule)
- Relevant statute, regulation, or case law
- How the rule has been interpreted in key cases
- Flag [RESEARCH NEEDED] where law is not provided
### Application
- Arguments in favour
- Counter-arguments and responses
- Areas of uncertainty flagged explicitly
### Conclusion
- Clear answer to each issue
- Overall recommendation
- Suggested next steps
### Caveats
What this memo does not cover. What additional research would change the analysis.
---
WARNING: This draft requires review by a qualified legal professional. It does not constitute legal advice.
## Example Trigger Phrases
- "Draft a legal memo on [issue]"
- "Write a legal brief arguing [position]"
- "Summarise the legal position on [topic]"
- "Write a letter before action for [situation]"
@@ -0,0 +1,59 @@
---
name: nda-analyser
description: "Analyse a Non-Disclosure Agreement (NDA) and flag key terms, unusual provisions, and negotiation points. Use when asked to review an NDA, mutual NDA, confidentiality agreement, or non-disclosure deed. Produces clause-by-clause analysis with risk flags and a negotiation checklist."
---
# NDA Analyser Skill
NDAs are often treated as routine paperwork but contain terms with significant long-term consequences. This skill analyses them systematically.
## Required Inputs
- **NDA text** (paste in full or describe key clauses)
- **Your party position** (disclosing / receiving / mutual)
- **Purpose of the NDA** (e.g. pre-sales, hiring, M&A, partnership)
- **Industry context** (optional)
## Output Structure
### 1. NDA Type and Parties
- **Type:** Unilateral / Mutual
- **Disclosing party:** [Name]
- **Receiving party:** [Name]
- **Purpose:** [As stated]
- **Governing law:** [Jurisdiction]
- **Term:** [Duration of obligations]
### 2. Definition of Confidential Information
- **How broadly defined?** Narrow / Standard / Very broad
- **Oral disclosures included?** Yes / No / With conditions
- **Standard exclusions present?** [public domain, prior knowledge, independently developed, legally required disclosure]
- **Flag:** [Unusual inclusions or missing exclusions]
### 3. Key Clause Analysis
**[Clause name] — Concern / Watch / Standard**
- **What it says:** [Plain English]
- **Issue:** [Why flagged]
- **Standard position:** [What this typically looks like]
- **Negotiation suggestion:** [If applicable]
Clauses always covered: permitted use, non-solicitation/non-compete, term and post-termination obligations, return/destruction of information, remedies, liability, residuals clause.
### 4. Negotiation Checklist
| Point | Current position | Suggested ask |
|---|---|---|
| [e.g. Confidentiality term] | [e.g. 5 years] | [e.g. Reduce to 2 years] |
### 5. Plain English Verdict
2-3 sentences. Standard NDA, one-sided, or needs a lawyer?
---
WARNING: This analysis is for informational purposes only and is not legal advice. Consult a qualified solicitor before signing.
## Example Trigger Phrases
- "Analyse this NDA"
- "Review this confidentiality agreement"
- "Is this NDA standard or unusual?"
- "What should I negotiate in this mutual NDA?"
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-operations",
"version": "1.0.0",
"description": "Operations skills: Process Documentation, SOP Writer, Vendor Evaluation, Project Status Report. Document workflows, write audit-ready SOPs, evaluate vendors with weighted scorecards, and produce RAG status reports.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["operations", "process", "sop", "vendor", "procurement", "project-management", "rag-status"]
}
@@ -0,0 +1,81 @@
---
name: process-documentation
description: "Document any business process in a clear, structured format. Use when asked to document a process, write a process guide, create a workflow document, or map out how something works. Produces a complete process document with steps, roles, inputs, outputs, and edge cases."
---
# Process Documentation Skill
Produces clear, structured process documentation that someone new to a role can follow without needing to ask questions.
## Required Inputs
- **Process name**
- **Process description** (rough notes are fine)
- **Who does this process** (roles involved)
- **How often it runs** (daily / weekly / monthly / event-triggered)
- **Tools involved**
- **Known edge cases**
## Output Structure
---
# Process: [Process Name]
**Owner:** [Role] | **Frequency:** [How often] | **Estimated time:** [Duration]
---
### Purpose
[1-2 sentences. Why does this process exist? What breaks if it is not done?]
### Scope
**In scope:** [What this covers]
**Out of scope:** [What it does not cover]
### Prerequisites
- [ ] [Required access or information]
- [ ] [Any dependency that must be completed first]
---
### Roles and Responsibilities
| Role | Responsibility |
|---|---|
| [Role 1] | [What they do] |
---
### Process Steps
**Step 1: [Step name]**
- **Who:** [Role]
- **When:** [Trigger or timing]
- **How:** [Substeps numbered]
- **Output:** [What exists at end of this step]
- **Tool:** [System used]
[Continue for all steps]
---
### Edge Cases and Exceptions
| Situation | What to do | Who to contact |
|---|---|---|
| [Edge case] | [Action] | [Name/role] |
---
### Common Mistakes
[2-4 things people get wrong the first time]
### Escalation Path
[Name/role] → [Next level] → [Final escalation]
### Review
Next review due: [Date]
## Example Trigger Phrases
- "Document this process: [description]"
- "Write a process guide for [workflow]"
- "Map out how [process] works"
@@ -0,0 +1,109 @@
---
name: project-status-report
description: "Write a structured project status report for any project. Use when asked to write a project update, status report, RAG report, project dashboard narrative, or weekly project communication. Produces a clear status report with RAG ratings, milestone progress, risks, and decisions needed."
---
# Project Status Report Skill
Produces a clear, structured project status report — the weekly communication that keeps stakeholders informed without requiring a meeting.
## Required Inputs
- **Project name**
- **Reporting period**
- **Current RAG status** (Red / Amber / Green)
- **Key milestones** (due, delivered, coming)
- **Issues or blockers**
- **Decisions needed from stakeholders**
- **Budget status** (if tracked)
- **Audience** (steering committee / sponsor / PMO / full team)
## Output Structure
---
# Project Status Report: [Project Name]
**Period:** [Date range] | **Author:** [PM] | **Next report:** [Date]
---
### Overall Status
| Dimension | Status | Last period | Trend |
|---|---|---|---|
| Overall | Red / Amber / Green | [Last] | Improving / Stable / Declining |
| Schedule | | | |
| Budget | | | |
| Scope | | | |
| Risks | | | |
RAG definitions:
- Green: On track. No significant issues.
- Amber: At risk. Issues identified but mitigations in place.
- Red: Off track. Escalation or decisions required to recover.
---
### Executive Summary
[3-5 sentences. Headline story. If it is Red, say so immediately and why. Never bury bad news after good news.]
---
### Milestone Progress
| Milestone | Due date | Status | Comment |
|---|---|---|---|
| [Milestone] | [Date] | Complete / At risk / Delayed / On track | [One line] |
**Completed this period:** [What was delivered]
**Due next period:** [What is expected]
---
### Issues and Blockers
**[Issue title] — Critical / High / Low**
- **Description:** [What the issue is]
- **Impact:** [What happens if unresolved]
- **Owner:** [Who is resolving]
- **Action:** [What is being done]
- **Resolution date:** [When it will be closed]
---
### Risks
| Risk | Likelihood | Impact | Mitigation | Owner |
|---|---|---|---|---|
| [Risk] | H/M/L | H/M/L | [Action] | [Name] |
---
### Decisions Required
| Decision | Background | Options | Recommendation | Needed by |
|---|---|---|---|---|
| [Decision] | [Context] | [Options] | [Recommendation] | [Date] |
---
### Budget Summary
| | Budget | Actual to date | Forecast | Variance |
|---|---|---|---|---|
| Total | £ | £ | £ | £ F/A |
---
### Next Period Plan
[3-5 specific bullet points — what will happen next period]
## Writing Rules
- Never soften a Red status
- Milestones are binary: complete or not complete
- Decisions must be genuinely actionable
- Keep to one page where possible
## Example Trigger Phrases
- "Write a project status report for [project]"
- "Generate a RAG status update for [project]"
- "Write the steering committee report for [project]"
@@ -0,0 +1,93 @@
---
name: sop-writer
description: "Write a Standard Operating Procedure (SOP) for any operational task. Use when asked to write an SOP, standard operating procedure, work instruction, or operating manual. Produces a formal SOP with purpose, scope, procedure steps, quality checks, and version control."
---
# SOP Writer Skill
Produces formal, audit-ready SOPs suitable for regulated industries, ISO certification, or operational scaling.
## Required Inputs
- **SOP title** (e.g. "SOP-001: New Client Onboarding")
- **Department / function**
- **Process description**
- **Regulatory or quality standard** (ISO 9001, GMP, CQC, FCA, etc.)
- **Roles involved**
- **Tools or equipment used**
## Output Structure
---
**[COMPANY NAME] — Standard Operating Procedure**
| Document ID | [SOP-XXX] |
|---|---|
| Title | [Title] |
| Department | [Department] |
| Version | 1.0 |
| Effective date | [Date] |
| Review date | [Date] |
| Status | Draft / Under review / Approved |
---
### 1. Purpose
[1-2 sentences. Why does this SOP exist?]
### 2. Scope
**Applies to:** [Roles, departments, locations]
**Does not apply to:** [Explicit exclusions]
### 3. Definitions
| Term | Definition |
|---|---|
| [Term] | [Plain English definition] |
### 4. Responsibilities
| Role | Responsibility |
|---|---|
| [Role] | [Specific responsibility] |
### 5. Required Materials / Tools / Access
- [Item]
### 6. Procedure
| Step | Action | Responsible | Record/Output |
|---|---|---|---|
| 6.1.1 | [Imperative action: "Open [system] and navigate to [location]"] | [Role] | [What to record] |
NOTE: Steps must be written in imperative form. Each step must have one action only.
### 7. Quality Checks
| Check point | What to verify | Pass criteria | If fail |
|---|---|---|---|
| [After step X] | [What to check] | [What good looks like] | [What to do] |
### 8. Non-Conformance
1. [Immediate action]
2. [Who to notify]
3. [How to document deviation]
### 9. References
[Related SOPs, policies, standards]
### 10. Document History
| Version | Date | Author | Changes |
|---|---|---|---|
| 1.0 | [Date] | [Name] | Initial release |
## Quality Checks
- All steps in imperative form
- Each step has exactly one action
- Roles specified for every step
- Quality checkpoints at critical stages
- Non-conformance process defined
## Example Trigger Phrases
- "Write an SOP for [process]"
- "Create a standard operating procedure for [task]"
- "Write a work instruction for [process]"
@@ -0,0 +1,70 @@
---
name: vendor-evaluation
description: "Create a structured vendor evaluation framework for any procurement decision. Use when asked to evaluate vendors, compare suppliers, run an RFP scoring process, or assess a software or service provider. Produces a weighted scorecard, evaluation criteria, and recommendation framework."
---
# Vendor Evaluation Skill
Produces a structured vendor evaluation framework — from defining criteria through to a scored comparison and recommendation.
## Required Inputs
- **What you are procuring**
- **Vendors being evaluated** (minimum 2)
- **Key decision criteria** (if known)
- **Decision makers**
- **Budget range**
- **Timeline to decide**
## Output Structure
### 1. Evaluation Criteria and Weights
| Category | Weight | Rationale |
|---|---|---|
| Functional fit | [%] | Does it do what we need? |
| Commercial terms | [%] | Price, flexibility, payment |
| Implementation | [%] | How hard to get started? |
| Support and SLA | [%] | What happens when things go wrong? |
| Security and compliance | [%] | Meets regulatory requirements? |
| Vendor stability | [%] | Will this company exist in 3 years? |
| References | [%] | Who else uses this? |
Weights must total 100%.
### 2. Scoring Rubric
- 5: Exceeds requirements — clear best-in-class
- 4: Meets requirements — fully satisfies with minor gaps
- 3: Partially meets — notable gaps requiring workarounds
- 2: Significant gaps — would require workarounds
- 1: Does not meet — cannot satisfy requirement
### 3. Vendor Scorecard
| Criterion | Weight | [Vendor A] | Weighted | [Vendor B] | Weighted | [Vendor C] | Weighted |
|---|---|---|---|---|---|---|---|
| Functional fit | [%] | /5 | | /5 | | /5 | |
| [Continue...] | | | | | | | |
| **Total** | 100% | | **/5** | | **/5** | | **/5** |
### 4. Key Questions for Every Vendor
Functional: Walk through [most critical use case]. What can your product not do that customers ask for?
Commercial: What is included vs add-ons? Contract minimum term and notice period? Price protection at renewal?
Implementation: Typical implementation for our size? What do you need from our team?
Support: SLA for critical issues? Support included vs charged extra?
Security: ISO 27001 / SOC 2 certified? Where is data stored? Breach notification process?
### 5. Reference Check Questions
- How long using [vendor]? Implementation surprises? Support responsiveness? One thing you wish you had known? Would you choose them again?
### 6. Recommendation
**Recommended vendor:** [Name] | **Score:** [X/5]
**Rationale:** [Specific strengths that matter for this decision]
**Key risks:** [Risk and mitigation]
**Conditions:** [Contract terms to negotiate before signing]
**Runner-up:** [Vendor and why they lost]
## Example Trigger Phrases
- "Help me evaluate vendors for [procurement]"
- "Create a vendor scorecard for [software/service]"
- "Compare [Vendor A] vs [Vendor B] for [use case]"
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-research",
"version": "1.0.0",
"description": "Research and healthcare skills: Clinical Case Summary, Research Protocol, Patient Communication, Literature Review. Write SBAR handovers, design research protocols, draft accessible patient communications, and structure literature reviews.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["research", "healthcare", "clinical", "patient", "literature-review", "protocol", "academic"]
}
@@ -0,0 +1,83 @@
---
name: clinical-case-summary
description: "Write a structured clinical case summary or case presentation. Use when asked to write a clinical case summary, case presentation, patient case report, or clinical handover. Produces a structured summary using SBAR or SOAP format. For educational and documentation purposes only — not a substitute for clinical judgement."
---
# Clinical Case Summary Skill
Produces structured clinical case summaries for educational, documentation, and handover purposes.
WARNING: For documentation and educational purposes only. All clinical content must be reviewed by a qualified healthcare professional. This is not clinical advice.
## Required Inputs
- **Purpose** (case presentation / handover / case report / educational / MDT summary)
- **Patient details** (anonymised — age, sex, relevant background)
- **Presenting complaint and history**
- **Examination findings**
- **Investigations and results**
- **Diagnosis or differential diagnoses**
- **Management and treatment**
- **Outcome** (if known)
- **Format preference** (SBAR / SOAP / Standard clinical / Narrative)
---
## Format A: SBAR (Handover / Referral)
**S — Situation**
[Patient identifier anonymised, location, reason for contact in one sentence]
**B — Background**
- Age / sex / relevant past medical history
- Current admission details
- Relevant medications and allergies
- Brief relevant social history
**A — Assessment**
- Current clinical status
- Vital signs if relevant
- Key examination findings
- Working diagnosis or differential
- Recent investigations and results
**R — Recommendation**
- What you need from the recipient
- Urgency level
- Immediate actions already taken
- Questions or concerns
---
## Format B: SOAP Note
**S — Subjective**
[Presenting complaint in patient words. Symptom history: onset, duration, character, severity, associated symptoms, relieving/aggravating factors]
**O — Objective**
- Vital signs: [BP, HR, RR, Temp, O2 sats]
- Examination: [Systematic findings]
- Investigations: [Results with reference ranges]
**A — Assessment**
- Primary diagnosis: [With brief rationale]
- Differential diagnoses: [Ranked with reasoning]
**P — Plan**
- Immediate management
- Investigations ordered
- Treatments initiated with dose, route, frequency
- Referrals
- Safety netting: what to watch for, when to escalate
- Follow-up plan
## Quality Checks
- Patient details fully anonymised
- Allergies and medications included in handover formats
- Safety netting included in SOAP plan
- Disclaimer included
## Example Trigger Phrases
- "Write a clinical handover using SBAR for this patient"
- "Summarise this case in SOAP format"
- "Write a case report for [clinical scenario]"
- "Prepare an MDT summary for this patient"
@@ -0,0 +1,71 @@
---
name: literature-review
description: "Structure and write a literature review for any research topic. Use when asked to write a literature review, systematic review summary, narrative review, or research background section. Produces a structured review with thematic organisation, critical analysis, and gap identification."
---
# Literature Review Skill
Structures and writes literature reviews — from background sections of a dissertation through to standalone narrative reviews for publication.
## Required Inputs
- **Topic or research question**
- **Type of review** (narrative / systematic / scoping / integrative / background section)
- **Sources provided** (paste references, abstracts, or key findings)
- **Word count target**
- **Audience** (academic journal / thesis / grant proposal / policy brief)
- **Time period to cover**
## Output Structure
### 1. Search Strategy Summary (for systematic/scoping reviews)
**Databases:** [PubMed, EMBASE, PsycINFO, etc.]
**Search terms:** [Key terms and Boolean combinations]
**Inclusion criteria:** Study types, population, date range, language
**Exclusion criteria:** [List]
**Results:** [n] identified → [n] after deduplication → [n] screened → [n] included
### 2. Literature Review Body
Organised thematically — not chronologically. Each theme = one section.
**Structure per thematic section:**
**[Theme heading]**
[Opening: state what this section covers and what evidence shows overall]
[Evidence synthesis: present what multiple studies found, compare and contrast. Do NOT summarise one paper then the next — synthesise across them: "Three studies found X (Smith, 2019; Jones, 2020; Lee, 2021), while two found Y, with the difference attributable to..."]
[Critical analysis: note methodological strengths and weaknesses — sample sizes, study designs, generalisability, risk of bias]
[Closing: transition to next theme]
### 3. Synthesis Table (systematic/scoping reviews)
| Author, year | Study design | Population | n | Key findings | Quality/Limitations |
|---|---|---|---|---|---|
### 4. Gap Analysis
**Well-established:** [What literature consistently shows]
**Contested:** [Areas where evidence is mixed and why]
**Missing:** [Gaps the field needs to address]
**How your study addresses the gap:** [If this is for a research proposal]
### 5. Conclusion Paragraph
[3-5 sentences. Current state of knowledge and what is needed next]
## Critical Analysis Framework
For each paper: internal validity, external validity, bias types, effect size significance vs clinical significance, funding conflicts.
## Quality Checks
- Organised thematically not as paper summaries
- Evidence synthesised across papers
- Critical analysis included
- Gaps identified
- All claims cited
## Example Trigger Phrases
- "Write a literature review on [topic]"
- "Synthesise the evidence on [topic] from these papers: [paste]"
- "Write the background section for my research proposal on [topic]"
@@ -0,0 +1,89 @@
---
name: patient-communication
description: "Write clear, plain English patient communications for any healthcare context. Use when asked to write a patient letter, patient information leaflet, appointment letter, test results letter, discharge summary for patients, or health education content. Targets accessible reading level with clear next steps."
---
# Patient Communication Skill
Writes patient-facing healthcare communications in plain, accessible language — targeting UK Grade 6 / US Grade 8 reading level.
WARNING: All patient communications must be reviewed and approved by a qualified healthcare professional before sending. This skill produces drafts only.
## Required Inputs
- **Communication type** (appointment letter / results letter / discharge info / patient leaflet / consent info / health education)
- **Clinical context**
- **Key messages** (what the patient must understand and do)
- **Tone** (reassuring / informative / urgent)
- **Specific instructions or next steps**
- **Contact details for queries**
## Output Structure
### Type A: Patient Letter
[Date]
Dear [Patient name],
**Re: [Clear subject line in bold]**
[Opening paragraph: State clearly what this letter is about. No preamble.]
[Main content — short paragraphs, 2-3 sentences each. Bullet points for instructions. Bold anything the patient must do or remember.]
**What happens next:**
- [Action 1 — specific with timeframe]
- [Action 2]
**If you have questions:**
Contact us at [phone] between [hours] or email [address].
If you feel unwell before your appointment, please [specific instruction].
