Merge pull request #14 from mohitagw15856/claude/add-engineering-skills-IfBhz
quality: improve 10 v7.0.0-era engineering skills
This commit is contained in:
mohitagw15856
GitHub
@@ -13,10 +13,12 @@ Ask the user for these if not provided:
|
||||
- **API or endpoint details** (raw spec, Postman export, or verbal description)
|
||||
- **Auth method** (API key / Bearer token / OAuth 2.0 / None)
|
||||
- **Base URL**
|
||||
- **API version** (e.g. v1, v2.3, or "unversioned" — affects deprecation notes and versioning headers)
|
||||
- **Rate limits** (requests per second/minute per token or IP, if known — or "unknown")
|
||||
- **Audience** (internal developers / external partners / public)
|
||||
- **Output format** (Markdown / OpenAPI YAML / Plain prose)
|
||||
- **Output format** (Markdown for developer portals and READMEs / Plain prose for Confluence or Notion — note: OpenAPI YAML is not produced by this skill)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
For each endpoint, produce the following:
|
||||
|
||||
@@ -133,13 +135,13 @@ data = response.json()
|
||||
- [ ] Every parameter is documented (type, required/optional, description)
|
||||
- [ ] Response fields are fully documented with types
|
||||
- [ ] All relevant error codes are listed with resolution guidance
|
||||
- [ ] Code examples are copy-paste runnable (no pseudocode)
|
||||
- [ ] Error codes cover at minimum: 400 (bad request), 401/403 (auth), 404 (not found), 429 (rate limited), 500 (server error) — or explicitly note which don't apply to this endpoint
|
||||
- [ ] Code examples use the actual base URL and a realistic placeholder token — no examples reference undefined variables or "YOUR_ENDPOINT" outside the snippet
|
||||
- [ ] Auth method is clearly stated at the top
|
||||
- [ ] Enum values are listed where applicable
|
||||
- [ ] Pagination documented if the endpoint is a list endpoint
|
||||
|
||||
## Example Trigger Phrases
|
||||
|
||||
## Usage Examples
|
||||
- "Document this API endpoint: [paste spec or description]"
|
||||
- "Turn this Postman collection into developer docs"
|
||||
- "Write API reference docs for [endpoint]"
|
||||
|
||||
@@ -10,6 +10,7 @@ This skill produces a complete Architecture Decision Record (ADR) following the
|
||||
## Required Inputs
|
||||
|
||||
Ask the user for these if not provided:
|
||||
- **ADR number** (sequential number in your ADR registry — e.g. 012; or "next available" if unknown)
|
||||
- **Decision title** (brief, e.g. "Use PostgreSQL as primary datastore")
|
||||
- **Context** (what situation led to this decision needing to be made?)
|
||||
- **Options considered** (at least 2; if only 1 is given, prompt for alternatives that were considered or ruled out)
|
||||
@@ -17,8 +18,9 @@ Ask the user for these if not provided:
|
||||
- **Reason for choice**
|
||||
- **Status** (Proposed / Accepted / Deprecated / Superseded)
|
||||
- **Author and date**
|
||||
- **Team context** (optional — team size, relevant experience, org constraints; helps calibrate formality and depth of the Context section)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
|
||||
@@ -89,13 +91,13 @@ For each option, produce:
|
||||
|
||||
## Implementation Notes
|
||||
|
||||
[Optional but valuable: any specific patterns, gotchas, or guidance for the team implementing based on this decision. Link to relevant tickets, RFCs, or design docs if applicable.]
|
||||
[Include if the decision has non-obvious implementation gotchas, or if there are related tickets/RFCs implementers will need. Skip only if the decision is purely tooling selection with no implementation ambiguity.]
|
||||
|
||||
---
|
||||
|
||||
## Review Date
|
||||
|
||||
[Optional: "This decision should be reviewed if [condition] — e.g. team grows beyond 20 engineers, or traffic exceeds 10M requests/day."]