Yours sincerely, [Name, Title, Department]
---
### Type B: Patient Information Leaflet
**[Plain language title]**
**What is [topic]?** [2-3 plain English sentences. Explain technical terms immediately.]
**Why has this been recommended for me?** [Personalised clinical reason in patient terms]
**What will happen?** [Numbered step by step]
**What are the benefits?** [Honest statement]
**What are the risks?** [Common first, then rare but serious. Use frequencies: "About 1 in 10 people..." not "10% incidence"]
**What should I do to prepare?** [Specific instructions]
**When should I contact someone?** [Specific signs — not vague. "Temperature above 38C" not "if you feel unwell"]
---
### Type C: Test Results Letter
**Your [test name] results — [Normal / Abnormal] — stated in the FIRST sentence, never paragraph 3.**
[What this means in plain English]
**What happens next:** [Clear next steps. If no action, say so explicitly.]
---
## Plain Language Rules (apply to all types)
- Maximum 2 syllables per word where possible
- Maximum 20 words per sentence
- Active voice: "We will contact you" not "You will be contacted"
- Spell out all acronyms on first use
- No Latin: "twice daily" not "bd"
- Use "you" and "we" throughout
- Numbers as digits: "2 tablets" not "two tablets"
## Example Trigger Phrases
- "Write a patient letter about [topic]"
- "Create a patient information leaflet for [procedure]"
- "Write a plain English results letter for [test]"
@@ -0,0 +1,97 @@
---
name: research-protocol
description: "Write a structured research protocol or study design document. Use when asked to write a research protocol, study protocol, research plan, methodology section, or research proposal. Produces a complete protocol with objectives, methodology, ethical considerations, and analysis plan."
---
# Research Protocol Skill
Produces structured research protocols for academic, clinical, social science, or market research studies.
## Required Inputs
- **Research type** (clinical trial / observational / qualitative / systematic review / survey)
- **Research question or hypothesis**
- **Setting and population**
- **Proposed methodology**
- **Timeline**
- **Funder or institution** (if applicable)
## Output Structure
---
# Research Protocol: [Study Title]
**Version:** 1.0 | **Date:** [Date] | **PI:** [Name, institution]
---
### 1. Background and Rationale
- What is already known
- What the gap in knowledge is
- Why this study is needed now
### 2. Research Objectives
**Primary:** [One clear answerable question or hypothesis]
**Secondary:** [Additional questions]
### 3. Study Design
- **Design:** [RCT / cohort / qualitative / mixed methods]
- **Setting:** [Where]
- **Duration:** [Total period and recruitment window]
- **Rationale:** [Why this design fits the question]
### 4. Participants
**Inclusion criteria:** [List]
**Exclusion criteria:** [List]
**Sample size:** [n] — Basis: [Power calculation or saturation rationale]
**Recruitment:** [Method and source]
### 5. Methodology / Intervention
For interventional: intervention description, control, randomisation, blinding
For observational/qualitative: data collection methods, tools, data collectors
### 6. Outcomes / Measures
**Primary outcome:** [Measure], assessed by [method], at [timepoint]
**Secondary outcomes:** [Measure], [method], [timepoint]
### 7. Data Management
- Storage: [Where and anonymisation method]
- Access controls: [Who can access]
- Retention: [How long]
### 8. Analysis Plan
Quantitative: [Statistical test], [missing data handling], [software]
Qualitative: [Framework — e.g. Braun & Clarke], [quality assurance]
### 9. Ethical Considerations
- Ethics approval: [Body / reference]
- Informed consent: [Process]
- Confidentiality: [How maintained]
- Risk to participants: [Assessment and mitigation]
### 10. Dissemination Plan
- Target journals: [2-3 relevant]
- Conference presentations
- Public/patient summary
### 11. Timeline
| Phase | Activities | Start | End |
|---|---|---|---|
| Setup | Ethics, approvals, tool development | | |
| Recruitment | | | |
| Data collection | | | |
| Analysis | | | |
| Write-up | | | |
## Quality Checks
- Primary objective is singular and answerable
- Sample size has stated basis
- Ethical considerations complete
- Analysis plan pre-specified
## Example Trigger Phrases
- "Write a research protocol for [study]"
- "Help me design a study to investigate [question]"
- "Write the methodology for my research proposal"
@@ -0,0 +1,13 @@
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "pm-sales",
"version": "1.0.0",
"description": "Sales skills: Sales Battlecard, Discovery Call Prep, Proposal Writer, Account Plan. Build competitive battlecards, prepare structured discovery calls, write winning proposals, and create strategic account plans.",
"author": {
"name": "Mohit Aggarwal",
"email": "mohit15856@gmail.com"
},
"homepage": "https://github.com/mohitagw15856/pm-claude-skills",
"license": "MIT",
"keywords": ["sales", "battlecard", "discovery", "proposal", "account-plan", "competitive", "crm"]
}
@@ -0,0 +1,94 @@
---
name: account-plan
description: "Build a structured account plan for any key customer or target account. Use when asked to create an account plan, key account strategy, strategic account review, or territory plan. Produces a complete account plan with relationship map, growth opportunities, risks, and 90-day action plan."
---
# Account Plan Skill
Produces a structured account plan — the document that separates account managers who grow accounts from those who just service them.
## Required Inputs
- **Account name**
- **Current ARR / revenue**
- **Contract renewal date**
- **Key contacts** (names, roles, relationship strength)
- **Products/services currently in use**
- **Known opportunities or expansion areas**
- **Known risks**
- **Planning horizon** (6 / 12 / 24 months)
## Output Structure
---
# Account Plan: [Account Name]
**Account Manager:** [Name] | **Period:** [Date range]
---
### Account Snapshot
| Metric | Current | Target (EOY) |
|---|---|---|
| ARR / Revenue | £[amount] | £[target] |
| NPS / Health score | [Score] | [Target] |
| Products in use | [List] | [Expansion targets] |
| Renewal date | [Date] | — |
| Risk level | Low / Medium / High | — |
---
### Relationship Map
| Name | Title | Influence | Relationship | Notes |
|---|---|---|---|---|
| [Name] | [Role] | Decision maker / Influencer / User | Strong / Neutral / Weak | [Insight] |
**Relationship gaps:** [Who we do not have access to that we should]
**Executive sponsor:** [Do we have one? If not — who could become one?]
---
### Why They Stay (Retention Anchors)
[2-3 specific reasons this account renews. If the list is short, that is the risk signal.]
---
### Growth Opportunities
| Opportunity | Product | Est. Value | Timeline | Next Action |
|---|---|---|---|---|
| [Opportunity] | [Product] | £[value] | [Q/Year] | [Specific action] |
**Whitespace:** What products do we have that this account does not use, and why?
---
### Risks and Mitigation
| Risk | Likelihood | Impact | Mitigation | Owner |
|---|---|---|---|---|
| [Risk] | H/M/L | H/M/L | [Action] | [Name] |
---
### 90-Day Action Plan
| Action | Why | Owner | Due |
|---|---|---|---|
| [Specific action] | [Why it matters] | [Name] | [Date] |
**Next QBR / EBR:** [Date — if no EBR cadence, flag as a risk]
---
### Success Criteria
At end of [period]:
- Renewed at or above current ARR
- [Expansion opportunity] progressed to [stage]
- Health score moved from [current] to [target]
## Example Trigger Phrases
- "Build an account plan for [customer]"
- "Create a key account strategy for [account]"
- "Help me plan my approach to renewing [account]"
@@ -0,0 +1,97 @@
---
name: discovery-call-prep
description: "Prepare a structured discovery call plan for any prospect. Use when asked to prepare for a sales call, discovery call, prospect meeting, or first call with a potential customer. Produces a call brief with research, hypotheses, questions, and success criteria."
---
# Discovery Call Prep Skill
Produces a complete discovery call brief — research summary, call hypothesis, structured questions, and success criteria — so every call starts with context and ends with a clear next step.
## Required Inputs
- **Prospect company name**
- **Contact name and role**
- **Any known context** (how they found you, prior interaction)
- **Your product/solution** (one line)
- **Call duration** (15 / 30 / 45 / 60 min)
## Output Structure
---
# Discovery Call Brief
**Prospect:** [Company] | **Contact:** [Name, Title] | **Duration:** [X min]
---
### Research Summary
- What they do: [Product/service, customer, business model]
- Size: [Headcount, revenue if public]
- Stage: [Startup / Scaleup / Enterprise]
- Recent news: [Funding, launches, leadership changes — last 90 days]
- Contact background: [Role tenure, previous companies, LinkedIn activity]
- Likely priorities for someone in this role: [Based on title and stage]
---
### Call Hypothesis
Before the call write your best guess:
- **Their most likely pain:** [What someone in this role at this company probably has]
- **Why they would care about us:** [Specific connection to your value]
- **Biggest risk to the deal:** [What might make this not a fit]
Write it down — then test it on the call.
---
### Call Agenda
"Here is what I was thinking for our [X] minutes:
- 2 min: Quick intros
- [X] min: Learn more about your situation
- [X] min: Share how we have helped similar companies
- 5 min: Next steps
Does that work? Anything specific you would like to cover?"
---
### Discovery Questions
Open with context (not a pitch):
- "What prompted you to take this call today?"
- "What does [relevant area] look like for you at the moment?"
Go deeper on pain:
- "How long has [problem] been an issue?"
- "What have you tried to solve it?"
- "What is the impact of not solving this?"
Understand buying context:
- "Who else would be involved in a decision like this?"
- "Have you looked at other solutions?"
- "Is there a reason you are exploring this now?"
Qualify on budget:
- "Have you set aside budget for this kind of initiative?"
Close discovery:
- "Based on what you have told me, it sounds like [summary]. Is that right?"
---
### Success Criteria
This call is successful if we leave with:
- Understanding of specific pain and business impact
- Knowledge of buying process and key stakeholders
- A clear agreed next step (demo / proposal / intro)
- Sense of timeline
This call is NOT successful if we only pitched and got "sounds interesting, send me some info."
---
### Suggested Next Step
"Based on what we discussed, the logical next step would be [specific]. Does [day/time] work?"
## Example Trigger Phrases
- "Prepare me for a discovery call with [company/contact]"
- "Build a call brief for my meeting with [name] at [company]"
- "What questions should I ask in a discovery call for [use case]?"
@@ -0,0 +1,92 @@
---
name: proposal-writer
description: "Write a structured sales proposal or commercial proposal for any deal. Use when asked to write a proposal, sales proposal, commercial proposal, statement of work, or quote document. Produces a complete proposal with problem statement, solution, investment, and next steps."
---
# Proposal Writer Skill
Writes commercial proposals that win business — structured around the prospect problem, not the product.
## Required Inputs
- **Prospect company and contact**
- **Their problem or goal** (from discovery — be specific)
- **Your proposed solution**
- **Commercial terms** (pricing, payment terms, contract length)
- **Timeline**
- **Key stakeholders** who will read this
- **Tone** (formal / conversational / technical)
## Output Structure
---
# Proposal: [Brief description of what you are solving]
**Prepared for:** [Contact, Title] | [Company]
**Prepared by:** [Name] | [Your Company]
**Date:** [Date] | **Valid until:** [Date]
---
### Understanding Your Situation
[2-3 paragraphs. Demonstrate you listened. Describe their situation, problem, and impact of not solving it in their words. This section should make them think "yes, exactly." Generic boilerplate here = proposal goes in the bin.]
**The key challenge:** [One sentence — the core problem]
**The impact:** [What this costs them]
**What you have tried:** [Acknowledge prior attempts]
---
### Our Proposed Approach
**What we will do** (3-5 deliverables or phases)
**Phase 1: [Name]** (Timeline: [Weeks 1-2])
[What happens, what is delivered, what customer input is needed]
**Phase 2: [Name]** (Timeline: [Weeks 3-6])
**What you will get** (outcomes, not features)
- [Outcome 1]
- [Outcome 2]
**What success looks like**
[How both parties know this worked]
---
### Why [Your Company]
[3-4 sentences. Specific to their situation. Reference similar customers. Generic "why us" sections are skipped.]
---
### Investment
| Item | Description | Investment |
|---|---|---|
| [Component 1] | [Description] | £[amount] |
| **Total** | | **£[total]** |
**Payment terms:** [Terms]
**Included:** [What is in]
**Not included:** [What is out — prevents scope disputes]
---
### Timeline
| Milestone | Date |
|---|---|
| Contract signed | [Date] |
| Kickoff | [Date] |
| Delivery | [Date] |
---
### Next Steps
1. [Sign / reply / schedule] by [date]
2. We will send contract and confirm kickoff
3. [Any immediate action]
## Example Trigger Phrases
- "Write a proposal for [prospect] to [solve their problem]"
- "Draft a statement of work for [project]"
- "Turn my discovery notes into a proposal"
@@ -0,0 +1,79 @@
---
name: sales-battlecard
description: "Create a competitive sales battlecard for any competitor. Use when asked to build a battlecard, competitive comparison, sales cheat sheet, or objection handling guide for a specific competitor. Produces a one-page battlecard with positioning, differentiators, objection responses, and landmines."
---
# Sales Battlecard Skill
Produces a practical one-page competitive battlecard that sales reps can use in calls — not a theoretical analysis.
## Required Inputs
- **Your product/company**
- **Competitor name**
- **Your target customer** (ICP)
- **Your top 3 differentiators** vs this competitor
- **Common objections** when competing against them
- **Known competitor weaknesses**
## Output Structure
---
# Battlecard: [Your Product] vs [Competitor]
Updated: [Date] — Review quarterly
---
### In One Sentence
When a prospect mentions [Competitor], say: "[Your positioning in one sentence]"
---
### Why Customers Choose [Competitor]
(Be honest about their genuine strengths)
- [Strength 1]
- [Strength 2]
---
### Why Customers Choose Us
(Specific differentiators with proof points)
- **[Differentiator 1]:** [Proof point — customer outcome or capability]
- **[Differentiator 2]:** [Proof point]
---
### Objection Responses
**"[Competitor] is cheaper"**
"You are right their list price is lower. What our customers find is [specific TCO difference]. [Customer] saw [result]. Should we explore total cost of ownership?"
**"We already use [Competitor]"**
"That is helpful. What is working well? [Listen] And what is one thing you wish was better?"
**"[Competitor] has [feature] you do not"**
"You are right. What problem are you solving with that feature? [Listen] Here is how our customers solve that..."
---
### Landmines to Plant
- "How do you currently handle [area where competitor is weak]?"
- "What happens when you need to [scenario competitor struggles with]?"
---
### Traps to Avoid
- Never badmouth [Competitor] directly
- Do not lead with features — lead with the prospect problem
- Do not claim you do everything better — be specific about where you win
---
### When We Win / When We Lose
We win when: [Scenario — e.g. customer prioritises outcome over price]
We lose when: [Honest scenario — e.g. primary driver is lowest upfront cost]
## Example Trigger Phrases
- "Build a battlecard against [competitor]"
- "Create a competitive cheat sheet for [competitor]"
- "Write objection handling for [competitor] comparisons"
+136
View File
@@ -0,0 +1,136 @@
# Examples: pm-figma Skills
## What this bundle does
10 Figma skills covering the full design lifecycle for product managers and designers — from planning what to design, through building components and prototypes, to QA before handoff.
---
## figma-component-audit
### Example 1 — Messy legacy library
**You say:**
> "Audit our Figma component library. We have buttons, inputs, cards, modals, and navigation components but the naming is all over the place and developers keep asking for states we haven't designed."
**Claude produces:**
**Audit Summary**
| Dimension | Status | Score |
|---|---|---|
| Naming consistency | 🔴 Poor | 3/10 |
| Component coverage | 🟡 Partial | 6/10 |
| Variant completeness | 🔴 Poor | 4/10 |
| Overall health | 🟡 Partial | 5/10 |
**Issue: Mixed capitalisation conventions**
- What's happening: `button-primary`, `Button/Primary`, `btn_primary` all exist in the same library
- Fix: Adopt PascalCase for components (`Button`), lowercase slash-separated for variants (`type/primary`, `size/large`, `state/default`)
- Before: `btn_primary_large_hover` → After: `Button` with variants `type/primary`, `size/large`, `state/hover`
**Missing states developers are asking for:**
| Component | Missing | Priority |
|---|---|---|
| Button | Active/pressed state | 🔴 High |
| Input | Error state with helper text | 🔴 High |
| Card | Skeleton loading state | 🟡 Medium |
---
## figma-design-brief
### Example 1 — PRD to design brief
**You say:**
> "Write a design brief for our new notification preferences feature. Users need to control which emails and push notifications they receive. Platform is iOS and Android. We need design ready in 2 weeks."
**Claude produces:**
**Feature:** Notification Preferences
**Platform:** iOS + Android | **Design due:** [2 weeks from today] | **Dev handoff:** [3 weeks]
**The goal:** Users can control their notification preferences without contacting support.
**Success looks like:** >80% of users who visit settings can update their preferences without a support ticket.
**Flows to design:**
1. Entry from Settings > Notifications
2. Toggle individual notification types on/off
3. Save preferences with confirmation
4. Error state if save fails
**Missing from current brief — open questions:**
- [ ] Are email and push controlled separately or together? (PM to confirm)
- [ ] What's the default state for new users? (PM to confirm)
---
## figma-design-qa
### Example 1 — Pre-handoff check
**You say:**
> "QA the checkout flow design before we hand it off to engineering. Web, using our custom design system, standard 30-minute QA."
**Claude produces:**
**Design QA Report: Checkout Flow**
**Overall status:** 🟡 Minor fixes needed
**Section 1: File Hygiene**
- All layers named semantically ✅
- No unused layers ✅
- Components from library ❌ — Order summary card is a detached copy
- Text uses text styles ✅
- Colours use variables ❌ — Button label in step 3 uses hardcoded #FFFFFF instead of `color.text.on-primary`
**Issues Found:**
- **Detached card component — 🟡 Fix before handoff**
- What: Order summary card (frame "Step 2 / Summary") is not linked to library
- Fix: Re-attach to `Card/Summary` library component
- Owner: Designer
---
## figma-design-critique-pm
### Example 1 — PM reviewing a dashboard design
**You say:**
> "Give me a PM critique of our new analytics dashboard design. User goal is to understand their campaign performance at a glance. Business goal is to reduce support tickets about 'why are my numbers down'."
**Claude produces:**
**PM Critique Summary**
Verdict: 🟡 Mostly on track with one significant gap
"The design successfully surfaces the top-line metrics above the fold and the date range selector is prominent. However, the design currently shows no contextual explanation for metric changes — a user whose conversions dropped 40% last week will still need to contact support because there's nothing in the design helping them understand why."
**Goal Alignment Check:**
| Goal | Status | Evidence |
|---|---|---|
| Understand performance at a glance | ✅ Yes | Top 4 KPIs are above fold, well-contrasted |
| Reduce "why are my numbers down" tickets | 🟡 Partial | Metrics shown but no context or anomaly explanation |
**PM Feedback:**
**Missing: Metric change context — 🔴 High impact**
- Observation: Metric cards show current value and % change vs prior period but no explanation of what drove the change
- User impact: A user seeing -40% conversions still has no information to act on without contacting support
- Business impact: Does not address the core support ticket driver — the "why"
- Evidence basis: Hypothesis (we should validate with support ticket analysis)
- Question for designer: Is there data available to surface top contributing factors? Even "top declining campaign" would help.