|
||||
[Include unless the decision is permanent or self-evidently final. State a specific trigger condition — e.g. "Review if team grows beyond 20 engineers or traffic exceeds 10M requests/day" — not just "should be reviewed periodically".]
|
||||
|
||||
---
|
||||
|
||||
@@ -107,10 +109,10 @@ For each option, produce:
|
||||
- [ ] Consequences include *negative* consequences — no decision is consequence-free
|
||||
- [ ] Decision is stated in plain language in the Decision section
|
||||
- [ ] Risks section identifies what would invalidate this decision
|
||||
- [ ] Written for someone with no prior context on this decision
|
||||
|
||||
## Example Trigger Phrases
|
||||
- [ ] Context section states the problem explicitly in its first 1–2 sentences (does not assume the reader knows what problem the team was solving)
|
||||
- [ ] Each rejected option's "Why ruled out" explanation names a specific constraint or trade-off (not a circular statement like "didn't meet our requirements")
|
||||
|
||||
## Usage Examples
|
||||
- "Write an ADR for using [technology]"
|
||||
- "Document our decision to [architectural choice]"
|
||||
- "Create an architecture decision record for [topic]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: changelog-generator
|
||||
description: "Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what changed in a version. Produces a structured changelog section with version header, categorised changes, and migration notes. Optimised for Opus 4.7 and newer models."
|
||||
description: "Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what changed in a version. Produces a structured changelog section with version header, categorised changes, and migration notes."
|
||||
---
|
||||
|
||||
# Changelog Generator Skill
|
||||
@@ -15,8 +15,10 @@ Ask for these if not provided:
|
||||
- **Release date** (or "today")
|
||||
- **Audience** (developers using an API / end users of a product / internal team — affects language)
|
||||
- **Any breaking changes** (flag these explicitly if known)
|
||||
- **Previous version behaviour** (optional — paste the previous changelog entry or describe what is changing; needed for accurate "Changed" entries)
|
||||
- **Scope** (whole product / specific package or module — e.g. "payments SDK only", "iOS app", "all services")
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
Follow [Keep a Changelog](https://keepachangelog.com) format:
|
||||
|
||||
@@ -52,6 +54,10 @@ Follow [Keep a Changelog](https://keepachangelog.com) format:
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
> **Skill guidance — do not include the following section in the delivered changelog:**
|
||||
|
||||
## Formatting Rules Applied
|
||||
|
||||
**Language:** Write for the reader, not the committer. "Add dark mode support" not "implement ThemeProvider with dark palette variant".
|
||||
@@ -72,9 +78,10 @@ Follow [Keep a Changelog](https://keepachangelog.com) format:
|
||||
- [ ] Related commits are grouped into single entries (not listed individually)
|
||||
- [ ] Version and date header is correct
|
||||
- [ ] Empty sections are omitted
|
||||
- [ ] Tone is imperative mood throughout
|
||||
- [ ] No entries start with past-tense verbs (no "Added", "Fixed", "Removed" — use "Add", "Fix", "Remove")
|
||||
- [ ] Every breaking change entry includes a specific migration action (not just "update your code")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a changelog for version [X]" + [paste commits]
|
||||
- "Generate release notes from these commits"
|
||||
- "Turn this git log into a CHANGELOG entry"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: code-review-checklist
|
||||
description: "Generate a tailored code review checklist for any pull request based on the language, type of change, and risk level. Use when asked to review code, check a PR, review a pull request, or generate a code review checklist. Produces a focused checklist with language-specific checks, risk-level-appropriate depth, and a clear approve/request-changes recommendation. Optimised for Opus 4.7 and newer models."
|
||||
description: "Generate a tailored code review checklist for any pull request based on the language, type of change, and risk level. Use when asked to review code, check a PR, review a pull request, or generate a code review checklist. Produces a focused checklist with language-specific checks, risk-level-appropriate depth, and a clear approve/request-changes recommendation."