---
## Tips for best results
- For `figma-design-brief`: paste the actual PRD snippet or ticket — the more specific the requirement, the more useful the brief
- For `figma-design-qa`: describe the platform and design system explicitly — the checklist adapts to iOS vs Android vs Web
- For `figma-design-critique-pm`: always state the business metric — without it, feedback stays generic
- For `figma-variant-matrix`: name the component exactly as it will appear in Figma — Claude uses this for layer naming recommendations
- For `figma-user-flow-planner`: state the starting point and user type — these determine which edge cases are most likely
## Related skills
- `design-critique` — General UX critique using Gestalt and Nielsen heuristics (pm-design bundle)
- `ux-research-plan` — Full research plan for user testing (pm-design bundle)
- `figma-prototype-plan` — Plan what to prototype before building it (this bundle)
+2408
View File
File diff suppressed because it is too large Load Diff
+846
View File
@@ -0,0 +1,846 @@
#!/bin/bash
# =============================================================================
# setup-pm-figma.sh
# Run from the ROOT of your pm-claude-skills repo.
# Creates all 10 Figma skills in both skills/ and plugins/pm-figma/skills/
# =============================================================================
set -e
REPO_ROOT="$(pwd)"
if [ ! -d "$REPO_ROOT/plugins" ] || [ ! -d "$REPO_ROOT/skills" ]; then
echo "ERROR: Run from the root of pm-claude-skills"
exit 1
fi
write_skill() {
local BUNDLE="$1"
local SKILL="$2"
local CONTENT="$3"
mkdir -p "$REPO_ROOT/skills/$SKILL"
mkdir -p "$REPO_ROOT/plugins/$BUNDLE/skills/$SKILL"
printf '%s' "$CONTENT" > "$REPO_ROOT/skills/$SKILL/SKILL.md"
printf '%s' "$CONTENT" > "$REPO_ROOT/plugins/$BUNDLE/skills/$SKILL/SKILL.md"
echo "$SKILL"
}
echo "================================================"
echo " Creating pm-figma skills (10 skills)..."
echo "================================================"
echo ""
# -------------------------------------------------------
# SKILL 1: figma-component-audit
# -------------------------------------------------------
write_skill "pm-figma" "figma-component-audit" '---
name: figma-component-audit
description: "Audit a Figma component library for consistency, coverage gaps, and naming issues. Use when asked to audit components, review a design system, check component consistency, identify missing components, or assess Figma library health. Produces a structured audit report with issues prioritised by impact, naming recommendations, and a fix plan."
---
# Figma Component Audit Skill
Produces a structured audit of a Figma component library — identifying inconsistencies, naming problems, coverage gaps, and prioritised recommendations.
## Required Inputs
- **Component list or description** (paste component names or describe what exists)
- **Product type** (mobile app / web app / desktop / multi-platform)
- **Design system maturity** (new / growing / mature / legacy)
- **Primary concern** (optional)
## Output Structure
### 1. Audit Summary
| Dimension | Status | Score |
|---|---|---|
| Naming consistency | Red/Amber/Green | /10 |
| Component coverage | | /10 |
| Variant completeness | | /10 |
| Documentation | | /10 |
| Overall health | | /10 |
**Verdict:** What is the state of this library and the single most important thing to fix?
### 2. Naming Issues
For each problem:
**Issue: [Problem type]**
- What is happening: [Specific examples]
- Why it matters: [Impact on designers and developers]
- Fix: [Exact naming convention to adopt]
- Examples: Before / After
Naming convention to enforce:
- Components: PascalCase (NavigationBar)
- Variants: Lowercase with slashes (size/large, state/hover)
- Pages: All caps (COMPONENTS, FOUNDATIONS)
### 3. Coverage Gaps
| Missing Component | Priority | Why Needed |
|---|---|---|
| [Component] | High/Medium/Low | [Use case] |
### 4. Variant Completeness Check
| Component | Default | Hover | Active | Disabled | Error | Missing |
|---|---|---|---|---|---|---|
| [Button] | Yes | Yes | No | Yes | No | Active, Error |
### 5. Prioritised Fix Plan
| # | Fix | Effort | Impact | Do First? |
|---|---|---|---|---|
| 1 | [Fix] | Low/Med/High | High | Yes |
## Quality Checks
- [ ] Naming recommendations have before/after examples
- [ ] Coverage gaps are relevant to the product type
- [ ] Fix plan is ordered by impact-to-effort ratio
- [ ] Variant completeness covers all interactive states
## Example Trigger Phrases
- "Audit my Figma component library"
- "Review our design system for consistency issues"
- "What components are we missing in our Figma library?"
- "Our component naming is a mess — help me fix it"
- "Do a health check on our Figma components"'
# -------------------------------------------------------
# SKILL 2: figma-design-brief
# -------------------------------------------------------
write_skill "pm-figma" "figma-design-brief" '---
name: figma-design-brief
description: "Write a structured design brief for a Figma design task from a product requirement or feature request. Use when asked to write a design brief, create a design spec for Figma, turn a PRD into design requirements, or brief a designer on what to build in Figma. Produces a brief with goals, scope, user flows, components needed, constraints, and success criteria."
---
# Figma Design Brief Skill
Converts a product requirement or feature request into a structured design brief — everything a designer needs to open Figma and start building confidently.
## Required Inputs
- **Feature or requirement** (paste PRD snippet, ticket, or describe the feature)
- **User goal** (what is the user trying to accomplish?)
- **Platform** (iOS / Android / Web / Responsive / All)
- **Existing components available** (optional)
- **Timeline** (when does design need to be ready?)
## Output Structure
### 1. Brief Header
Feature, PM, Designer, Platform, Design due, Dev handoff dates.
### 2. What We Are Designing and Why
- **The goal:** [One sentence — user problem being solved]
- **Context:** [2-3 sentences. Why now? What triggers this?]
- **Success looks like:** [Specific observable outcome]
### 3. User Flows to Design
**Flow N: [Flow name]**
- Entry point: [Where user starts]
- Steps: [Numbered key steps]
- Exit point: [Where flow ends]
- Edge cases: [empty state, error state, loading state]
### 4. Screens Required
| Screen | New / Update | Notes |
|---|---|---|
| [Screen] | New | [Key requirement] |
### 5. Components Needed
| Component | In library? | Action |
|---|---|---|
| [Component] | Yes/No/Needs variant | Use/Create/Extend |
### 6. Constraints and Requirements
- Must haves: [Non-negotiable constraints]
- Must avoid: [Design patterns to not use]
- Accessibility: [WCAG level, touch target sizes]
### 7. Open Questions
- [ ] [Question — with owner]
## Quality Checks
- [ ] Goal is outcome-focused (not "design the feature")
- [ ] All flows include edge cases
- [ ] Components table identifies create vs reuse
- [ ] Constraints include accessibility requirements
- [ ] Open questions have owners
## Example Trigger Phrases
- "Write a design brief for [feature]"
- "Turn this PRD into a Figma design brief"
- "Brief the designer on what to build for [requirement]"
- "Create a design spec for [feature] for Figma"
- "What does the designer need to know to design [feature]?"'
# -------------------------------------------------------
# SKILL 3: figma-annotation-guide
# -------------------------------------------------------
write_skill "pm-figma" "figma-annotation-guide" '---
name: figma-annotation-guide
description: "Generate structured developer handoff annotations for a Figma screen or component. Use when asked to write Figma annotations, create dev handoff notes, document a Figma design for developers, or write specs for a screen. Produces a complete annotation set covering interactions, states, spacing, accessibility, and edge cases."
---
# Figma Annotation Guide Skill
Produces a complete set of developer handoff annotations for a Figma screen or component — the notes that turn a visual design into a buildable spec.
## Required Inputs
- **Screen or component description** (describe or summarise what was designed)
- **Platform** (iOS / Android / Web / React Native)
- **Interaction type** (static / interactive / animated / form)
- **Developer audience** (mobile / frontend / full-stack)
## Output Structure
### 1. Screen/Component Overview
Name, purpose, entry points, exit points.
### 2. Interaction Annotations
**[Element name]**
- Default state: [Visual description]
- On tap/click: [Exact action — API call, state change, navigation]
- Loading state: [Description]
- Success state: [What happens after]
- Error state: [What error looks like and user options]
- Disabled condition: [When and why]
### 3. State Inventory
| Element | States Required |
|---|---|
| [Element] | Default, Hover, Active, Disabled, Loading, Error, Empty |
Flag missing designs: "Warning: Error state not designed — needed before build"
### 4. Spacing and Layout Notes
Fixed vs fluid elements, scroll behaviour, breakpoints, safe areas.
### 5. Content and Copy Rules
Character limits, dynamic vs static content, truncation rules, empty states.
### 6. Accessibility Annotations
Touch targets, screen reader labels, focus order, colour contrast, motion preferences.
### 7. Edge Cases and Developer Questions
- [ ] [Unresolved question for developer to flag]
## Quality Checks
- [ ] Every interactive element has all states defined
- [ ] State inventory flags missing designs
- [ ] Accessibility covers touch targets and screen reader labels
- [ ] Empty states specified
- [ ] Edge cases listed as actionable questions
## Example Trigger Phrases
- "Write dev annotations for this Figma screen"
- "Create developer handoff notes for [screen/component]"
- "Document this design for the engineering team"
- "Write the Figma spec for [feature]"
- "What should I annotate before handing off this design?"'
# -------------------------------------------------------
# SKILL 4: figma-design-review
# -------------------------------------------------------
write_skill "pm-figma" "figma-design-review" '---
name: figma-design-review
description: "Run a structured PM design review against product requirements. Use when asked to review a Figma design, check a design against requirements, do a PM design review, or assess whether a design meets the product spec. Produces a requirements coverage check, UX concerns, open questions, and explicit approval status."
---
# Figma Design Review Skill
Runs a structured PM design review — checking that a design meets product requirements, covers all user flows, and is ready for engineering. This is a requirements-and-outcomes review, not an aesthetic critique.
## Required Inputs
- **Design description or screen summary**
- **Original requirements** (PRD snippet, ticket, or acceptance criteria)
- **User flow being designed**
- **Review stage** (concept / mid-fidelity / pre-handoff final)
## Output Structure
### 1. Review Header
Feature, review stage, reviewed by, date.
**Overall status:** Approved / Approved with changes / Needs revision
### 2. Requirements Coverage Check
| Requirement | Covered? | Notes |
|---|---|---|
| [Requirement from PRD] | Yes/No/Partial | [Specific observation] |
Missing coverage summary: [Requirements not addressed — must resolve before approval]
### 3. User Flow Completeness
| Flow step | Designed? | Issues |
|---|---|---|
| [Step] | Yes/No/Partial | [Issue] |
| Error state | Yes/No | |
| Empty state | Yes/No | |
| Loading state | Yes/No | |
### 4. PM Concerns
**[Concern] — Blocking / Should fix / Nice to fix**
- What: [Specific observation]
- Why it matters: [Business or user impact — not aesthetic preference]
- Suggested resolution: [What PM wants to see]
### 5. Open Questions
| Question | Owner | Needed by |
|---|---|---|
| [Question] | Designer/Eng/PM | [Date] |
### 6. Approval Decision
Approved / Approved with changes (list) / Needs revision (focus area + next review date)
## Quality Checks
- [ ] Every requirement assessed
- [ ] All flow states checked (error, empty, loading)
- [ ] Concerns are outcome-focused not aesthetic
- [ ] Open questions have owners
- [ ] Approval status is explicit
## Example Trigger Phrases
- "Review this Figma design against the requirements"
- "Do a PM design review for [feature]"
- "Check if this design meets the product spec"
- "Is this design ready to hand off to engineering?"
- "What is missing from this design before we can build it?"'
# -------------------------------------------------------
# SKILL 5: figma-user-flow-planner
# -------------------------------------------------------
write_skill "pm-figma" "figma-user-flow-planner" '---
name: figma-user-flow-planner
description: "Plan user flows and screen states for a Figma design before any designing starts. Use when asked to plan a user flow, map out screens for a feature, define screen states, plan a Figma file structure, or work out what needs to be designed before opening Figma. Produces a complete flow map with all screens, states, entry/exit points, and a suggested Figma page structure."
---
# Figma User Flow Planner Skill
Plans what needs to be designed before a pixel is touched — mapping all screens, states, entry points, and edge cases so designers do not discover missing states mid-build.
## Required Inputs
- **Feature or task being designed**
- **User type** (who performs this flow?)
- **Platform** (iOS / Android / Web / Multi-platform)
- **Starting point** (where does the user begin?)
- **Known edge cases** (optional)
## Output Structure
### 1. Flow Overview
Feature, user, goal, entry points, success exit, failure exits.
### 2. Screen Map
| # | Screen name | Type | Triggered by | Notes |
|---|---|---|---|---|
| 1 | [Screen] | New/Modal/Drawer/Toast | [What triggers] | [Considerations] |
Screen types to cover: entry, happy path, loading, success, error (network/validation/permission), empty, first-time/onboarding, edge cases.
### 3. State Matrix
**[Screen name]**
| State | Trigger | Visual change | Action available |
|---|---|---|---|
| Default | Page load | [Description] | [What user can do] |
| Loading | User taps action | Skeleton/spinner | None |
| Error | API failure | Error message | Retry/Go back |
| Empty | No data | Empty state | [CTA] |
### 4. Decision Points
**Decision: [Name]**
- If yes: [Screen N]
- If no: [Screen X]
### 5. Suggested Figma File Structure
```
Feature name/
- Cover
- Flow Map
- Happy Path
- Error States
- Empty States
- Edge Cases
- Handoff
```
### 6. What Not to Design Yet
[Explicit out-of-scope items — prevents scope creep]
## Quality Checks
- [ ] All three state types covered: loading, error, empty
- [ ] All decision points mapped with both branches
- [ ] Entry points include all realistic user paths
- [ ] Out-of-scope section is explicit
- [ ] Figma file structure matches screen map
## Example Trigger Phrases
- "Plan the user flow for [feature] in Figma"
- "What screens do I need to design for [feature]?"
- "Map out the states for [feature] before we start designing"
- "Help me structure my Figma file for [feature]"
- "What do we need to design before handing this to the developer?"'
# -------------------------------------------------------
# SKILL 6: figma-variant-matrix
# -------------------------------------------------------
write_skill "pm-figma" "figma-variant-matrix" '---
name: figma-variant-matrix
description: "Define component variants and states systematically for Figma. Use when asked to plan component variants, define states for a component, set up a Figma variant matrix, or work out what properties a component needs before building it. Produces a complete variant matrix with all properties, values, and combinations needed."
---
# Figma Variant Matrix Skill
Defines all variants, properties, and states a component needs before building it in Figma — preventing missing variants discovered after the component is already used across 40 screens.
## Required Inputs
- **Component name** (Button, Card, Input, Badge, Navigation item, etc.)
- **Component purpose** (what does it do, where is it used?)
- **Platform** (iOS / Android / Web / Multi-platform)
- **Design system context** (standalone / part of existing system)
## Output Structure
### 1. Component Overview
Name, category (Interactive/Display/Layout/Form/Navigation/Feedback), used in contexts.
### 2. Variant Properties
| Property | Values | Notes |
|---|---|---|
| Type | Primary, Secondary, Tertiary, Destructive | |
| Size | Large, Medium, Small | |
| State | Default, Hover, Active, Disabled, Loading | |
| Icon | None, Leading, Trailing, Only | |
Total combinations: [N]. Flag if over 50 — consider splitting into multiple components.
### 3. State Definitions
For each state, list only what changes from Default:
- Default: [Full visual spec]
- Hover (web): [Delta from default]
- Active/Pressed: [Delta]
- Disabled: [Delta — use layer-level properties, not opacity on whole component]
- Loading: [What replaces label, interactive during loading?]
- Error (forms): [Border colour, helper text, icon changes]
### 4. Anatomy Breakdown
| Layer name | Purpose | Required? | Notes |
|---|---|---|---|
| container | Background and bounds | Yes | |
| label | Text | Conditional | Hide when icon-only |
| icon-leading | Leading icon slot | No | |
### 5. Token Mapping
| Property | Token | Fallback |
|---|---|---|
| Background default | color.brand.primary | #hex |
| Border radius | radius.medium | 8px |
### 6. Build Order
1. Default state, most common variant
2. Convert to component, add properties
3. Size variants
4. State variants
5. Type variants
6. Icon slot variants last
## Quality Checks
- [ ] All interactive states defined
- [ ] Total variant count calculated, flagged if over 50
- [ ] Every layer named semantically
- [ ] Token mapping covers all visual properties
- [ ] Disabled state uses layer-level properties not opacity
## Example Trigger Phrases
- "Define the variants for a [component] in Figma"
- "What states does my [component] need?"
- "Help me plan the variant matrix for [component]"
- "Set up the Figma properties for a [button/card/input]"
- "What are all the combinations I need for my [component]?"'
# -------------------------------------------------------
# SKILL 7: figma-spacing-system
# -------------------------------------------------------
write_skill "pm-figma" "figma-spacing-system" '---
name: figma-spacing-system
description: "Design a spacing and layout token system for a Figma design system. Use when asked to create a spacing system, define layout tokens, set up a grid system, build a spacing scale, or establish layout foundations for a Figma file. Produces a complete spacing scale, grid definition, component spacing conventions, and Figma implementation guide."
---
# Figma Spacing System Skill
Produces a complete spacing and layout token system — the foundation that makes a design system consistent and developer handoff unambiguous.
## Required Inputs
- **Platform** (iOS / Android / Web / Multi-platform)
- **Base unit** (4px / 8px — default to 8px)
- **Design system name** (for token naming)
- **Component density** (compact / standard / comfortable)
- **Grid requirements** (or "derive from platform standard")
## Output Structure
### 1. Base Unit
[4px or 8px] with rationale. All values must be multiples.
### 2. Spacing Scale
| Token | Value | Use case |
|---|---|---|
| spacing.none | 0px | Removing space intentionally |
| spacing.xs | 4/8px | Icon padding, tight labels |
| spacing.sm | 8/12px | Internal component padding compact |
| spacing.md | 12/16px | Internal component padding standard |
| spacing.lg | 16/24px | Section padding, card internal |
| spacing.xl | 24/32px | Between components |
| spacing.2xl | 32/48px | Section separation |
| spacing.3xl | 48/64px | Page-level breaks |
| spacing.4xl | 64/96px | Hero sections |
### 3. Layout Grid
Mobile (375px): 4 columns, margin [value], gutter [value]
Tablet (768px): 8 columns, margin [value], gutter [value]
Desktop (1440px): 12 columns, margin [value], gutter [value], max content width [value]
### 4. Component Spacing Conventions
| Context | Token | Example |
|---|---|---|
| Button horizontal padding | spacing.md | Left/right |
| Button vertical padding | spacing.sm | Top/bottom |
| Card internal padding | spacing.lg | All sides |
| Input padding | spacing.sm vertical, spacing.md horizontal | |
| Icon gap from label | spacing.xs | |
| Section gap | spacing.xl | |
### 5. Figma Implementation
1. Create SPACING page documenting each token visually
2. Resources > Variables > create Number collection named Spacing
3. Apply variables to Auto Layout padding/gap values
4. Share token names with engineers as-is or via Tokens Studio
### 6. Anti-Patterns to Avoid
- Values not on the scale (13px, 22px) — round to nearest token
- Absolute pixel values in components instead of tokens
- Mixing 4px and 8px base units in the same product
## Quality Checks
- [ ] All token values are multiples of the base unit
- [ ] Scale covers xs through 4xl
- [ ] Grid defined for all relevant breakpoints
- [ ] Component conventions cover common decisions
- [ ] Figma implementation steps included
## Example Trigger Phrases
- "Create a spacing system for our Figma design system"
- "Define our spacing tokens for Figma"
- "Set up a grid and spacing scale for [product]"
- "What spacing values should we use in our design system?"
- "Help me build the layout foundation for our Figma file"'
# -------------------------------------------------------
# SKILL 8: figma-prototype-plan
# -------------------------------------------------------
write_skill "pm-figma" "figma-prototype-plan" '---
name: figma-prototype-plan
description: "Plan prototype interactions and flows for user testing in Figma. Use when asked to plan a Figma prototype, set up prototype interactions, define what to prototype for a user test, or prepare a Figma prototype for usability testing. Produces a prototype scope, interaction specification, test task scripts, and Figma setup guide."
---
# Figma Prototype Plan Skill
Plans what to prototype in Figma and how — scoping to what the user test needs, defining every interaction, and setting up the test scenarios. Prevents over-building and ensures the prototype answers the research question.
## Required Inputs
- **Research question** (what are you trying to learn?)