|
||||
---
|
||||
|
||||
# Code Review Checklist Skill
|
||||
@@ -14,15 +14,19 @@ Ask the user for these if not provided:
|
||||
- **Type of change** (feature / bug fix / refactor / dependency upgrade / security patch / performance)
|
||||
- **Risk level** (low / medium / high / critical)
|
||||
- **PR description** (paste the description or link to the PR)
|
||||
- **Code or diff** (optional — paste key changed files or a `git diff`; significantly improves checklist specificity)
|
||||
- **Author context** (new starter / experienced / external contributor)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### 1. Review Summary
|
||||
**PR:** [Title or reference]
|
||||
---
|
||||
|
||||
# Code Review: [PR Title or Reference]
|
||||
|
||||
### 1. PR Overview
|
||||
**Scope assessment:** [Small / Medium / Large / Too large — should be split]
|
||||
**Recommended review depth:** [Skim / Standard / Deep dive]
|
||||
**Estimated review time:** [Minutes]
|
||||
**Estimated review time:** [e.g. 20–30 min — use 5 min per 50 lines of diff as a rough guide]
|
||||
|
||||
### 2. Correctness Checks
|
||||
|
||||
@@ -94,14 +98,17 @@ Language-specific correctness checks — choose based on the language stated:
|
||||
### 7. Common Pitfalls for This Change Type
|
||||
Based on the change type and language, flag 2-3 things reviewers typically miss for this combination.
|
||||
|
||||
---
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Checklist is tailored to the stated language (not generic)
|
||||
- [ ] Change-type-specific section is included
|
||||
- [ ] Risk-appropriate depth matches stated risk level
|
||||
- [ ] Decision framework is explicit
|
||||
- [ ] Decision framework includes at least one named blocking condition and one named non-blocking comment condition
|
||||
- [ ] Common pitfalls are specific to the stated language + change-type combo (not generic advice like "watch out for bugs")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Generate a code review checklist for [PR description]"
|
||||
- "What should I check in this pull request?"
|
||||
- "Give me a code review checklist for a [language] [change type]"
|
||||
- "Review checklist for a high-risk PR in [language]"
|
||||
- "Review checklist for a high-risk PR in [language]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: debugging-log-analyser
|
||||
description: "Parse error logs, stack traces, and crash reports into a structured root cause diagnosis. Use when sharing a log, stack trace, error output, or crash dump. Produces a structured diagnosis with probable root cause, affected code path, suggested fix, and next debugging steps. Optimised for Opus 4.7 and newer models."
|
||||
description: "Parse error logs, stack traces, and crash reports into a structured root cause diagnosis. Use when sharing a log, stack trace, error output, or crash dump. Produces a structured diagnosis with probable root cause, affected code path, suggested fix, and next debugging steps."
|
||||
---
|
||||
|
||||
# Debugging Log Analyser Skill
|
||||
@@ -12,14 +12,19 @@ Parses raw error logs, stack traces, and crash reports into a structured diagnos
|
||||
Ask for these if not provided:
|
||||
- **The log / stack trace / error output** (paste directly or describe the error)
|
||||
- **Language and framework** (e.g. Node.js + Express, Python + Django, Java Spring, Go)
|
||||
- **Context** (what the user was doing when the error occurred)
|
||||
- **Context** (what changed before this started — e.g. recent deploy, config change, increased traffic, new input data; or "nothing changed" is also useful)
|
||||
- **Frequency** (one-off / intermittent / consistent / regression after a specific change)
|
||||
- **Environment** (local dev / staging / production)
|
||||
- **What they've already tried** (if anything)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
|
||||
# Debugging Report: [Service/App Name]
|
||||
|
||||
### 1. Error Classification
|
||||
**Error type:** [Runtime exception / Build error / Config error / Network error / Memory/resource error / Unknown]
|
||||
**Error type:** [Runtime exception / Build error / Config error / Network error / Memory error / Unknown]
|
||||
**Severity:** [Fatal / Critical / Warning / Informational]
|
||||
**Recurrence pattern:** [One-off / Intermittent / Consistent / On-startup / Under load]
|
||||
|
||||
@@ -64,14 +69,17 @@ One or two concrete things that would prevent this class of error recurring:
|
||||
- Add monitoring/alerting for [condition]
|
||||
- Test that covers [scenario]
|
||||
|
||||
---
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Root cause is specific (not "there might be a null pointer issue")
|
||||
- [ ] At least one concrete code-level fix is suggested
|
||||
- [ ] Next steps are actionable commands, not vague advice
|
||||
- [ ] Language-specific idioms are used correctly
|
||||
- [ ] Suggested fix references the actual language/framework in the input (not a generic fix that could apply to any language)
|
||||
- [ ] Confidence level includes a stated reason (not just "High" or "Low" with no explanation)
|
||||
- [ ] Prevention is proactive (not just "add error handling")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Why is this crashing?" + [paste log]
|
||||
- "Can you analyse this stack trace?"
|
||||
- "I'm getting this error, what does it mean?"
|
||||
|
||||
@@ -5,7 +5,7 @@ description: "Write a structured incident postmortem or post-incident review. Us
|
||||
|
||||
# Incident Postmortem Skill
|
||||
|
||||
This skill produces a complete, blameless incident postmortem document following industry-standard format. Output is ready to share with engineering teams, leadership, and affected stakeholders.
|
||||
This skill produces a complete, blameless incident postmortem document following industry-standard format. Output enforces blameless framing throughout — system gaps over individual failures — and drives toward specific, closeable action items rather than vague process commitments.
|
||||
|
||||
## Required Inputs
|
||||
|
||||
@@ -20,8 +20,10 @@ Ask the user for these if not provided:
|
||||
- **How it was resolved**
|
||||
- **Initial thoughts on root cause**
|
||||
- **Action items already identified** (optional)
|
||||
- **Responders** (who was on-call or responded — names or roles; used for the timeline, not for blame)
|
||||
- **Customer or external communications sent** (optional — any status page updates, emails, or support messages with timestamps)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
|
||||
@@ -131,13 +133,14 @@ Rules for action items:
|
||||
|
||||
- [ ] Timeline has no blame-focused language
|
||||
- [ ] Root cause is specific (not "human error")
|
||||
- [ ] Root cause answers "why did this happen?" not just "what happened?" — it names a system or process gap, not a symptom
|
||||
- [ ] Contributing factors explain the systemic gaps
|
||||
- [ ] Every action item has an owner and due date
|
||||
- [ ] "What went well" section is genuine, not token
|
||||
- [ ] No action item contains vague language like "improve monitoring", "increase resilience", or "better testing" — each must name a specific change
|
||||
- [ ] Executive summary is readable by non-technical leadership
|
||||
|
||||
## Example Trigger Phrases
|
||||
|
||||
## Usage Examples
|
||||
- "Write a postmortem for the [incident name] outage"
|
||||
- "Help me write a P1 incident report"
|
||||
- "Generate an RCA document for [service] going down on [date]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: pr-description-writer
|
||||
description: "Write a clear, structured pull request description from a git diff, branch summary, or commit list. Use when asked to write a PR description, draft a pull request, or document code changes. Produces a description with summary, motivation, changes made, testing steps, and reviewer guidance. Optimised for Opus 4.7 and newer models."
|
||||
description: "Write a clear, structured pull request description from a git diff, branch summary, or commit list. Use when asked to write a PR description, draft a pull request, or document code changes. Produces a description with summary, motivation, changes made, testing steps, and reviewer guidance."