- **Feature or flow being prototyped**
- **Prototype fidelity** (low wireframe / mid functional / high pixel-perfect)
- **Testing method** (moderated in-person / moderated remote / unmoderated)
- **Number of test tasks**
## Output Structure
### 1. Prototype Scope
**In scope:** [Flows with real interactions — specific screens listed]
**Out of scope:** [Screens to show as static — not worth building as interactive]
**Rationale:** Prototypes should be the minimum needed to test the hypothesis.
### 2. Interaction Specification
**Interaction N: [Description]**
- Trigger: Tap/Swipe/Hover/Form submit
- Element: [Figma layer name]
- Destination: [Figma frame name]
- Animation: Instant/Dissolve/Push left/Push right/Slide up
- Timing: [ms]
- Reset after: Yes/No
### 3. Prototype Flow Diagram
```
[Start frame]
-> Tap "Action"
[Next frame]
-> Tap "Complete" -> [Success frame]
-> Tap "Cancel" -> [Back to start]
```
### 4. Test Task Scripts
**Task N: [Title]**
Scenario (read to participant):
"[Realistic scenario giving context without directing the click path]"
Observing:
- [What to watch for]
Success when: [Specific trigger]
### 5. Figma Setup Guide
- Starting frame: [Name]
- Device preview: [Device]
- Prototype settings: background colour, show device, type
- Sharing: Can view link, reset process between participants
### 6. Build vs Fake Table
| Element | Build | Fake | Notes |
|---|---|---|---|
| Primary CTA flow | Yes | | Core to research |
| Secondary nav | | Yes | Not being tested |
| Error state | Yes | | Testing recovery |
## Quality Checks
- [ ] Scope limited to what the research question requires
- [ ] Every interaction has a named destination frame
- [ ] Task scripts are scenario-based (not "click on X")
- [ ] Success criteria defined for each task
- [ ] Reset process defined for between participants
## Example Trigger Phrases
- "Plan the Figma prototype for our user test on [feature]"
- "What interactions do I need to build for this prototype?"
- "Help me set up a Figma prototype for [research question]"
- "Write the test task scripts for our [feature] prototype"
- "What should I prototype vs leave as static screens?"'
# -------------------------------------------------------
# SKILL 9: figma-design-qa
# -------------------------------------------------------
write_skill "pm-figma" "figma-design-qa" '---
name: figma-design-qa
description: "Run a pre-handoff QA checklist on any Figma design before it goes to engineering. Use when asked to QA a Figma design, do a pre-handoff check, review a design before engineering, or validate a Figma file is ready to build. Produces a structured QA checklist covering file hygiene, component usage, accessibility, and handoff readiness with pass/fail status."
---
# Figma Design QA Skill
Runs a systematic pre-handoff QA check on a Figma design — catching issues that cause engineering back-and-forth before they become expensive.
## Required Inputs
- **Feature or screen being QA-d**
- **Platform** (iOS / Android / Web)
- **Design system** (custom / Material / HIG / None)
- **Handoff tool** (Figma Inspect / Zeplin / Storybook / Direct link)
- **QA depth** (quick 15 min / standard 30 min / thorough 60 min)
## Output Structure
QA Report: [Feature] | [Date] | [Platform]
**Overall status:** Ready / Minor fixes needed / Not ready
### Section 1: File Hygiene
- All layers named semantically (no "Rectangle 12")
- No unused/hidden layers in final frames
- Components from library (not detached copies)
- All text uses text styles (not manual font settings)
- All colours use styles or variables (not hex overrides)
- Frames named to match screen map
- No leftover prototype wires to wrong frames
### Section 2: Component Usage
- All buttons use library component
- All inputs use library component
- All icons from approved icon library
- No custom components that should be in library
- Variants used correctly (right size, state, type)
### Section 3: Content and Copy
- No placeholder text (Lorem ipsum) in final designs
- All copy reviewed and approved
- Realistic content used (not "User Name")
- Long text edge cases tested
- Error messages are human-readable
- Empty states have copy and CTA
### Section 4: States and Coverage
- Default, Loading, Empty, Error, Success states
- Interactive elements have hover/active (web)
- Disabled states designed where applicable
### Section 5: Accessibility
- All text meets WCAG AA contrast (4.5:1 body, 3:1 large)
- UI components meet 3:1 contrast against background
- Touch targets minimum 44x44pt iOS / 48x48dp Android
- Focus states for keyboard/switch navigation (web)
- Information not conveyed by colour alone
- Icons have text labels or accessible names annotated
### Section 6: Handoff Readiness
- Dev annotations on non-obvious interactions
- Spacing uses Auto Layout (not absolute positioning)
- Images/assets exported at correct resolutions
- Design matches approved requirements
- Link to prototype included
### Issues Found
For each fail:
**[Issue] — Blocking / Fix before handoff / Fix in next iteration**
- What: [Specific layer/screen/element]
- Fix: [Exact action needed]
- Owner: [Designer/PM/Both]
### Handoff Decision
Status, signed off by, date.
## Quality Checks
- [ ] All 6 sections completed
- [ ] Every fail has a specific description and fix action
- [ ] Blocking issues separated from minor ones
- [ ] Handoff decision is explicit
## Example Trigger Phrases
- "QA this Figma design before handoff"
- "Run a pre-handoff check on [feature] design"
- "Is this Figma design ready for engineering?"
- "Do a design QA on [screen/feature]"
- "What needs fixing before we hand this off?"'
# -------------------------------------------------------
# SKILL 10: figma-design-critique-pm
# -------------------------------------------------------
write_skill "pm-figma" "figma-design-critique-pm" '---
name: figma-design-critique-pm
description: "Run a PM-perspective design critique focused on product outcomes, user goals, and business requirements — not aesthetics. Use when asked for a PM design critique, a product review of a design, feedback on a Figma design from a product perspective, or when you want to critique a design without being a designer. Produces structured outcome-based feedback tied to user goals and business metrics."
---
# Figma Design Critique — PM Perspective Skill
This skill is specifically for product managers critiquing designs — focused on whether the design achieves the user goal and business outcome, not whether it looks good. Different from the general design-critique skill which covers UX aesthetics; this one centres product thinking.
## Required Inputs
- **Design description or screen summary**
- **User goal** (what is the user trying to accomplish?)
- **Business goal** (what outcome does the product need?)
- **Original requirements** (what was this supposed to do?)
- **Key metric** (what would move if this design works?)
## Output Structure
### 1. PM Critique Summary
User goal, business goal restated.
**Verdict:** On track / Mostly on track / Needs rethinking
One-paragraph summary: what works from a product perspective, and the single most important thing to address.
### 2. Goal Alignment Check
| Goal | Design supports it? | Evidence |
|---|---|---|
| [User goal] | Yes/Partial/No | [Specific observation] |
| [Business goal] | Yes/Partial/No | [Observation] |
| [Key requirement] | Yes/Partial/No | [Observation] |
### 3. PM Feedback (Outcome-Focused)
Every concern must tie to an outcome. "I do not like this layout" is not PM feedback. "This layout puts the primary action below the fold, which will reduce mobile conversion" is PM feedback.
**[Concern] — High/Medium/Low impact**
- Observation: [Neutral description of what the design does]
- User impact: [What this means for the user goal]
- Business impact: [What this means for the metric]
- Evidence basis: [Research/data/analogous patterns/hypothesis — be honest]
- Question for designer: [What to explore — not a directive]
### 4. What the Design Does Well
2-4 specific things working well from a product perspective — with evidence. Not "colours are nice" but "primary CTA is the most prominent element, aligning with conversion goal." Always include this section.
### 5. Questions Before Next Iteration
| Question | Who answers | Why it matters |
|---|---|---|
| [Question] | Designer/PM/Eng | [Impact] |
### 6. PM Recommendation
Approve / Approve with changes (list) / Revise and re-review (one focus area only)
## PM Critique Rules
- Never reference aesthetics as reason for feedback — only outcomes
- "I prefer" is not feedback — "users are likely to" is feedback
- Lead with what is working before what is not
- Ask questions before giving directives
- One primary recommendation — not a redesign in bullets
## Quality Checks
- [ ] Every concern tied to user or business outcome
- [ ] What is working section is genuine and specific
- [ ] Questions section included (not just directives)
- [ ] PM recommendation is explicit
- [ ] Evidence basis stated honestly
## Example Trigger Phrases
- "Give me a PM critique of this design"
- "Review this design from a product perspective"
- "What product feedback do I have on this Figma design?"
- "Critique this design without being a designer"
- "Does this design achieve the user goal?"'
echo ""
echo "================================================"
echo " All 10 pm-figma skills created successfully!"
echo ""
echo " Skills written to:"
echo " skills/figma-component-audit/"
echo " skills/figma-design-brief/"
echo " skills/figma-annotation-guide/"
echo " skills/figma-design-review/"
echo " skills/figma-user-flow-planner/"
echo " skills/figma-variant-matrix/"
echo " skills/figma-spacing-system/"
echo " skills/figma-prototype-plan/"
echo " skills/figma-design-qa/"
echo " skills/figma-design-critique-pm/"
echo ""
echo " And mirrored into:"
echo " plugins/pm-figma/skills/[each skill]/"
echo ""
echo " Next: run create-plugin-json-pm-figma.sh"
echo "================================================"
BIN
View File
Binary file not shown.
+94
View File
@@ -0,0 +1,94 @@
---
name: account-plan
description: "Build a structured account plan for any key customer or target account. Use when asked to create an account plan, key account strategy, strategic account review, or territory plan. Produces a complete account plan with relationship map, growth opportunities, risks, and 90-day action plan."
---
# Account Plan Skill
Produces a structured account plan — the document that separates account managers who grow accounts from those who just service them.
## Required Inputs
- **Account name**
- **Current ARR / revenue**
- **Contract renewal date**
- **Key contacts** (names, roles, relationship strength)
- **Products/services currently in use**
- **Known opportunities or expansion areas**
- **Known risks**
- **Planning horizon** (6 / 12 / 24 months)
## Output Structure
---
# Account Plan: [Account Name]
**Account Manager:** [Name] | **Period:** [Date range]
---
### Account Snapshot
| Metric | Current | Target (EOY) |
|---|---|---|
| ARR / Revenue | £[amount] | £[target] |
| NPS / Health score | [Score] | [Target] |
| Products in use | [List] | [Expansion targets] |
| Renewal date | [Date] | — |
| Risk level | Low / Medium / High | — |
---
### Relationship Map
| Name | Title | Influence | Relationship | Notes |
|---|---|---|---|---|
| [Name] | [Role] | Decision maker / Influencer / User | Strong / Neutral / Weak | [Insight] |
**Relationship gaps:** [Who we do not have access to that we should]
**Executive sponsor:** [Do we have one? If not — who could become one?]
---
### Why They Stay (Retention Anchors)
[2-3 specific reasons this account renews. If the list is short, that is the risk signal.]
---
### Growth Opportunities
| Opportunity | Product | Est. Value | Timeline | Next Action |
|---|---|---|---|---|
| [Opportunity] | [Product] | £[value] | [Q/Year] | [Specific action] |
**Whitespace:** What products do we have that this account does not use, and why?
---
### Risks and Mitigation
| Risk | Likelihood | Impact | Mitigation | Owner |
|---|---|---|---|---|
| [Risk] | H/M/L | H/M/L | [Action] | [Name] |
---
### 90-Day Action Plan
| Action | Why | Owner | Due |
|---|---|---|---|
| [Specific action] | [Why it matters] | [Name] | [Date] |
**Next QBR / EBR:** [Date — if no EBR cadence, flag as a risk]
---
### Success Criteria
At end of [period]:
- Renewed at or above current ARR
- [Expansion opportunity] progressed to [stage]
- Health score moved from [current] to [target]
## Example Trigger Phrases
- "Build an account plan for [customer]"
- "Create a key account strategy for [account]"
- "Help me plan my approach to renewing [account]"
+60
View File
@@ -0,0 +1,60 @@
---
name: budget-variance-analysis
description: "Produce a structured budget variance analysis from actual vs budget figures. Use when asked to analyse budget variances, explain underspend or overspend, write a variance commentary, or investigate why actuals differ from plan. Produces a categorised variance table with root cause analysis and management commentary."
---
# Budget Variance Analysis Skill
Produces a complete variance analysis from numbers through to root cause explanation and management commentary.
## Required Inputs
- **Actuals and budget figures** (paste as table or describe line by line)
- **Period** (month / quarter / YTD)
- **Materiality threshold** (e.g. £10k or 5%)
- **Known reasons for variances** (if any)
- **Audience** (CFO / board / management / auditor)
## Output Structure
### 1. Variance Summary Table
| Line Item | Budget | Actual | Variance £ | Variance % | F/A |
|---|---|---|---|---|---|
| Revenue | | | | | |
| Cost of Sales | | | | | |
| Gross Profit | | | | | |
| Opex | | | | | |
| EBITDA | | | | | |
F = Favourable | A = Adverse
### 2. Material Variance Commentary
For each variance above threshold:
**[Line item] — £[amount] F/A ([%])**
- **Root cause:** [Specific explanation — not "timing" without detail]
- **Permanent or timing?** Will this reverse next period?
- **Management action:** What is being done
- **Forecast impact:** Does this change full-year outlook?
### 3. Top 3 Variances Requiring Attention
Ranked by materiality and strategic significance.
### 4. Forecast Revision
Does the full-year forecast need updating? State revised expectation and key assumptions.
### 5. Executive Summary
3-4 sentences of management commentary suitable for a board pack.
## Quality Checks
- All variances above threshold explained
- Root causes specific (not vague)
- Favourable/Adverse correctly labelled
- Forecast impact stated for material variances
## Example Trigger Phrases
- "Write a variance analysis for these actuals vs budget: [paste]"
- "Explain why we are over budget on [cost line]"
- "Write the variance commentary for our finance review"
- "Produce a budget vs actual analysis for Q[N]"
+83
View File
@@ -0,0 +1,83 @@
---
name: clinical-case-summary
description: "Write a structured clinical case summary or case presentation. Use when asked to write a clinical case summary, case presentation, patient case report, or clinical handover. Produces a structured summary using SBAR or SOAP format. For educational and documentation purposes only — not a substitute for clinical judgement."
---
# Clinical Case Summary Skill
Produces structured clinical case summaries for educational, documentation, and handover purposes.
WARNING: For documentation and educational purposes only. All clinical content must be reviewed by a qualified healthcare professional. This is not clinical advice.
## Required Inputs
- **Purpose** (case presentation / handover / case report / educational / MDT summary)
- **Patient details** (anonymised — age, sex, relevant background)
- **Presenting complaint and history**
- **Examination findings**
- **Investigations and results**
- **Diagnosis or differential diagnoses**
- **Management and treatment**
- **Outcome** (if known)
- **Format preference** (SBAR / SOAP / Standard clinical / Narrative)
---
## Format A: SBAR (Handover / Referral)
**S — Situation**
[Patient identifier anonymised, location, reason for contact in one sentence]
**B — Background**
- Age / sex / relevant past medical history
- Current admission details
- Relevant medications and allergies
- Brief relevant social history
**A — Assessment**
- Current clinical status
- Vital signs if relevant
- Key examination findings
- Working diagnosis or differential
- Recent investigations and results
**R — Recommendation**
- What you need from the recipient
- Urgency level
- Immediate actions already taken
- Questions or concerns
---
## Format B: SOAP Note
**S — Subjective**
[Presenting complaint in patient words. Symptom history: onset, duration, character, severity, associated symptoms, relieving/aggravating factors]
**O — Objective**
- Vital signs: [BP, HR, RR, Temp, O2 sats]
- Examination: [Systematic findings]
- Investigations: [Results with reference ranges]
**A — Assessment**
- Primary diagnosis: [With brief rationale]
- Differential diagnoses: [Ranked with reasoning]
**P — Plan**
- Immediate management
- Investigations ordered
- Treatments initiated with dose, route, frequency
- Referrals
- Safety netting: what to watch for, when to escalate
- Follow-up plan
## Quality Checks
- Patient details fully anonymised
- Allergies and medications included in handover formats
- Safety netting included in SOAP plan
- Disclaimer included
## Example Trigger Phrases
- "Write a clinical handover using SBAR for this patient"
- "Summarise this case in SOAP format"
- "Write a case report for [clinical scenario]"
- "Prepare an MDT summary for this patient"
+54
View File
@@ -0,0 +1,54 @@
---
name: compliance-checklist
description: "Generate a compliance checklist for any regulation, standard, or policy. Use when asked to create a compliance checklist, regulatory review, audit checklist, or policy adherence review. Covers GDPR, ISO 27001, FCA, HIPAA, SOC 2, and other frameworks. Produces a prioritised checklist with pass/fail assessment and remediation actions."
---
# Compliance Checklist Skill
Generates a structured compliance checklist for any regulatory framework with a prioritised gap analysis and remediation actions.
## Required Inputs
- **Framework or regulation** (e.g. GDPR, HIPAA, SOC 2, ISO 27001, FCA Consumer Duty, PCI DSS)
- **Organisation type** (e.g. SaaS company, financial services, NHS trust, law firm)
- **Scope** (e.g. data handling, customer onboarding, IT security, HR processes)
- **Known gaps or concerns** (optional)
## Output Structure
### 1. Framework Overview
- **Regulation/Standard:** [Name and version]
- **Enforcement body:** [Regulator]
- **Overall compliance status:** Red Gaps / Amber Partial / Green Compliant
### 2. Compliance Checklist
| # | Requirement | Status | Priority | Action Required |
|---|---|---|---|---|
| 1 | [Plain English requirement] | Met / Gap / Partial / Unknown | Critical / High / Low | [Specific action] |
Priority definitions:
- Critical: Regulatory breach risk. Remediate immediately.
- High: Significant gap. Address within 30 days.
- Low: Best practice. Address in next review cycle.
### 3. Critical Gaps Summary
List only Critical items with: what is missing, regulatory requirement breached, recommended remediation and owner.
### 4. Recommended Remediation Plan
| Action | Owner | Timeline | Effort |
|---|---|---|---|
| [Specific action] | [Team/role] | [Timeframe] | Low/Med/High |
### 5. Documentation Gaps
Policies, records, or evidence needed to demonstrate compliance.
---
WARNING: This checklist is a starting point based on publicly available guidance. It does not constitute legal or compliance advice.
## Example Trigger Phrases
- "Create a GDPR compliance checklist for our SaaS product"
- "Generate a SOC 2 audit checklist"
- "Review our compliance against FCA Consumer Duty"
- "Build an ISO 27001 gap analysis"
+64
View File
@@ -0,0 +1,64 @@
---
name: contract-review
description: "Review and summarise any contract or legal agreement. Use when asked to review a contract, check an agreement, flag legal risks, or summarise key clauses. Produces a structured review with key terms, flagged clauses, risk rating, and plain English summary. Not a substitute for qualified legal advice."
---
# Contract Review Skill
This skill produces a structured contract review identifying key terms, unusual or high-risk clauses, and a plain English summary. Always include the disclaimer that this is not legal advice.
## Required Inputs
- **Contract text or description** (paste or describe)
- **Reviewer role** (e.g. the party signing, their legal team, a business owner)
- **Contract type** (e.g. SaaS agreement, employment contract, NDA, supplier contract)
- **Key concerns** (optional — e.g. "focus on IP ownership and termination clauses")
## Output Structure
### 1. Contract Overview
- **Type:** [Contract type]
- **Parties:** [Party A and Party B]
- **Effective date / duration:** [If stated]
- **Governing law:** [Jurisdiction]
- **Overall risk rating:** Green Low / Amber Medium / Red High
### 2. Key Terms Summary
| Term | Detail |
|---|---|
| Payment / fees | |
| Term and renewal | |
| Termination rights | |
| Liability cap | |
| IP ownership | |
| Confidentiality | |
| Dispute resolution | |
### 3. Flagged Clauses
For each flagged clause:
**[Risk level] — [Clause name]**
- **What it says:** [Plain English summary]
- **Why it matters:** [Risk or implication]
- **Suggested action:** [Negotiate / Accept / Seek legal advice / Query]
### 4. Missing Clauses
List any standard clauses absent but normally expected for this contract type.
### 5. Plain English Summary
3-5 sentences. What does this contract mean for the party signing it?
### 6. Recommended Next Steps
- [Action 1]
- [Action 2]
---
WARNING: This review is for informational purposes only and does not constitute legal advice. Always consult a qualified solicitor or lawyer before signing any legally binding agreement.
## Example Trigger Phrases
- "Review this contract: [paste]"
- "Flag the key risks in this agreement"
- "Summarise this SaaS contract in plain English"
- "What should I watch out for in this supplier agreement?"
+97
View File
@@ -0,0 +1,97 @@
---
name: discovery-call-prep
description: "Prepare a structured discovery call plan for any prospect. Use when asked to prepare for a sales call, discovery call, prospect meeting, or first call with a potential customer. Produces a call brief with research, hypotheses, questions, and success criteria."
---
# Discovery Call Prep Skill
Produces a complete discovery call brief — research summary, call hypothesis, structured questions, and success criteria — so every call starts with context and ends with a clear next step.
## Required Inputs
- **Prospect company name**
- **Contact name and role**
- **Any known context** (how they found you, prior interaction)
- **Your product/solution** (one line)
- **Call duration** (15 / 30 / 45 / 60 min)
## Output Structure
---
# Discovery Call Brief
**Prospect:** [Company] | **Contact:** [Name, Title] | **Duration:** [X min]
---
### Research Summary
- What they do: [Product/service, customer, business model]
- Size: [Headcount, revenue if public]
- Stage: [Startup / Scaleup / Enterprise]
- Recent news: [Funding, launches, leadership changes — last 90 days]
- Contact background: [Role tenure, previous companies, LinkedIn activity]
- Likely priorities for someone in this role: [Based on title and stage]
---
### Call Hypothesis
Before the call write your best guess:
- **Their most likely pain:** [What someone in this role at this company probably has]
- **Why they would care about us:** [Specific connection to your value]
- **Biggest risk to the deal:** [What might make this not a fit]
Write it down — then test it on the call.
---
### Call Agenda
"Here is what I was thinking for our [X] minutes:
- 2 min: Quick intros
- [X] min: Learn more about your situation
- [X] min: Share how we have helped similar companies
- 5 min: Next steps
Does that work? Anything specific you would like to cover?"
---
### Discovery Questions
Open with context (not a pitch):
- "What prompted you to take this call today?"
- "What does [relevant area] look like for you at the moment?"
Go deeper on pain:
- "How long has [problem] been an issue?"
- "What have you tried to solve it?"
- "What is the impact of not solving this?"
Understand buying context:
- "Who else would be involved in a decision like this?"
- "Have you looked at other solutions?"
- "Is there a reason you are exploring this now?"
Qualify on budget:
- "Have you set aside budget for this kind of initiative?"
Close discovery:
- "Based on what you have told me, it sounds like [summary]. Is that right?"
---
### Success Criteria
This call is successful if we leave with:
- Understanding of specific pain and business impact
- Knowledge of buying process and key stakeholders
- A clear agreed next step (demo / proposal / intro)
- Sense of timeline
This call is NOT successful if we only pitched and got "sounds interesting, send me some info."
---
### Suggested Next Step
"Based on what we discussed, the logical next step would be [specific]. Does [day/time] work?"
## Example Trigger Phrases
- "Prepare me for a discovery call with [company/contact]"
- "Build a call brief for my meeting with [name] at [company]"
- "What questions should I ask in a discovery call for [use case]?"
@@ -0,0 +1,86 @@
---
name: employee-engagement-survey
description: "Design an employee engagement survey and analyse results. Use when asked to create an employee survey, engagement questionnaire, pulse survey, or eNPS survey. Also use when asked to analyse survey results. Produces a complete survey with questions, rating scales, and an analysis framework."
---
# Employee Engagement Survey Skill
Designs complete employee engagement surveys and provides a framework for analysing and acting on results.
## Mode Detection
- User provides survey results -> Analysis mode
- User wants to create a survey -> Design mode
---
## Design Mode
### Required Inputs
- Survey type (annual / quarterly pulse / post-onboarding / exit / specific topic)
- Company size and stage
- Key areas of concern (optional)
- Anonymity approach
- Length target (short: 5-10 / standard: 15-25 / comprehensive: 30+)
### Opening Statement (always include)
"This survey is anonymous. Your responses help us understand what is working and what to improve. Results will be shared with [who] and we will communicate actions taken by [date]."
### Core Questions
**Overall Engagement**
1. On a scale of 0-10, how likely are you to recommend [Company] as a great place to work? (eNPS)
2. I feel proud to work at [Company]. [1-5]
3. I intend to still be working here in 12 months. [1-5]
**Role and Clarity**
4. I understand how my work contributes to company goals. [1-5]
5. I have the tools and resources I need to do my job. [1-5]
6. My workload is manageable. [1-5]
**Manager and Team**
7. My manager gives useful feedback. [1-5]
8. My manager cares about my development. [1-5]
9. I feel part of a team that works well together. [1-5]
**Culture and Belonging**
10. I feel I can be myself at work. [1-5]
11. People treat each other with respect. [1-5]
12. [Company] lives by its stated values. [1-5]
**Growth and Recognition**
13. I have opportunities to grow and develop. [1-5]
14. My contributions are recognised. [1-5]
15. I have had a meaningful career conversation in the last 6 months. [Yes/No]
**Open questions (always include)**
- What is one thing [Company] should start doing?
- What is one thing [Company] should stop doing?
- Anything else to share?
---
## Analysis Mode
### Analysis Output
**1. Headline Scores**
| Metric | Score | Benchmark | Trend |
|---|---|---|---|
| eNPS | [-100 to +100] | Industry avg | vs last survey |
eNPS: Below 0 = Concerning / 0-30 = Good / 30-70 = Great / 70+ = Excellent
**2. Strengths** — Top scoring areas with evidence.
**3. Improvement Areas** — 3 lowest scoring areas with verbatim comment themes.
**4. Action Planning Template**
| Improvement area | Action | Owner | Timeline | Measure |
|---|---|---|---|---|
**5. Communication Template** — Draft message to share results with employees.
## Example Trigger Phrases
- "Create an employee engagement survey for our team"
- "Design a pulse survey for [topic]"
- "Analyse these engagement survey results: [paste]"
+98
View File
@@ -0,0 +1,98 @@
---
name: executive-summary
description: "Write an executive summary for any document, report, or proposal. Use when asked to write an executive summary, management summary, briefing paper, or one-pager for senior stakeholders. Produces a structured summary that busy executives can read in under 3 minutes and act on."
---
# Executive Summary Skill
Writes executive summaries that busy decision-makers actually read — front-loaded with conclusions, structured for skimming, ruthless about what to include.
## Required Inputs
- **Source document or topic** (paste or describe)
- **Audience** (CEO / board / investor / minister / client / committee)
- **Decision or action needed** (what should the reader do after reading?)
- **Length limit** (1 page / 2 pages / 500 words)
- **Format** (formal report / slide / email / briefing paper)
## Core Principle
An executive summary is NOT a summary of the document. It is a standalone document that:
- States the conclusion upfront — not at the end
- Contains only what the reader needs to make a decision
- Can be understood without reading anything else
- Recommends a specific action
## Output Structure
---
### [Title]
**Executive Summary**
*Prepared for: [Audience] | Date: [Date] | Author: [Name]*
---
**Bottom line up front:**
[The most important thing. The recommendation or finding. 2-3 sentences. A reader who only reads this should know what you are asking or telling them.]
---
**Background (why this matters):**
[2-3 sentences. Minimum context to understand the bottom line. Not the history — just what the reader needs now.]
---
**Key findings / analysis:**
- **[Finding 1]:** [One sentence — specific and evidence-based]
- **[Finding 2]:** [One sentence]
- **[Finding 3]:** [One sentence]
---
**Options considered:** (include only if a decision is being presented)
| Option | Benefit | Risk | Recommendation |
|---|---|---|---|
| [Option A] | [Benefit] | [Risk] | Recommended |
| [Option B] | [Benefit] | [Risk] | Not recommended |
---
**Recommendation:**
[Specific. "We recommend [action] because [reason]. This will [outcome]." Not "we suggest consideration of options."]
---
**Immediate next steps:**
- [Action 1 — specific, with owner and date]
- [Action 2]
---
**Risks of inaction:** [What happens if the reader does nothing]
**Full report:** [Reference to where the full document can be found]
---
## Adapting for Different Audiences
**CEO/MD:** Lead with financial or strategic impact. 1 page. Make the decision binary. Ask in sentence one.
**Board:** Lead with governance or risk. Frame against organisational objectives. State specifically what you need from them.
**Investor:** Lead with return or opportunity. Specific numbers. 1 page. Anticipate "why now."
**Minister/senior public sector:** Lead with public benefit or policy alignment. Include cost-benefit framing.
**Client:** Lead with their problem. Show you understand before presenting recommendation.
## Quality Checks
- Bottom line in first 3 sentences
- Standalone — no need to read full document
- Recommendation is specific
- Fits length limit
- Written for audience priorities not author priorities
- Next steps have owners and dates
## Example Trigger Phrases
- "Write an executive summary of this report: [paste]"
- "Summarise this document for the board: [paste]"
- "Create a one-pager from this proposal for the CEO"
- "Turn these findings into an exec summary"
+64
View File
@@ -0,0 +1,64 @@
---
name: figma-annotation-guide
description: "Generate structured developer handoff annotations for a Figma screen or component. Use when asked to write Figma annotations, create dev handoff notes, document a Figma design for developers, or write specs for a screen. Produces a complete annotation set covering interactions, states, spacing, accessibility, and edge cases."
---
# Figma Annotation Guide Skill
Produces a complete set of developer handoff annotations for a Figma screen or component — the notes that turn a visual design into a buildable spec.
## Required Inputs
- **Screen or component description** (describe or summarise what was designed)
- **Platform** (iOS / Android / Web / React Native)
- **Interaction type** (static / interactive / animated / form)
- **Developer audience** (mobile / frontend / full-stack)
## Output Structure
### 1. Screen/Component Overview
Name, purpose, entry points, exit points.
### 2. Interaction Annotations
**[Element name]**
- Default state: [Visual description]
- On tap/click: [Exact action — API call, state change, navigation]
- Loading state: [Description]
- Success state: [What happens after]
- Error state: [What error looks like and user options]
- Disabled condition: [When and why]
### 3. State Inventory
| Element | States Required |
|---|---|
| [Element] | Default, Hover, Active, Disabled, Loading, Error, Empty |
Flag missing designs: "Warning: Error state not designed — needed before build"
### 4. Spacing and Layout Notes
Fixed vs fluid elements, scroll behaviour, breakpoints, safe areas.
### 5. Content and Copy Rules
Character limits, dynamic vs static content, truncation rules, empty states.
### 6. Accessibility Annotations
Touch targets, screen reader labels, focus order, colour contrast, motion preferences.
### 7. Edge Cases and Developer Questions
- [ ] [Unresolved question for developer to flag]
## Quality Checks
- [ ] Every interactive element has all states defined
- [ ] State inventory flags missing designs
- [ ] Accessibility covers touch targets and screen reader labels
- [ ] Empty states specified
- [ ] Edge cases listed as actionable questions
## Example Trigger Phrases
- "Write dev annotations for this Figma screen"
- "Create developer handoff notes for [screen/component]"
- "Document this design for the engineering team"
- "Write the Figma spec for [feature]"
- "What should I annotate before handing off this design?"
+74
View File
@@ -0,0 +1,74 @@
---
name: figma-component-audit
description: "Audit a Figma component library for consistency, coverage gaps, and naming issues. Use when asked to audit components, review a design system, check component consistency, identify missing components, or assess Figma library health. Produces a structured audit report with issues prioritised by impact, naming recommendations, and a fix plan."
---
# Figma Component Audit Skill
Produces a structured audit of a Figma component library — identifying inconsistencies, naming problems, coverage gaps, and prioritised recommendations.
## Required Inputs
- **Component list or description** (paste component names or describe what exists)
- **Product type** (mobile app / web app / desktop / multi-platform)
- **Design system maturity** (new / growing / mature / legacy)
- **Primary concern** (optional)
## Output Structure
### 1. Audit Summary
| Dimension | Status | Score |
|---|---|---|
| Naming consistency | Red/Amber/Green | /10 |
| Component coverage | | /10 |
| Variant completeness | | /10 |
| Documentation | | /10 |
| Overall health | | /10 |
**Verdict:** What is the state of this library and the single most important thing to fix?
### 2. Naming Issues
For each problem:
**Issue: [Problem type]**
- What is happening: [Specific examples]
- Why it matters: [Impact on designers and developers]
- Fix: [Exact naming convention to adopt]
- Examples: Before / After
Naming convention to enforce:
- Components: PascalCase (NavigationBar)
- Variants: Lowercase with slashes (size/large, state/hover)
- Pages: All caps (COMPONENTS, FOUNDATIONS)
### 3. Coverage Gaps
| Missing Component | Priority | Why Needed |
|---|---|---|
| [Component] | High/Medium/Low | [Use case] |
### 4. Variant Completeness Check
| Component | Default | Hover | Active | Disabled | Error | Missing |
|---|---|---|---|---|---|---|
| [Button] | Yes | Yes | No | Yes | No | Active, Error |
### 5. Prioritised Fix Plan
| # | Fix | Effort | Impact | Do First? |
|---|---|---|---|---|
| 1 | [Fix] | Low/Med/High | High | Yes |
## Quality Checks
- [ ] Naming recommendations have before/after examples
- [ ] Coverage gaps are relevant to the product type
- [ ] Fix plan is ordered by impact-to-effort ratio
- [ ] Variant completeness covers all interactive states
## Example Trigger Phrases
- "Audit my Figma component library"
- "Review our design system for consistency issues"
- "What components are we missing in our Figma library?"
- "Our component naming is a mess — help me fix it"
- "Do a health check on our Figma components"
+68
View File
@@ -0,0 +1,68 @@
---
name: figma-design-brief
description: "Write a structured design brief for a Figma design task from a product requirement or feature request. Use when asked to write a design brief, create a design spec for Figma, turn a PRD into design requirements, or brief a designer on what to build in Figma. Produces a brief with goals, scope, user flows, components needed, constraints, and success criteria."
---
# Figma Design Brief Skill
Converts a product requirement or feature request into a structured design brief — everything a designer needs to open Figma and start building confidently.
## Required Inputs
- **Feature or requirement** (paste PRD snippet, ticket, or describe the feature)
- **User goal** (what is the user trying to accomplish?)
- **Platform** (iOS / Android / Web / Responsive / All)
- **Existing components available** (optional)
- **Timeline** (when does design need to be ready?)
## Output Structure
### 1. Brief Header
Feature, PM, Designer, Platform, Design due, Dev handoff dates.
### 2. What We Are Designing and Why
- **The goal:** [One sentence — user problem being solved]
- **Context:** [2-3 sentences. Why now? What triggers this?]
- **Success looks like:** [Specific observable outcome]
### 3. User Flows to Design
**Flow N: [Flow name]**
- Entry point: [Where user starts]
- Steps: [Numbered key steps]
- Exit point: [Where flow ends]
- Edge cases: [empty state, error state, loading state]
### 4. Screens Required
| Screen | New / Update | Notes |
|---|---|---|
| [Screen] | New | [Key requirement] |
### 5. Components Needed
| Component | In library? | Action |
|---|---|---|
| [Component] | Yes/No/Needs variant | Use/Create/Extend |
### 6. Constraints and Requirements
- Must haves: [Non-negotiable constraints]
- Must avoid: [Design patterns to not use]
- Accessibility: [WCAG level, touch target sizes]
### 7. Open Questions
- [ ] [Question — with owner]
## Quality Checks
- [ ] Goal is outcome-focused (not "design the feature")
- [ ] All flows include edge cases
- [ ] Components table identifies create vs reuse
- [ ] Constraints include accessibility requirements
- [ ] Open questions have owners
## Example Trigger Phrases
- "Write a design brief for [feature]"
- "Turn this PRD into a Figma design brief"
- "Brief the designer on what to build for [requirement]"
- "Create a design spec for [feature] for Figma"
- "What does the designer need to know to design [feature]?"
+76
View File
@@ -0,0 +1,76 @@
---
name: figma-design-critique-pm
description: "Run a PM-perspective design critique focused on product outcomes, user goals, and business requirements — not aesthetics. Use when asked for a PM design critique, a product review of a design, feedback on a Figma design from a product perspective, or when you want to critique a design without being a designer. Produces structured outcome-based feedback tied to user goals and business metrics."
---
# Figma Design Critique — PM Perspective Skill
This skill is specifically for product managers critiquing designs — focused on whether the design achieves the user goal and business outcome, not whether it looks good. Different from the general design-critique skill which covers UX aesthetics; this one centres product thinking.
## Required Inputs
- **Design description or screen summary**
- **User goal** (what is the user trying to accomplish?)
- **Business goal** (what outcome does the product need?)
- **Original requirements** (what was this supposed to do?)
- **Key metric** (what would move if this design works?)
## Output Structure
### 1. PM Critique Summary
User goal, business goal restated.
**Verdict:** On track / Mostly on track / Needs rethinking
One-paragraph summary: what works from a product perspective, and the single most important thing to address.
### 2. Goal Alignment Check
| Goal | Design supports it? | Evidence |
|---|---|---|
| [User goal] | Yes/Partial/No | [Specific observation] |
| [Business goal] | Yes/Partial/No | [Observation] |
| [Key requirement] | Yes/Partial/No | [Observation] |
### 3. PM Feedback (Outcome-Focused)
Every concern must tie to an outcome. "I do not like this layout" is not PM feedback. "This layout puts the primary action below the fold, which will reduce mobile conversion" is PM feedback.
**[Concern] — High/Medium/Low impact**
- Observation: [Neutral description of what the design does]
- User impact: [What this means for the user goal]
- Business impact: [What this means for the metric]
- Evidence basis: [Research/data/analogous patterns/hypothesis — be honest]
- Question for designer: [What to explore — not a directive]
### 4. What the Design Does Well
2-4 specific things working well from a product perspective — with evidence. Not "colours are nice" but "primary CTA is the most prominent element, aligning with conversion goal." Always include this section.
### 5. Questions Before Next Iteration
| Question | Who answers | Why it matters |
|---|---|---|
| [Question] | Designer/PM/Eng | [Impact] |
### 6. PM Recommendation
Approve / Approve with changes (list) / Revise and re-review (one focus area only)
## PM Critique Rules
- Never reference aesthetics as reason for feedback — only outcomes
- "I prefer" is not feedback — "users are likely to" is feedback
- Lead with what is working before what is not
- Ask questions before giving directives
- One primary recommendation — not a redesign in bullets
## Quality Checks
- [ ] Every concern tied to user or business outcome
- [ ] What is working section is genuine and specific
- [ ] Questions section included (not just directives)
- [ ] PM recommendation is explicit
- [ ] Evidence basis stated honestly
## Example Trigger Phrases
- "Give me a PM critique of this design"
- "Review this design from a product perspective"
- "What product feedback do I have on this Figma design?"
- "Critique this design without being a designer"
- "Does this design achieve the user goal?"
+88
View File
@@ -0,0 +1,88 @@
---
name: figma-design-qa
description: "Run a pre-handoff QA checklist on any Figma design before it goes to engineering. Use when asked to QA a Figma design, do a pre-handoff check, review a design before engineering, or validate a Figma file is ready to build. Produces a structured QA checklist covering file hygiene, component usage, accessibility, and handoff readiness with pass/fail status."
---
# Figma Design QA Skill
Runs a systematic pre-handoff QA check on a Figma design — catching issues that cause engineering back-and-forth before they become expensive.