|
||||
---
|
||||
|
||||
# PR Description Writer Skill
|
||||
@@ -15,8 +15,10 @@ Ask for these if not provided:
|
||||
- **How to test it** (any specific steps a reviewer needs to verify it works)
|
||||
- **Risk level** (low / medium / high — affects how much reviewer guidance to include)
|
||||
- **PR type** (feature / bug fix / refactor / dependency upgrade / config change / hotfix)
|
||||
- **Target branch** (e.g. main / develop / release/2.4 — affects risk framing and reviewer guidance)
|
||||
- **Linked issue or ticket** (e.g. JIRA-1234, GitHub #567 — or "none")
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### Title
|
||||
A clear, imperative-mood title under 72 characters:
|
||||
@@ -43,7 +45,7 @@ Bullet list of specific changes — one bullet per logical change, not per file:
|
||||
### Screenshots / Demo
|
||||
[If UI change: include before/after screenshots or a screen recording]
|
||||
[If API change: include example request/response]
|
||||
[If no visual change: this section can be omitted]
|
||||
[If no visual change and no API contract change: omit this section entirely — do not leave it as a placeholder]
|
||||
|
||||
### How to Test
|
||||
Step-by-step instructions a reviewer can follow:
|
||||
@@ -76,10 +78,11 @@ Flag anything that warrants extra attention:
|
||||
- [ ] Title is imperative mood and under 72 characters
|
||||
- [ ] Summary explains what AND why (not just what)
|
||||
- [ ] Changes list describes logical changes (not file-by-file changes)
|
||||
- [ ] Title starts with a valid type prefix (feat / fix / refactor / chore / deps / config / hotfix) and is under 72 characters
|
||||
- [ ] Testing steps are reproducible by someone unfamiliar with the code
|
||||
- [ ] Risk-appropriate reviewer guidance is included
|
||||
- [ ] For high-risk PRs, Reviewer Notes flags at least one specific area of concern or deliberate trade-off; for low-risk PRs, Reviewer Notes is either omitted or kept to one line
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a PR description for these changes" + [paste diff or description]
|
||||
- "Draft a pull request for [feature]"
|
||||
- "I need a PR description — here's what I changed"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: runbook-writer
|
||||
description: "Write an operational runbook for a service, incident type, or deployment procedure. Use when asked to write a runbook, create an ops guide, document an operational procedure, or prepare an incident response playbook. Produces a runbook with overview, prerequisites, step-by-step procedures, rollback steps, troubleshooting table, and escalation paths. Optimised for Opus 4.7 and newer models."
|
||||
description: "Write an operational runbook for a service, incident type, or deployment procedure. Use when asked to write a runbook, create an ops guide, document an operational procedure, or prepare an incident response playbook. Produces a runbook with overview, prerequisites, step-by-step procedures, rollback steps, troubleshooting table, and escalation paths."