## Required Inputs
- **Feature or screen being QA-d**
- **Platform** (iOS / Android / Web)
- **Design system** (custom / Material / HIG / None)
- **Handoff tool** (Figma Inspect / Zeplin / Storybook / Direct link)
- **QA depth** (quick 15 min / standard 30 min / thorough 60 min)
## Output Structure
QA Report: [Feature] | [Date] | [Platform]
**Overall status:** Ready / Minor fixes needed / Not ready
### Section 1: File Hygiene
- All layers named semantically (no "Rectangle 12")
- No unused/hidden layers in final frames
- Components from library (not detached copies)
- All text uses text styles (not manual font settings)
- All colours use styles or variables (not hex overrides)
- Frames named to match screen map
- No leftover prototype wires to wrong frames
### Section 2: Component Usage
- All buttons use library component
- All inputs use library component
- All icons from approved icon library
- No custom components that should be in library
- Variants used correctly (right size, state, type)
### Section 3: Content and Copy
- No placeholder text (Lorem ipsum) in final designs
- All copy reviewed and approved
- Realistic content used (not "User Name")
- Long text edge cases tested
- Error messages are human-readable
- Empty states have copy and CTA
### Section 4: States and Coverage
- Default, Loading, Empty, Error, Success states
- Interactive elements have hover/active (web)
- Disabled states designed where applicable
### Section 5: Accessibility
- All text meets WCAG AA contrast (4.5:1 body, 3:1 large)
- UI components meet 3:1 contrast against background
- Touch targets minimum 44x44pt iOS / 48x48dp Android
- Focus states for keyboard/switch navigation (web)
- Information not conveyed by colour alone
- Icons have text labels or accessible names annotated
### Section 6: Handoff Readiness
- Dev annotations on non-obvious interactions
- Spacing uses Auto Layout (not absolute positioning)
- Images/assets exported at correct resolutions
- Design matches approved requirements
- Link to prototype included
### Issues Found
For each fail:
**[Issue] — Blocking / Fix before handoff / Fix in next iteration**
- What: [Specific layer/screen/element]
- Fix: [Exact action needed]
- Owner: [Designer/PM/Both]
### Handoff Decision
Status, signed off by, date.
## Quality Checks
- [ ] All 6 sections completed
- [ ] Every fail has a specific description and fix action
- [ ] Blocking issues separated from minor ones
- [ ] Handoff decision is explicit
## Example Trigger Phrases
- "QA this Figma design before handoff"
- "Run a pre-handoff check on [feature] design"
- "Is this Figma design ready for engineering?"
- "Do a design QA on [screen/feature]"
- "What needs fixing before we hand this off?"
+68
View File
@@ -0,0 +1,68 @@
---
name: figma-design-review
description: "Run a structured PM design review against product requirements. Use when asked to review a Figma design, check a design against requirements, do a PM design review, or assess whether a design meets the product spec. Produces a requirements coverage check, UX concerns, open questions, and explicit approval status."
---
# Figma Design Review Skill
Runs a structured PM design review — checking that a design meets product requirements, covers all user flows, and is ready for engineering. This is a requirements-and-outcomes review, not an aesthetic critique.
## Required Inputs
- **Design description or screen summary**
- **Original requirements** (PRD snippet, ticket, or acceptance criteria)
- **User flow being designed**
- **Review stage** (concept / mid-fidelity / pre-handoff final)
## Output Structure
### 1. Review Header
Feature, review stage, reviewed by, date.
**Overall status:** Approved / Approved with changes / Needs revision
### 2. Requirements Coverage Check
| Requirement | Covered? | Notes |
|---|---|---|
| [Requirement from PRD] | Yes/No/Partial | [Specific observation] |
Missing coverage summary: [Requirements not addressed — must resolve before approval]
### 3. User Flow Completeness
| Flow step | Designed? | Issues |
|---|---|---|
| [Step] | Yes/No/Partial | [Issue] |
| Error state | Yes/No | |
| Empty state | Yes/No | |
| Loading state | Yes/No | |
### 4. PM Concerns
**[Concern] — Blocking / Should fix / Nice to fix**
- What: [Specific observation]
- Why it matters: [Business or user impact — not aesthetic preference]
- Suggested resolution: [What PM wants to see]
### 5. Open Questions
| Question | Owner | Needed by |
|---|---|---|
| [Question] | Designer/Eng/PM | [Date] |
### 6. Approval Decision
Approved / Approved with changes (list) / Needs revision (focus area + next review date)
## Quality Checks
- [ ] Every requirement assessed
- [ ] All flow states checked (error, empty, loading)
- [ ] Concerns are outcome-focused not aesthetic
- [ ] Open questions have owners
- [ ] Approval status is explicit
## Example Trigger Phrases
- "Review this Figma design against the requirements"
- "Do a PM design review for [feature]"
- "Check if this design meets the product spec"
- "Is this design ready to hand off to engineering?"
- "What is missing from this design before we can build it?"
+84
View File
@@ -0,0 +1,84 @@
---
name: figma-prototype-plan
description: "Plan prototype interactions and flows for user testing in Figma. Use when asked to plan a Figma prototype, set up prototype interactions, define what to prototype for a user test, or prepare a Figma prototype for usability testing. Produces a prototype scope, interaction specification, test task scripts, and Figma setup guide."
---
# Figma Prototype Plan Skill
Plans what to prototype in Figma and how — scoping to what the user test needs, defining every interaction, and setting up the test scenarios. Prevents over-building and ensures the prototype answers the research question.
## Required Inputs
- **Research question** (what are you trying to learn?)
- **Feature or flow being prototyped**
- **Prototype fidelity** (low wireframe / mid functional / high pixel-perfect)
- **Testing method** (moderated in-person / moderated remote / unmoderated)
- **Number of test tasks**
## Output Structure
### 1. Prototype Scope
**In scope:** [Flows with real interactions — specific screens listed]
**Out of scope:** [Screens to show as static — not worth building as interactive]
**Rationale:** Prototypes should be the minimum needed to test the hypothesis.
### 2. Interaction Specification
**Interaction N: [Description]**
- Trigger: Tap/Swipe/Hover/Form submit
- Element: [Figma layer name]
- Destination: [Figma frame name]
- Animation: Instant/Dissolve/Push left/Push right/Slide up
- Timing: [ms]
- Reset after: Yes/No
### 3. Prototype Flow Diagram
```
[Start frame]
-> Tap "Action"
[Next frame]
-> Tap "Complete" -> [Success frame]
-> Tap "Cancel" -> [Back to start]
```
### 4. Test Task Scripts
**Task N: [Title]**
Scenario (read to participant):
"[Realistic scenario giving context without directing the click path]"
Observing:
- [What to watch for]
Success when: [Specific trigger]
### 5. Figma Setup Guide
- Starting frame: [Name]
- Device preview: [Device]
- Prototype settings: background colour, show device, type
- Sharing: Can view link, reset process between participants
### 6. Build vs Fake Table
| Element | Build | Fake | Notes |
|---|---|---|---|
| Primary CTA flow | Yes | | Core to research |
| Secondary nav | | Yes | Not being tested |
| Error state | Yes | | Testing recovery |
## Quality Checks
- [ ] Scope limited to what the research question requires
- [ ] Every interaction has a named destination frame
- [ ] Task scripts are scenario-based (not "click on X")
- [ ] Success criteria defined for each task
- [ ] Reset process defined for between participants
## Example Trigger Phrases
- "Plan the Figma prototype for our user test on [feature]"
- "What interactions do I need to build for this prototype?"
- "Help me set up a Figma prototype for [research question]"
- "Write the test task scripts for our [feature] prototype"
- "What should I prototype vs leave as static screens?"
+77
View File
@@ -0,0 +1,77 @@
---
name: figma-spacing-system
description: "Design a spacing and layout token system for a Figma design system. Use when asked to create a spacing system, define layout tokens, set up a grid system, build a spacing scale, or establish layout foundations for a Figma file. Produces a complete spacing scale, grid definition, component spacing conventions, and Figma implementation guide."
---
# Figma Spacing System Skill
Produces a complete spacing and layout token system — the foundation that makes a design system consistent and developer handoff unambiguous.
## Required Inputs
- **Platform** (iOS / Android / Web / Multi-platform)
- **Base unit** (4px / 8px — default to 8px)
- **Design system name** (for token naming)
- **Component density** (compact / standard / comfortable)
- **Grid requirements** (or "derive from platform standard")
## Output Structure
### 1. Base Unit
[4px or 8px] with rationale. All values must be multiples.
### 2. Spacing Scale
| Token | Value | Use case |
|---|---|---|
| spacing.none | 0px | Removing space intentionally |
| spacing.xs | 4/8px | Icon padding, tight labels |
| spacing.sm | 8/12px | Internal component padding compact |
| spacing.md | 12/16px | Internal component padding standard |
| spacing.lg | 16/24px | Section padding, card internal |
| spacing.xl | 24/32px | Between components |
| spacing.2xl | 32/48px | Section separation |
| spacing.3xl | 48/64px | Page-level breaks |
| spacing.4xl | 64/96px | Hero sections |
### 3. Layout Grid
Mobile (375px): 4 columns, margin [value], gutter [value]
Tablet (768px): 8 columns, margin [value], gutter [value]
Desktop (1440px): 12 columns, margin [value], gutter [value], max content width [value]
### 4. Component Spacing Conventions
| Context | Token | Example |
|---|---|---|
| Button horizontal padding | spacing.md | Left/right |
| Button vertical padding | spacing.sm | Top/bottom |
| Card internal padding | spacing.lg | All sides |
| Input padding | spacing.sm vertical, spacing.md horizontal | |
| Icon gap from label | spacing.xs | |
| Section gap | spacing.xl | |
### 5. Figma Implementation
1. Create SPACING page documenting each token visually
2. Resources > Variables > create Number collection named Spacing
3. Apply variables to Auto Layout padding/gap values
4. Share token names with engineers as-is or via Tokens Studio
### 6. Anti-Patterns to Avoid
- Values not on the scale (13px, 22px) — round to nearest token
- Absolute pixel values in components instead of tokens
- Mixing 4px and 8px base units in the same product
## Quality Checks
- [ ] All token values are multiples of the base unit
- [ ] Scale covers xs through 4xl
- [ ] Grid defined for all relevant breakpoints
- [ ] Component conventions cover common decisions
- [ ] Figma implementation steps included
## Example Trigger Phrases
- "Create a spacing system for our Figma design system"
- "Define our spacing tokens for Figma"
- "Set up a grid and spacing scale for [product]"
- "What spacing values should we use in our design system?"
- "Help me build the layout foundation for our Figma file"
+76
View File
@@ -0,0 +1,76 @@
---
name: figma-user-flow-planner
description: "Plan user flows and screen states for a Figma design before any designing starts. Use when asked to plan a user flow, map out screens for a feature, define screen states, plan a Figma file structure, or work out what needs to be designed before opening Figma. Produces a complete flow map with all screens, states, entry/exit points, and a suggested Figma page structure."
---
# Figma User Flow Planner Skill
Plans what needs to be designed before a pixel is touched — mapping all screens, states, entry points, and edge cases so designers do not discover missing states mid-build.
## Required Inputs
- **Feature or task being designed**
- **User type** (who performs this flow?)
- **Platform** (iOS / Android / Web / Multi-platform)
- **Starting point** (where does the user begin?)
- **Known edge cases** (optional)
## Output Structure
### 1. Flow Overview
Feature, user, goal, entry points, success exit, failure exits.
### 2. Screen Map
| # | Screen name | Type | Triggered by | Notes |
|---|---|---|---|---|
| 1 | [Screen] | New/Modal/Drawer/Toast | [What triggers] | [Considerations] |
Screen types to cover: entry, happy path, loading, success, error (network/validation/permission), empty, first-time/onboarding, edge cases.
### 3. State Matrix
**[Screen name]**
| State | Trigger | Visual change | Action available |
|---|---|---|---|
| Default | Page load | [Description] | [What user can do] |
| Loading | User taps action | Skeleton/spinner | None |
| Error | API failure | Error message | Retry/Go back |
| Empty | No data | Empty state | [CTA] |
### 4. Decision Points
**Decision: [Name]**
- If yes: [Screen N]
- If no: [Screen X]
### 5. Suggested Figma File Structure
```
Feature name/
- Cover
- Flow Map
- Happy Path
- Error States
- Empty States
- Edge Cases
- Handoff
```
### 6. What Not to Design Yet
[Explicit out-of-scope items — prevents scope creep]
## Quality Checks
- [ ] All three state types covered: loading, error, empty
- [ ] All decision points mapped with both branches
- [ ] Entry points include all realistic user paths
- [ ] Out-of-scope section is explicit
- [ ] Figma file structure matches screen map
## Example Trigger Phrases
- "Plan the user flow for [feature] in Figma"
- "What screens do I need to design for [feature]?"
- "Map out the states for [feature] before we start designing"
- "Help me structure my Figma file for [feature]"
- "What do we need to design before handing this to the developer?"
+78
View File
@@ -0,0 +1,78 @@
---
name: figma-variant-matrix
description: "Define component variants and states systematically for Figma. Use when asked to plan component variants, define states for a component, set up a Figma variant matrix, or work out what properties a component needs before building it. Produces a complete variant matrix with all properties, values, and combinations needed."
---
# Figma Variant Matrix Skill
Defines all variants, properties, and states a component needs before building it in Figma — preventing missing variants discovered after the component is already used across 40 screens.
## Required Inputs
- **Component name** (Button, Card, Input, Badge, Navigation item, etc.)
- **Component purpose** (what does it do, where is it used?)
- **Platform** (iOS / Android / Web / Multi-platform)
- **Design system context** (standalone / part of existing system)
## Output Structure
### 1. Component Overview
Name, category (Interactive/Display/Layout/Form/Navigation/Feedback), used in contexts.
### 2. Variant Properties
| Property | Values | Notes |
|---|---|---|
| Type | Primary, Secondary, Tertiary, Destructive | |
| Size | Large, Medium, Small | |
| State | Default, Hover, Active, Disabled, Loading | |
| Icon | None, Leading, Trailing, Only | |
Total combinations: [N]. Flag if over 50 — consider splitting into multiple components.
### 3. State Definitions
For each state, list only what changes from Default:
- Default: [Full visual spec]
- Hover (web): [Delta from default]
- Active/Pressed: [Delta]
- Disabled: [Delta — use layer-level properties, not opacity on whole component]
- Loading: [What replaces label, interactive during loading?]
- Error (forms): [Border colour, helper text, icon changes]
### 4. Anatomy Breakdown
| Layer name | Purpose | Required? | Notes |
|---|---|---|---|
| container | Background and bounds | Yes | |
| label | Text | Conditional | Hide when icon-only |
| icon-leading | Leading icon slot | No | |
### 5. Token Mapping
| Property | Token | Fallback |
|---|---|---|
| Background default | color.brand.primary | #hex |
| Border radius | radius.medium | 8px |
### 6. Build Order
1. Default state, most common variant
2. Convert to component, add properties
3. Size variants
4. State variants
5. Type variants
6. Icon slot variants last
## Quality Checks
- [ ] All interactive states defined
- [ ] Total variant count calculated, flagged if over 50
- [ ] Every layer named semantically
- [ ] Token mapping covers all visual properties
- [ ] Disabled state uses layer-level properties not opacity
## Example Trigger Phrases
- "Define the variants for a [component] in Figma"
- "What states does my [component] need?"
- "Help me plan the variant matrix for [component]"
- "Set up the Figma properties for a [button/card/input]"
- "What are all the combinations I need for my [component]?"
+76
View File
@@ -0,0 +1,76 @@
---
name: financial-due-diligence
description: "Generate a financial due diligence checklist and analysis framework for any investment, acquisition, or partnership. Use when asked for a due diligence checklist, M&A financial review, investment analysis framework, or vendor financial assessment."
---
# Financial Due Diligence Skill
Produces a structured financial due diligence framework — document request list and analytical questions — for any investment, acquisition, or significant commercial relationship.
## Required Inputs
- **Transaction type** (acquisition / investment / partnership / supplier / fundraise)
- **Stage of diligence** (initial screening / full DD / confirmatory)
- **Target company type** (startup / SME / listed / subsidiary)
- **Key concerns** (optional — e.g. revenue recognition, customer concentration)
## Output Structure
### 1. Document Request List
**Financial Statements**
- Audited accounts for last 3 years
- Management accounts for current year (monthly)
- Board-approved budget and latest reforecast
- 3-year financial model with assumptions
**Revenue**
- Revenue by customer (top 20, % of total)
- Revenue by product/segment
- Contracted vs recurring vs one-off breakdown
- Churn and renewal data
**Costs**
- Cost of sales breakdown
- Headcount by department with compensation detail
- Top 10 supplier contracts
**Cash and Debt**
- Bank statements (12 months)
- Debt schedule with covenants and maturity
- Working capital analysis
**Tax**
- Last 3 years tax returns
- Any open enquiries
- R&D tax credit claims
### 2. Key Analytical Questions
**Revenue quality:** Is revenue growing organically? What % is truly recurring? Customer concentration risk?
**Margin analysis:** Gross margin trend over 3 years? One-off items inflating EBITDA? Normalised EBITDA?
**Cash conversion:** Does profit convert to cash? Cash conversion cycle? Working capital red flags?
**Debt and liabilities:** Net debt position? Contingent liabilities? Covenant headroom?
### 3. Red Flags Checklist
- Revenue concentration over 30% in one customer
- Declining gross margins without explanation
- EBITDA-to-cash conversion below 70%
- Auditor qualifications or emphasis of matter
- Related party transactions not at arm length
- Aggressive revenue recognition
- Growing debtor days with no explanation
### 4. Summary Output Template
- Revenue quality: [Assessment]
- Margin sustainability: [Assessment]
- Cash generation: [Assessment]
- Balance sheet risk: [Assessment]
- Overall: Green Strong / Amber Acceptable / Red Material concerns
## Example Trigger Phrases
- "Give me a financial due diligence checklist for [company type]"
- "What documents should I request for financial DD?"
- "Build a DD framework for our Series A investment"
+62
View File
@@ -0,0 +1,62 @@
---
name: financial-model-narrative
description: "Turn financial model outputs into a clear written narrative. Use when asked to write a financial narrative, explain a financial model, summarise a P&L, or translate spreadsheet numbers into a board-ready story. Produces an executive narrative with key insights, drivers, and forward-looking commentary."
---
# Financial Model Narrative Skill
Turns financial model outputs into a clear, structured written narrative suitable for board packs, investor updates, or management reporting.
## Required Inputs
- **Financial data** (paste key figures: revenue, costs, margins, EBITDA, cash)
- **Period covered** (month / quarter / annual / multi-year)
- **Audience** (board / investors / management / bank / internal)
- **Key message** (what is the headline story?)
- **Actuals vs budget / prior period?** (comparison context)
## Output Structure
### 1. Headline Summary
3-5 sentences. The financial story in plain English. Lead with the most important insight — not "revenue was X" but what that figure means.
### 2. Revenue
- Performance vs prior period / budget
- Key drivers: what caused the movement
- Risks or opportunities in the revenue line
### 3. Costs and Margins
- Gross margin: % and trend
- Key cost movements and why
- EBITDA performance and drivers
- One-off items clearly flagged
### 4. Cash and Balance Sheet
- Cash position and movement
- Runway (for startups)
- Key working capital movements
### 5. Variance Analysis
For each significant variance:
**[Line item] — Over/Under by [amount]**
- **Cause:** [Plain English explanation]
- **Permanent or temporary?** One-time / Structural
- **Action being taken:** [If applicable]
### 6. Forward-Looking Commentary
- Expected next period
- Key risks to forecast
- Key opportunities
- Any reforecast or guidance change
## Writing Rules
- Never just restate a number — always explain what it means
- Flag variances over 10% automatically
- Use past tense for actuals, conditional for forecast
- One insight per paragraph
## Example Trigger Phrases
- "Write a financial narrative for these results: [paste numbers]"
- "Turn this P&L into a board narrative"
- "Write the finance section of our board pack"
- "Explain these financial results in plain English"
+99
View File
@@ -0,0 +1,99 @@
---
name: grant-proposal
description: "Write a structured grant proposal or funding application for any grant type. Use when asked to write a grant proposal, funding application, research grant, charitable grant, or innovation fund application. Produces a complete proposal with project summary, rationale, methodology, impact, and budget narrative."
---
# Grant Proposal Skill
Produces structured grant proposals tailored to the funder priorities — the most common reason grants fail is writing about what you want to do rather than what the funder wants to fund.
## Required Inputs
- **Funder name and grant programme**
- **Grant amount sought**
- **Project description** (rough notes are fine)
- **Your organisation** (type, track record, capacity)
- **Funder stated priorities** (copy from their guidance — essential)
- **Word or page limits**
- **Deadline**
## Output Structure
---
### Project Title
[Informative and memorable. Should convey the problem being solved and the approach.]
### 1. Project Summary / Abstract (200-300 words — written last, placed first)
[What you will do, why it matters, who will benefit, measurable outcomes. Every sentence earns its place.]
### 2. Problem Statement / Need
- **The problem:** [Specific, evidenced — use data]
- **Who is affected:** [Population, scale, geography]
- **Current situation:** [What exists and why it is insufficient]
- **Consequence of inaction:** [What happens if not funded]
- **Why your organisation:** [Track record, relationships, expertise]
Funder test: does this problem align with [funder] stated priorities? Make the connection explicit.
### 3. Project Objectives
3-5 SMART objectives:
- **Objective 1:** [Specific, Measurable, Achievable, Relevant, Time-bound]
### 4. Methodology / Approach
**Phase 1: [Name]** (Months 1-X)
[What will happen, who will do it, what is produced]
**Key activities:**
- [Activity — specific]
**What makes this approach innovative or effective:** [Why this over alternatives]
### 5. Impact and Outcomes
| Level | Description | Measure |
|---|---|---|
| Output | [Tangible deliverable] | [How counted] |
| Short-term outcome | [Immediate change] | [How measured] |
| Medium-term outcome | [Behaviour change] | [How measured] |
| Long-term impact | [Systemic change] | [How evidenced] |
**Direct beneficiaries:** [Who and how many]
**Sustainability:** [How work continues beyond grant period]
### 6. Evaluation Plan
- Who evaluates, how, when, what is measured, how findings are shared
### 7. Budget Narrative
| Budget line | Amount | Justification |
|---|---|---|
| Staff costs | £[amount] | [Role, % FTE, duration, salary] |
| Travel | £[amount] | [Specific journeys named] |
| Equipment | £[amount] | [Itemised] |
| Indirect costs | £[amount] | [[X]% of direct — check policy] |
| **Total** | **£[total]** | |
**Value for money:** [Cost per beneficiary. What could not be done without this grant]
### 8. Organisational Capacity
[Track record of similar projects, governance, financial management. Name previous grants and outputs — be specific]
### 9. Risk Register
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| [Risk] | H/M/L | H/M/L | [Specific mitigation] |
---
## Funder Alignment Check
- Every section explicitly references funder stated priorities
- Word limits respected
- Budget aligns with eligible costs policy
- Required attachments prepared
## Example Trigger Phrases
- "Write a grant proposal for [project] applying to [funder]"
- "Help me write a funding application for [grant programme]"
- "Turn these project notes into a grant proposal: [paste]"
+48
View File
@@ -0,0 +1,48 @@
---
name: investor-pitch-deck
description: "Build the narrative and slide structure for an investor pitch deck. Use when asked to create a pitch deck, investor presentation, fundraising deck, or startup pitch. Produces a slide-by-slide structure with narrative beats, key messages, and what each slide must prove to an investor."
---
# Investor Pitch Deck Skill
Builds the complete narrative and slide structure for an investor pitch deck — focused on what investors need to see, not what founders want to show.
## Required Inputs
- **Company name and one-line description**
- **Stage** (Pre-seed / Seed / Series A / Series B)
- **Ask** (how much raising and what for)
- **Key metrics** (revenue, growth, users, retention)
- **Target investors** (generalist / sector-specific / angels)
- **Deck length** (10 / 12 / 15 slides)
## Output Structure
For each slide:
- **What this slide must prove** (the investor question it answers)
- **Content guidance** (specific, not generic)
- **Common mistake to avoid**
---
**Slide 1: Cover** — Proves you can say what you do in one sentence.
**Slide 2: Problem** — Proves the problem is real, painful, and large. Lead with the human problem, not market size.
**Slide 3: Solution** — Proves your solution is meaningfully better. Focus on outcome, not features.
**Slide 4: Product** — Proves this is real and works. Show the actual product.
**Slide 5: Traction** — Proves people want this. Show retention and revenue, not signups.
**Slide 6: Market** — Proves the market is large enough. Use bottoms-up TAM where possible.
**Slide 7: Business Model** — Proves you understand unit economics. Include CAC and LTV.
**Slide 8: Go-To-Market** — Proves you can acquire customers efficiently. Focus on what is actually working.
**Slide 9: Competition** — Proves you understand the landscape. Never say "no competitors."
**Slide 10: Team** — Proves this team can execute this opportunity. One sentence per person, specific.
**Slide 11: Financials** — Proves you understand your business. Show assumptions, not just projections.
**Slide 12: The Ask** — Proves you know exactly what you need. Specific use of funds and 18-month milestones.
## Narrative Principles
- Every slide answers one investor question
- Investors decide go/no-go on slides 1-5 — front-load evidence
- Keep to 10-12 slides for a first meeting
## Example Trigger Phrases
- "Build a pitch deck structure for [company]"
- "Help me structure my Series A deck"
- "What slides should my investor pitch have?"
+74
View File
@@ -0,0 +1,74 @@
---
name: job-description-writer
description: "Write a clear, inclusive, and structured job description for any role. Use when asked to write a job description, job posting, JD, or job advert. Produces a complete JD with role summary, responsibilities, requirements, and inclusive language review."
---
# Job Description Writer Skill
Writes complete, inclusive job descriptions that attract the right candidates and reduce bias in the hiring process.
## Required Inputs
- **Job title and level**
- **Team and reporting line**
- **Top 5 things this person will actually do**
- **Must-have requirements** (be ruthless — only what is truly required)
- **Nice-to-have requirements**
- **Salary range** (JDs with salary ranges get 30% more applicants)
- **Location and remote policy**
- **Company description** (2-3 sentences)
## Output Structure
### [Job Title]
**[Company] | [Location] | [Remote policy] | [Salary range]**
**About [Company]**
[2-3 sentences. Specific and honest — not marketing copy.]
**The Role**
[3-4 sentences. What this person will own, why the role exists now, what success looks like in year one.]
**What You Will Do**
[6-8 bullet points. Outcomes and responsibilities, not activities. Start each with an action verb. Most important first.]
**What We Are Looking For**
Must have (4-6 items only):
- [Requirement]
Nice to have (3-4 items):
- [Nice to have]
**What We Offer**
[Compensation, benefits, development. Be specific.]
**How to Apply**
[Clear instructions. What to send, where, timeline.]
---
### Inclusive Language Review
**Words to remove or replace:**
| Original | Replace with | Why |
|---|---|---|
| "rockstar" | "experienced" | Gendered connotation |
| "ninja" | "skilled" | Same issue |
| "must have degree" | "relevant experience or qualification" | Excludes qualified non-graduates |
**Requirement audit:**
- Years of experience requirements flagged (screen out women and underrepresented groups disproportionately)
- Any requirements potentially discriminating against protected characteristics
## Quality Checks
- Salary range included
- Must-haves genuinely essential (6 items max)
- Each responsibility starts with action verb
- Inclusive language review completed
- No years-of-experience requirements unless legally required
## Example Trigger Phrases
- "Write a job description for a [role]"
- "Create an inclusive job posting for [role]"
- "Review and rewrite this JD: [paste]"
+63
View File
@@ -0,0 +1,63 @@
---
name: legal-brief
description: "Draft a structured legal brief, case summary, or legal argument outline. Use when asked to write a legal brief, case note, legal memo, argument outline, or position paper. Produces a structured document using IRAC format (Issue, Rule, Application, Conclusion)."
---
# Legal Brief Skill
This skill drafts structured legal briefs and memos using IRAC format — the standard structure for legal writing.
## Required Inputs
- **Brief type** (legal memo / case summary / argument outline / position paper / letter before action)
- **Legal issue or question**
- **Jurisdiction** (England & Wales / US / EU / Other)
- **Relevant facts**
- **Relevant law or cases** (if known — otherwise flagged as [RESEARCH NEEDED])
- **Audience** (internal memo / court submission / client letter)
## Output Structure
### Header
- **To:** [Recipient]
- **From:** [Author]
- **Date:** [Date]
- **Re:** [Matter reference]
- **Confidential:** Subject to legal professional privilege
### Issue(s)
One sentence per legal question:
- Issue 1: Whether X constitutes Y under [law]
### Brief Answer
One sentence per issue — conclusion upfront before analysis.
### Facts
Concise relevant facts only. Flag disputed facts.
### Law (Rule)
- Relevant statute, regulation, or case law
- How the rule has been interpreted in key cases
- Flag [RESEARCH NEEDED] where law is not provided
### Application
- Arguments in favour
- Counter-arguments and responses
- Areas of uncertainty flagged explicitly
### Conclusion
- Clear answer to each issue
- Overall recommendation
- Suggested next steps
### Caveats
What this memo does not cover. What additional research would change the analysis.
---
WARNING: This draft requires review by a qualified legal professional. It does not constitute legal advice.
## Example Trigger Phrases
- "Draft a legal memo on [issue]"
- "Write a legal brief arguing [position]"
- "Summarise the legal position on [topic]"
- "Write a letter before action for [situation]"
+71
View File
@@ -0,0 +1,71 @@
---
name: literature-review
description: "Structure and write a literature review for any research topic. Use when asked to write a literature review, systematic review summary, narrative review, or research background section. Produces a structured review with thematic organisation, critical analysis, and gap identification."
---
# Literature Review Skill
Structures and writes literature reviews — from background sections of a dissertation through to standalone narrative reviews for publication.
## Required Inputs
- **Topic or research question**
- **Type of review** (narrative / systematic / scoping / integrative / background section)
- **Sources provided** (paste references, abstracts, or key findings)
- **Word count target**
- **Audience** (academic journal / thesis / grant proposal / policy brief)
- **Time period to cover**
## Output Structure
### 1. Search Strategy Summary (for systematic/scoping reviews)
**Databases:** [PubMed, EMBASE, PsycINFO, etc.]
**Search terms:** [Key terms and Boolean combinations]
**Inclusion criteria:** Study types, population, date range, language
**Exclusion criteria:** [List]
**Results:** [n] identified → [n] after deduplication → [n] screened → [n] included
### 2. Literature Review Body
Organised thematically — not chronologically. Each theme = one section.
**Structure per thematic section:**
**[Theme heading]**
[Opening: state what this section covers and what evidence shows overall]
[Evidence synthesis: present what multiple studies found, compare and contrast. Do NOT summarise one paper then the next — synthesise across them: "Three studies found X (Smith, 2019; Jones, 2020; Lee, 2021), while two found Y, with the difference attributable to..."]
[Critical analysis: note methodological strengths and weaknesses — sample sizes, study designs, generalisability, risk of bias]
[Closing: transition to next theme]
### 3. Synthesis Table (systematic/scoping reviews)
| Author, year | Study design | Population | n | Key findings | Quality/Limitations |
|---|---|---|---|---|---|
### 4. Gap Analysis
**Well-established:** [What literature consistently shows]
**Contested:** [Areas where evidence is mixed and why]
**Missing:** [Gaps the field needs to address]
**How your study addresses the gap:** [If this is for a research proposal]
### 5. Conclusion Paragraph
[3-5 sentences. Current state of knowledge and what is needed next]
## Critical Analysis Framework
For each paper: internal validity, external validity, bias types, effect size significance vs clinical significance, funding conflicts.
## Quality Checks
- Organised thematically not as paper summaries
- Evidence synthesised across papers
- Critical analysis included
- Gaps identified
- All claims cited
## Example Trigger Phrases
- "Write a literature review on [topic]"
- "Synthesise the evidence on [topic] from these papers: [paste]"
- "Write the background section for my research proposal on [topic]"
+59
View File
@@ -0,0 +1,59 @@
---
name: nda-analyser
description: "Analyse a Non-Disclosure Agreement (NDA) and flag key terms, unusual provisions, and negotiation points. Use when asked to review an NDA, mutual NDA, confidentiality agreement, or non-disclosure deed. Produces clause-by-clause analysis with risk flags and a negotiation checklist."
---
# NDA Analyser Skill
NDAs are often treated as routine paperwork but contain terms with significant long-term consequences. This skill analyses them systematically.
## Required Inputs
- **NDA text** (paste in full or describe key clauses)
- **Your party position** (disclosing / receiving / mutual)
- **Purpose of the NDA** (e.g. pre-sales, hiring, M&A, partnership)
- **Industry context** (optional)
## Output Structure
### 1. NDA Type and Parties
- **Type:** Unilateral / Mutual
- **Disclosing party:** [Name]
- **Receiving party:** [Name]
- **Purpose:** [As stated]
- **Governing law:** [Jurisdiction]
- **Term:** [Duration of obligations]
### 2. Definition of Confidential Information
- **How broadly defined?** Narrow / Standard / Very broad
- **Oral disclosures included?** Yes / No / With conditions
- **Standard exclusions present?** [public domain, prior knowledge, independently developed, legally required disclosure]
- **Flag:** [Unusual inclusions or missing exclusions]
### 3. Key Clause Analysis
**[Clause name] — Concern / Watch / Standard**
- **What it says:** [Plain English]
- **Issue:** [Why flagged]
- **Standard position:** [What this typically looks like]
- **Negotiation suggestion:** [If applicable]
Clauses always covered: permitted use, non-solicitation/non-compete, term and post-termination obligations, return/destruction of information, remedies, liability, residuals clause.
### 4. Negotiation Checklist
| Point | Current position | Suggested ask |
|---|---|---|
| [e.g. Confidentiality term] | [e.g. 5 years] | [e.g. Reduce to 2 years] |
### 5. Plain English Verdict
2-3 sentences. Standard NDA, one-sided, or needs a lawyer?
---
WARNING: This analysis is for informational purposes only and is not legal advice. Consult a qualified solicitor before signing.
## Example Trigger Phrases
- "Analyse this NDA"
- "Review this confidentiality agreement"
- "Is this NDA standard or unusual?"
- "What should I negotiate in this mutual NDA?"
+89
View File
@@ -0,0 +1,89 @@
---
name: onboarding-plan
description: "Create a structured 30/60/90-day onboarding plan for any new hire. Use when asked to write an onboarding plan, new hire plan, 30-60-90 day plan, or first 90 days roadmap. Produces a week-by-week plan with milestones, meetings, learning goals, and success criteria."
---
# Onboarding Plan Skill
Creates a complete, structured onboarding plan tailored to a specific role — covering the first 90 days with clear milestones and success criteria.
## Required Inputs
- **Role and level** of the new hire
- **Team and manager**
- **Key stakeholders** they will work with
- **Top 3 priorities** for their first 90 days
- **Tools and systems** they will need access to
- **Company stage** (startup / scaleup / enterprise)
## Output Structure
### Onboarding Plan: [Name] — [Role]
**Start date:** [Date] | **Manager:** [Name] | **Buddy:** [Name]
---
### Before Day 1 (Manager checklist)
- IT setup: laptop, accounts, email, Slack, key tools
- Access provisioned to key systems
- First week calendar blocked with key meetings
- Buddy assigned and briefed
- Welcome message sent with Day 1 logistics
---
### Week 1: Orient
Theme: Listen, learn, do not act yet.
| Day | Focus | Key activities |
|---|---|---|
| Day 1 | IT setup, team intro | 1:1 with manager, team lunch |
| Day 2 | Product deep dive | Demo, key docs to read |
| Day 3 | Process and tools | Shadow key workflows |
| Day 4 | Stakeholder intros | 3-4 intro 1:1s |
| Day 5 | Week 1 debrief | Check-in, questions logged |
**Week 1 milestone:** Can describe what the company does, the team role, and their top 3 priorities.
---
### Days 8-30: Learn
Learning goals:
- Deep understanding of product from customer perspective
- Know key metrics the team is measured on
- Understand current projects and status
- Map key stakeholder relationships
- Complete all compliance/HR training
**30-day milestone:** All stakeholder 1:1s complete. 2-3 early observations shared with manager.
---
### Days 31-60: Contribute
Goals:
- Own at least one project end-to-end
- Make one meaningful contribution
- Build cross-functional relationships
- Identify one process improvement
**60-day milestone:** Delivered one tangible output. Manager says "this person is contributing."
---
### Days 61-90: Lead
Goals:
- Operating independently on core responsibilities
- Has formed and shared a point of view on priorities
- Building reputation with key stakeholders
**90-day milestone:** Ready for formal review. Clear 6-month plan in place.
---
### 90-Day Review Questions
Manager: Meeting expectations? What to double down on? What to develop?
New hire: Have the clarity, tools, support needed? What surprised you? What would you change about onboarding?
## Example Trigger Phrases
- "Create a 30/60/90 day plan for a new [role]"
- "Write an onboarding plan for [name] starting as [role]"
- "Build a first 90 days roadmap for our new hire"
+89
View File
@@ -0,0 +1,89 @@
---
name: patient-communication
description: "Write clear, plain English patient communications for any healthcare context. Use when asked to write a patient letter, patient information leaflet, appointment letter, test results letter, discharge summary for patients, or health education content. Targets accessible reading level with clear next steps."
---
# Patient Communication Skill
Writes patient-facing healthcare communications in plain, accessible language — targeting UK Grade 6 / US Grade 8 reading level.
WARNING: All patient communications must be reviewed and approved by a qualified healthcare professional before sending. This skill produces drafts only.
## Required Inputs
- **Communication type** (appointment letter / results letter / discharge info / patient leaflet / consent info / health education)
- **Clinical context**
- **Key messages** (what the patient must understand and do)
- **Tone** (reassuring / informative / urgent)
- **Specific instructions or next steps**
- **Contact details for queries**
## Output Structure
### Type A: Patient Letter
[Date]
Dear [Patient name],
**Re: [Clear subject line in bold]**
[Opening paragraph: State clearly what this letter is about. No preamble.]
[Main content — short paragraphs, 2-3 sentences each. Bullet points for instructions. Bold anything the patient must do or remember.]
**What happens next:**
- [Action 1 — specific with timeframe]
- [Action 2]
**If you have questions:**
Contact us at [phone] between [hours] or email [address].
If you feel unwell before your appointment, please [specific instruction].
Yours sincerely, [Name, Title, Department]
---
### Type B: Patient Information Leaflet
**[Plain language title]**
**What is [topic]?** [2-3 plain English sentences. Explain technical terms immediately.]
**Why has this been recommended for me?** [Personalised clinical reason in patient terms]
**What will happen?** [Numbered step by step]
**What are the benefits?** [Honest statement]
**What are the risks?** [Common first, then rare but serious. Use frequencies: "About 1 in 10 people..." not "10% incidence"]
**What should I do to prepare?** [Specific instructions]
**When should I contact someone?** [Specific signs — not vague. "Temperature above 38C" not "if you feel unwell"]
---
### Type C: Test Results Letter
**Your [test name] results — [Normal / Abnormal] — stated in the FIRST sentence, never paragraph 3.**
[What this means in plain English]
**What happens next:** [Clear next steps. If no action, say so explicitly.]
---
## Plain Language Rules (apply to all types)
- Maximum 2 syllables per word where possible
- Maximum 20 words per sentence
- Active voice: "We will contact you" not "You will be contacted"
- Spell out all acronyms on first use
- No Latin: "twice daily" not "bd"
- Use "you" and "we" throughout
- Numbers as digits: "2 tablets" not "two tablets"
## Example Trigger Phrases
- "Write a patient letter about [topic]"
- "Create a patient information leaflet for [procedure]"
- "Write a plain English results letter for [test]"
+71
View File
@@ -0,0 +1,71 @@
---
name: press-release
description: "Write a professional press release for any announcement. Use when asked to write a press release, media announcement, news release, or press statement. Produces a structured press release with headline, dateline, body, boilerplate, and media contact — ready to send to journalists."