|
||||
---
|
||||
|
||||
# Runbook Writer Skill
|
||||
@@ -15,14 +15,16 @@ Ask for these if not provided:
|
||||
- **System/service name and what it does** (brief description)
|
||||
- **Audience** (new on-call engineers / experienced SREs / DevOps team)
|
||||
- **Tech stack** (where relevant — e.g. Kubernetes, AWS RDS, Node.js)
|
||||
- **Monitoring tools** (e.g. Grafana, Datadog, CloudWatch, Splunk — used to name specific dashboards and alert links in the steps)
|
||||
- **Key environment details** (e.g. Kubernetes cluster name, AWS account/region, relevant namespaces or resource names — paste what's relevant for exact commands)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
**Runbook:** [Runbook Title]
|
||||
**Service:** [Service Name]
|
||||
**Type:** [Deployment / Incident Response / Maintenance / DR]
|
||||
**Last Updated:** [Date]
|
||||
**Last Updated:** [Insert today's date in YYYY-MM-DD format]
|
||||
**Owner:** [Team or person]
|
||||
**Severity:** [P1 / P2 / P3 — if incident-type]
|
||||
|
||||
@@ -133,10 +135,11 @@ After completing the runbook:
|
||||
- [ ] Expected output is specified for each step so engineer knows if it worked
|
||||
- [ ] Failure path is explicit for each step (not "if it fails, investigate")
|
||||
- [ ] Rollback procedure is complete and independently testable
|
||||
- [ ] Escalation paths name specific contacts, not just team names
|
||||
- [ ] Escalation table has no cells containing only "[Team name]" — every row must either have a real contact or be explicitly flagged as [FILL IN: on-call rotation link]
|
||||
- [ ] Rollback section contains at least one concrete command (not left as "[rollback command]" placeholder)
|
||||
- [ ] Runbook can be followed by someone who has never touched this system
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a runbook for [service] deployment"
|
||||
- "Create an incident response runbook for [alert type]"
|
||||
- "I need a runbook for [procedure]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: system-design-interview
|
||||
description: "Structure a complete system design answer for interview questions or real architecture sessions. Use when asked to design a system, answer a system design interview question, or architect a solution at scale. Produces a structured answer covering requirements, capacity estimates, high-level design, component deep-dives, trade-offs, and follow-up considerations. Optimised for Opus 4.7 and newer models."
|
||||
description: "Structure a complete system design answer for interview questions or real architecture sessions. Use when asked to design a system, answer a system design interview question, or architect a solution at scale. Produces a structured answer covering requirements, capacity estimates, high-level design, component deep-dives, trade-offs, and follow-up considerations."
|
||||
---
|
||||
|
||||
# System Design Interview Skill
|
||||
@@ -14,8 +14,10 @@ Ask for these if not provided:
|
||||
- **Scope** (interview prep / real architecture decision / practice run)
|
||||
- **Scale target** (rough numbers: DAU, requests/sec, data volume — or "assume typical web scale")
|
||||
- **Constraints or priorities** (e.g. prioritise availability over consistency, minimise cost, low-latency reads)
|
||||
- **Time available** (interview context only: 30 / 45 / 60 minutes — skip for real architecture sessions)
|
||||
- **Emphasis** (optional — any area to go deeper on, e.g. "focus on the DB design" or "spend more time on scaling")
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### 1. Clarifying Questions
|
||||
Before designing, list 4–6 questions that would change the design. Examples:
|
||||
@@ -62,12 +64,7 @@ Then proceed with stated assumptions if answering an interview question.
|
||||
|
||||
### 5. High-Level Architecture
|
||||
|
||||
```
|
||||
[Client] → [CDN/Edge] → [Load Balancer] → [API Servers] → [Cache] → [DB]
|
||||
→ [Message Queue] → [Workers]
|
||||
```
|
||||
|
||||
Describe each layer in 1–2 sentences explaining its role and technology choice.
|
||||
Draw an ASCII diagram specific to this system. Do not default to the client→CDN→LB→API→Cache→DB template unless it genuinely applies. Label each component with the specific technology chosen (e.g. "Kafka" not "Message Queue", "PostgreSQL" not "DB"). Describe each component in 1–2 sentences explaining its role and why that technology was chosen.
|
||||
|
||||
### 6. Component Deep-Dive
|
||||
|
||||
@@ -122,12 +119,13 @@ Things to tackle in production but out of scope for this design session:
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Clarifying questions are design-changing (not generic filler)
|
||||
- [ ] Capacity estimates use real numbers (not just "it scales")
|
||||
- [ ] Capacity estimates show the arithmetic: DAU → requests/day → requests/sec → storage per record → total storage, so the numbers can be sanity-checked
|
||||
- [ ] Every row in the Trade-offs table has a non-empty Trade-off column (no rows where the trade-off is blank or says "none")
|
||||
- [ ] At least 2 component deep-dives with technology choices justified
|
||||
- [ ] Trade-offs section is honest (not just benefits of chosen approach)
|
||||
- [ ] Data flow is described end-to-end for the critical path
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Help me answer a system design interview: [question]"
|
||||
- "Design [system] for a system design interview"
|
||||
- "How would I architect [system] at scale?"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: test-strategy-doc
|
||||
description: "Write a test strategy document from a feature spec, PRD, or system description. Use when asked to create a test plan, write a test strategy, define QA approach, or plan testing for a feature or release. Produces a complete test strategy with scope, risk assessment, test types, coverage targets, and a prioritised test case outline. Optimised for Opus 4.7 and newer models."