---
# Press Release Skill
Writes press releases that journalists actually read — structured around the news angle, not the desire to promote.
## Required Inputs
- **The news** (what is actually happening — be specific)
- **Company name**
- **Date of announcement / embargo date**
- **Key quote** (from which executive and approximately what they want to say)
- **Why this matters** (to the reader, not the company)
- **Target media** (trade / national / local / consumer / investor)
- **Media contact details**
## Output Structure
---
FOR IMMEDIATE RELEASE / EMBARGOED UNTIL: [Date and time]
---
# [Headline — active verb, specific news, under 10 words]
## [Subheadline — the so-what in one sentence, adds context not repetition]
**[City, Date]** — [Opening paragraph: Who, What, When, Where, Why in 2-3 sentences. A journalist should be able to run this paragraph alone. No background, no context, no company history.]
[Second paragraph: the significance. Why does this matter? What does it mean for customers or the industry?]
[Third paragraph: quote from executive. Human and specific. Not a restatement of the headline.]
"[Quote text — specific, adds something the facts do not say]," said [Name], [Title] at [Company]. "[Second sentence extending the thought]."
[Fourth paragraph: supporting detail — data, customer names with permission, additional context]
[Fifth paragraph optional: what happens next, when it goes live, what people can do]
---
ENDS
---
**Notes to editors:**
**About [Company]**
[Boilerplate: 3-4 sentences. What the company does, when founded, where based, key facts. Factual not promotional.]
**Media contact:**
[Name] | [Title] | [Email] | [Phone] | [Hours/timezone]
---
## Headline Rules
- Active voice: "Company launches X" not "X is launched by Company"
- Specific: "raises 5M" not "secures significant investment"
- Under 10 words
- Never start with the company name — lead with the news
## Journalist Test
Would a journalist care? Is the headline the full story? Is there a human angle? Is the quote something a human would say? Can the first paragraph stand alone?
## Example Trigger Phrases
- "Write a press release announcing [news]"
- "Draft a media statement about [event]"
- "We are launching [product] — write the press release"
- "Turn this announcement into a press release: [paste notes]"
+81
View File
@@ -0,0 +1,81 @@
---
name: process-documentation
description: "Document any business process in a clear, structured format. Use when asked to document a process, write a process guide, create a workflow document, or map out how something works. Produces a complete process document with steps, roles, inputs, outputs, and edge cases."
---
# Process Documentation Skill
Produces clear, structured process documentation that someone new to a role can follow without needing to ask questions.
## Required Inputs
- **Process name**
- **Process description** (rough notes are fine)
- **Who does this process** (roles involved)
- **How often it runs** (daily / weekly / monthly / event-triggered)
- **Tools involved**
- **Known edge cases**
## Output Structure
---
# Process: [Process Name]
**Owner:** [Role] | **Frequency:** [How often] | **Estimated time:** [Duration]
---
### Purpose
[1-2 sentences. Why does this process exist? What breaks if it is not done?]
### Scope
**In scope:** [What this covers]
**Out of scope:** [What it does not cover]
### Prerequisites
- [ ] [Required access or information]
- [ ] [Any dependency that must be completed first]
---
### Roles and Responsibilities
| Role | Responsibility |
|---|---|
| [Role 1] | [What they do] |
---
### Process Steps
**Step 1: [Step name]**
- **Who:** [Role]
- **When:** [Trigger or timing]
- **How:** [Substeps numbered]
- **Output:** [What exists at end of this step]
- **Tool:** [System used]
[Continue for all steps]
---
### Edge Cases and Exceptions
| Situation | What to do | Who to contact |
|---|---|---|
| [Edge case] | [Action] | [Name/role] |
---
### Common Mistakes
[2-4 things people get wrong the first time]
### Escalation Path
[Name/role] → [Next level] → [Final escalation]
### Review
Next review due: [Date]
## Example Trigger Phrases
- "Document this process: [description]"
- "Write a process guide for [workflow]"
- "Map out how [process] works"
+109
View File
@@ -0,0 +1,109 @@
---
name: project-status-report
description: "Write a structured project status report for any project. Use when asked to write a project update, status report, RAG report, project dashboard narrative, or weekly project communication. Produces a clear status report with RAG ratings, milestone progress, risks, and decisions needed."
---
# Project Status Report Skill
Produces a clear, structured project status report — the weekly communication that keeps stakeholders informed without requiring a meeting.
## Required Inputs
- **Project name**
- **Reporting period**
- **Current RAG status** (Red / Amber / Green)
- **Key milestones** (due, delivered, coming)
- **Issues or blockers**
- **Decisions needed from stakeholders**
- **Budget status** (if tracked)
- **Audience** (steering committee / sponsor / PMO / full team)
## Output Structure
---
# Project Status Report: [Project Name]
**Period:** [Date range] | **Author:** [PM] | **Next report:** [Date]
---
### Overall Status
| Dimension | Status | Last period | Trend |
|---|---|---|---|
| Overall | Red / Amber / Green | [Last] | Improving / Stable / Declining |
| Schedule | | | |
| Budget | | | |
| Scope | | | |
| Risks | | | |
RAG definitions:
- Green: On track. No significant issues.
- Amber: At risk. Issues identified but mitigations in place.
- Red: Off track. Escalation or decisions required to recover.
---
### Executive Summary
[3-5 sentences. Headline story. If it is Red, say so immediately and why. Never bury bad news after good news.]
---
### Milestone Progress
| Milestone | Due date | Status | Comment |
|---|---|---|---|
| [Milestone] | [Date] | Complete / At risk / Delayed / On track | [One line] |
**Completed this period:** [What was delivered]
**Due next period:** [What is expected]
---
### Issues and Blockers
**[Issue title] — Critical / High / Low**
- **Description:** [What the issue is]
- **Impact:** [What happens if unresolved]
- **Owner:** [Who is resolving]
- **Action:** [What is being done]
- **Resolution date:** [When it will be closed]
---
### Risks
| Risk | Likelihood | Impact | Mitigation | Owner |
|---|---|---|---|---|
| [Risk] | H/M/L | H/M/L | [Action] | [Name] |
---
### Decisions Required
| Decision | Background | Options | Recommendation | Needed by |
|---|---|---|---|---|
| [Decision] | [Context] | [Options] | [Recommendation] | [Date] |
---
### Budget Summary
| | Budget | Actual to date | Forecast | Variance |
|---|---|---|---|---|
| Total | £ | £ | £ | £ F/A |
---
### Next Period Plan
[3-5 specific bullet points — what will happen next period]
## Writing Rules
- Never soften a Red status
- Milestones are binary: complete or not complete
- Decisions must be genuinely actionable
- Keep to one page where possible
## Example Trigger Phrases
- "Write a project status report for [project]"
- "Generate a RAG status update for [project]"
- "Write the steering committee report for [project]"
+92
View File
@@ -0,0 +1,92 @@
---
name: proposal-writer
description: "Write a structured sales proposal or commercial proposal for any deal. Use when asked to write a proposal, sales proposal, commercial proposal, statement of work, or quote document. Produces a complete proposal with problem statement, solution, investment, and next steps."
---
# Proposal Writer Skill
Writes commercial proposals that win business — structured around the prospect problem, not the product.
## Required Inputs
- **Prospect company and contact**
- **Their problem or goal** (from discovery — be specific)
- **Your proposed solution**
- **Commercial terms** (pricing, payment terms, contract length)
- **Timeline**
- **Key stakeholders** who will read this
- **Tone** (formal / conversational / technical)
## Output Structure
---
# Proposal: [Brief description of what you are solving]
**Prepared for:** [Contact, Title] | [Company]
**Prepared by:** [Name] | [Your Company]
**Date:** [Date] | **Valid until:** [Date]
---
### Understanding Your Situation
[2-3 paragraphs. Demonstrate you listened. Describe their situation, problem, and impact of not solving it in their words. This section should make them think "yes, exactly." Generic boilerplate here = proposal goes in the bin.]
**The key challenge:** [One sentence — the core problem]
**The impact:** [What this costs them]
**What you have tried:** [Acknowledge prior attempts]
---
### Our Proposed Approach
**What we will do** (3-5 deliverables or phases)
**Phase 1: [Name]** (Timeline: [Weeks 1-2])
[What happens, what is delivered, what customer input is needed]
**Phase 2: [Name]** (Timeline: [Weeks 3-6])
**What you will get** (outcomes, not features)
- [Outcome 1]
- [Outcome 2]
**What success looks like**
[How both parties know this worked]
---
### Why [Your Company]
[3-4 sentences. Specific to their situation. Reference similar customers. Generic "why us" sections are skipped.]
---
### Investment
| Item | Description | Investment |
|---|---|---|
| [Component 1] | [Description] | £[amount] |
| **Total** | | **£[total]** |
**Payment terms:** [Terms]
**Included:** [What is in]
**Not included:** [What is out — prevents scope disputes]
---
### Timeline
| Milestone | Date |
|---|---|
| Contract signed | [Date] |
| Kickoff | [Date] |
| Delivery | [Date] |
---
### Next Steps
1. [Sign / reply / schedule] by [date]
2. We will send contract and confirm kickoff
3. [Any immediate action]
## Example Trigger Phrases
- "Write a proposal for [prospect] to [solve their problem]"
- "Draft a statement of work for [project]"
- "Turn my discovery notes into a proposal"
+68
View File
@@ -0,0 +1,68 @@
---
name: redundancy-consultation
description: "Structure a redundancy consultation process and draft key communications. Use when asked to plan a redundancy process, write a redundancy letter, structure a consultation, or manage a reduction in force. UK employment law focus. Always recommend qualified HR/legal advice before proceeding."
---
# Redundancy Consultation Skill
Structures redundancy processes and drafts communications. Significant legal and human risk — always flag that employment legal advice is essential before proceeding.
WARNING: Defaults to UK employment law (Employment Rights Act 1996). Always recommend qualified HR/legal advice before any redundancy action.
## Required Inputs
- **Number of roles affected** (1-19 = individual; 20+ = collective consultation required)
- **Reason for redundancy** (genuine business reason)
- **Jurisdiction** (UK / US / EU / Other)
- **Timeline constraints**
- **Selection pool** (if multiple people in similar roles)
## Output Structure
### 1. Process Overview
**Individual redundancy (fewer than 20):**
| Stage | Action | Minimum timeline |
|---|---|---|
| 1 | Confirm business case internally | Before any communication |
| 2 | At-risk notification meeting | Day 1 |
| 3 | Individual consultation | Minimum 1 meaningful meeting |
| 4 | Redundancy confirmed or alternative found | After genuine consideration |
| 5 | Notice period begins | Per contract |
| 6 | Final day and payment | Per contract + statutory |
**Collective redundancy (20+ roles — UK):**
- Minimum 45 days consultation before first dismissal
- Must notify BEIS (HR1 form) before consultation begins
- Employee representatives must be elected if no union recognised
- Failure = unlimited protective award per employee
### 2. Selection Criteria (if pool exists)
Objective, non-discriminatory only: skills/qualifications, performance (documented evidence), attendance (exclude disability/pregnancy-related absences), length of service (tiebreaker only).
NEVER select on: age, disability, pregnancy/maternity, part-time status, trade union membership.
### 3. At-Risk Letter Draft
"Dear [Name], I am writing to inform you that your role of [Job Title] is at risk of redundancy. This is because [specific business reason]. We would like to meet on [date] to discuss the situation and explore alternatives. You have the right to be accompanied by a colleague or trade union representative. No decision has been made. Yours sincerely, [Manager]"
### 4. Consultation Meeting Script
Opening: "No decision has been made. This meeting is to explain the situation and listen to your views."
Key questions: Any ways to avoid this? Alternative roles of interest? Anything about selection to challenge?
### 5. Redundancy Confirmation Letter Draft
Issued only after genuine consultation. Must include: statutory pay calculated, notice period, payment for accrued holiday, right of appeal.
### 6. Statutory Redundancy Pay Guide (UK)
- Under 22: 0.5 week per year of service
- 22-40: 1 week per year of service
- 41+: 1.5 weeks per year of service
- Weekly pay capped (verify current rate)
- Maximum 20 years counts
---
WARNING: Take advice from an employment lawyer or qualified HR professional before beginning any redundancy process.
## Example Trigger Phrases
- "Help me structure a redundancy consultation"
- "Draft an at-risk letter for [role]"
- "What is the process for making someone redundant in the UK?"
+97
View File
@@ -0,0 +1,97 @@
---
name: research-protocol
description: "Write a structured research protocol or study design document. Use when asked to write a research protocol, study protocol, research plan, methodology section, or research proposal. Produces a complete protocol with objectives, methodology, ethical considerations, and analysis plan."
---
# Research Protocol Skill
Produces structured research protocols for academic, clinical, social science, or market research studies.
## Required Inputs
- **Research type** (clinical trial / observational / qualitative / systematic review / survey)
- **Research question or hypothesis**
- **Setting and population**
- **Proposed methodology**
- **Timeline**
- **Funder or institution** (if applicable)
## Output Structure
---
# Research Protocol: [Study Title]
**Version:** 1.0 | **Date:** [Date] | **PI:** [Name, institution]
---
### 1. Background and Rationale
- What is already known
- What the gap in knowledge is
- Why this study is needed now
### 2. Research Objectives
**Primary:** [One clear answerable question or hypothesis]
**Secondary:** [Additional questions]
### 3. Study Design
- **Design:** [RCT / cohort / qualitative / mixed methods]
- **Setting:** [Where]
- **Duration:** [Total period and recruitment window]
- **Rationale:** [Why this design fits the question]
### 4. Participants
**Inclusion criteria:** [List]
**Exclusion criteria:** [List]
**Sample size:** [n] — Basis: [Power calculation or saturation rationale]
**Recruitment:** [Method and source]
### 5. Methodology / Intervention
For interventional: intervention description, control, randomisation, blinding
For observational/qualitative: data collection methods, tools, data collectors
### 6. Outcomes / Measures
**Primary outcome:** [Measure], assessed by [method], at [timepoint]
**Secondary outcomes:** [Measure], [method], [timepoint]
### 7. Data Management
- Storage: [Where and anonymisation method]
- Access controls: [Who can access]
- Retention: [How long]
### 8. Analysis Plan
Quantitative: [Statistical test], [missing data handling], [software]
Qualitative: [Framework — e.g. Braun & Clarke], [quality assurance]
### 9. Ethical Considerations
- Ethics approval: [Body / reference]
- Informed consent: [Process]
- Confidentiality: [How maintained]
- Risk to participants: [Assessment and mitigation]
### 10. Dissemination Plan
- Target journals: [2-3 relevant]
- Conference presentations
- Public/patient summary
### 11. Timeline
| Phase | Activities | Start | End |
|---|---|---|---|
| Setup | Ethics, approvals, tool development | | |
| Recruitment | | | |
| Data collection | | | |
| Analysis | | | |
| Write-up | | | |
## Quality Checks
- Primary objective is singular and answerable
- Sample size has stated basis
- Ethical considerations complete
- Analysis plan pre-specified
## Example Trigger Phrases
- "Write a research protocol for [study]"
- "Help me design a study to investigate [question]"
- "Write the methodology for my research proposal"
+79
View File
@@ -0,0 +1,79 @@
---
name: sales-battlecard
description: "Create a competitive sales battlecard for any competitor. Use when asked to build a battlecard, competitive comparison, sales cheat sheet, or objection handling guide for a specific competitor. Produces a one-page battlecard with positioning, differentiators, objection responses, and landmines."
---
# Sales Battlecard Skill
Produces a practical one-page competitive battlecard that sales reps can use in calls — not a theoretical analysis.
## Required Inputs
- **Your product/company**
- **Competitor name**
- **Your target customer** (ICP)
- **Your top 3 differentiators** vs this competitor
- **Common objections** when competing against them
- **Known competitor weaknesses**
## Output Structure
---
# Battlecard: [Your Product] vs [Competitor]
Updated: [Date] — Review quarterly
---
### In One Sentence
When a prospect mentions [Competitor], say: "[Your positioning in one sentence]"
---
### Why Customers Choose [Competitor]
(Be honest about their genuine strengths)
- [Strength 1]
- [Strength 2]
---
### Why Customers Choose Us
(Specific differentiators with proof points)
- **[Differentiator 1]:** [Proof point — customer outcome or capability]
- **[Differentiator 2]:** [Proof point]
---
### Objection Responses
**"[Competitor] is cheaper"**
"You are right their list price is lower. What our customers find is [specific TCO difference]. [Customer] saw [result]. Should we explore total cost of ownership?"
**"We already use [Competitor]"**
"That is helpful. What is working well? [Listen] And what is one thing you wish was better?"
**"[Competitor] has [feature] you do not"**
"You are right. What problem are you solving with that feature? [Listen] Here is how our customers solve that..."
---
### Landmines to Plant
- "How do you currently handle [area where competitor is weak]?"
- "What happens when you need to [scenario competitor struggles with]?"
---
### Traps to Avoid
- Never badmouth [Competitor] directly
- Do not lead with features — lead with the prospect problem
- Do not claim you do everything better — be specific about where you win
---
### When We Win / When We Lose
We win when: [Scenario — e.g. customer prioritises outcome over price]
We lose when: [Honest scenario — e.g. primary driver is lowest upfront cost]
## Example Trigger Phrases
- "Build a battlecard against [competitor]"
- "Create a competitive cheat sheet for [competitor]"
- "Write objection handling for [competitor] comparisons"
+93
View File
@@ -0,0 +1,93 @@
---
name: sop-writer
description: "Write a Standard Operating Procedure (SOP) for any operational task. Use when asked to write an SOP, standard operating procedure, work instruction, or operating manual. Produces a formal SOP with purpose, scope, procedure steps, quality checks, and version control."
---
# SOP Writer Skill
Produces formal, audit-ready SOPs suitable for regulated industries, ISO certification, or operational scaling.
## Required Inputs
- **SOP title** (e.g. "SOP-001: New Client Onboarding")
- **Department / function**
- **Process description**
- **Regulatory or quality standard** (ISO 9001, GMP, CQC, FCA, etc.)
- **Roles involved**
- **Tools or equipment used**
## Output Structure
---
**[COMPANY NAME] — Standard Operating Procedure**
| Document ID | [SOP-XXX] |
|---|---|
| Title | [Title] |
| Department | [Department] |
| Version | 1.0 |
| Effective date | [Date] |
| Review date | [Date] |
| Status | Draft / Under review / Approved |
---
### 1. Purpose
[1-2 sentences. Why does this SOP exist?]
### 2. Scope
**Applies to:** [Roles, departments, locations]
**Does not apply to:** [Explicit exclusions]
### 3. Definitions
| Term | Definition |
|---|---|
| [Term] | [Plain English definition] |
### 4. Responsibilities
| Role | Responsibility |
|---|---|
| [Role] | [Specific responsibility] |
### 5. Required Materials / Tools / Access
- [Item]
### 6. Procedure
| Step | Action | Responsible | Record/Output |
|---|---|---|---|
| 6.1.1 | [Imperative action: "Open [system] and navigate to [location]"] | [Role] | [What to record] |
NOTE: Steps must be written in imperative form. Each step must have one action only.
### 7. Quality Checks
| Check point | What to verify | Pass criteria | If fail |
|---|---|---|---|
| [After step X] | [What to check] | [What good looks like] | [What to do] |
### 8. Non-Conformance
1. [Immediate action]
2. [Who to notify]
3. [How to document deviation]
### 9. References
[Related SOPs, policies, standards]
### 10. Document History
| Version | Date | Author | Changes |
|---|---|---|---|
| 1.0 | [Date] | [Name] | Initial release |
## Quality Checks
- All steps in imperative form
- Each step has exactly one action
- Roles specified for every step
- Quality checkpoints at critical stages
- Non-conformance process defined
## Example Trigger Phrases
- "Write an SOP for [process]"
- "Create a standard operating procedure for [task]"
- "Write a work instruction for [process]"

Some files were not shown because too many files have changed in this diff Show More