|
||||
description: "Write a test strategy document from a feature spec, PRD, or system description. Use when asked to create a test plan, write a test strategy, define QA approach, or plan testing for a feature or release. Produces a complete test strategy with scope, risk assessment, test types, coverage targets, and a prioritised test case outline."
|
||||
---
|
||||
|
||||
# Test Strategy Document Skill
|
||||
@@ -11,12 +11,14 @@ Produces a complete test strategy from a feature spec, PRD, or system descriptio
|
||||
|
||||
Ask for these if not provided:
|
||||
- **Feature or system being tested** (paste a spec, PRD, or describe it in plain English)
|
||||
- **Tech stack** (language, framework, testing tools already in use if known)
|
||||
- **Tech stack** (language and framework — e.g. TypeScript + React, Python + FastAPI)
|
||||
- **Existing test coverage** (e.g. "we have unit tests but no E2E tests", "we use Jest + Playwright already", or "starting from scratch")
|
||||
- **Deployment cadence** (e.g. continuous deployment / weekly releases / quarterly — affects what must be automated vs. manual)
|
||||
- **Risk level** (low / medium / high / critical — affects depth and coverage requirements)
|
||||
- **Timeline** (when does this need to ship — affects prioritisation)
|
||||
- **Team context** (who is doing the testing — developers / dedicated QA / both)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### 1. Test Scope
|
||||
|
||||
@@ -66,7 +68,7 @@ Identify the highest-risk areas first — these drive depth and coverage:
|
||||
- **Tools:** [e.g. Playwright, Cypress, Selenium]
|
||||
- **Focus areas:** [The 3–5 most critical user flows]
|
||||
|
||||
**Performance Tests** *(include only if risk is medium+)*
|
||||
**Performance Tests** *(include if any row in the Risk Assessment table has performance as a risk factor, regardless of overall risk level)*
|
||||
- **What:** Load, stress, or latency testing
|
||||
- **Targets:** [Specific numbers — e.g. 200 req/sec at p95 < 200ms]
|
||||
- **Tools:** [e.g. k6, Locust, JMeter]
|
||||
@@ -115,11 +117,12 @@ Testing is complete when:
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Risk table is populated and drives test priority (not filled in generically)
|
||||
- [ ] P0 test cases cover the highest-risk paths specifically
|
||||
- [ ] Every "P0 — exhaustive" row in the Risk Assessment table has at least one corresponding P0 test case
|
||||
- [ ] "Out of scope" section names at least one explicit exclusion (not left blank)
|
||||
- [ ] Each test type names a concrete tool (not "some testing framework")
|
||||
- [ ] Definition of Done is measurable (not "tests are done when QA is happy")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a test strategy for [feature]" + [paste spec or PRD]
|
||||
- "Create a test plan for [system]"
|
||||
- "How should we test [feature]?"
|
||||
|
||||
@@ -13,10 +13,12 @@ Ask the user for these if not provided:
|
||||
- **API or endpoint details** (raw spec, Postman export, or verbal description)
|
||||
- **Auth method** (API key / Bearer token / OAuth 2.0 / None)
|
||||
- **Base URL**
|
||||
- **API version** (e.g. v1, v2.3, or "unversioned" — affects deprecation notes and versioning headers)
|
||||
- **Rate limits** (requests per second/minute per token or IP, if known — or "unknown")
|
||||
- **Audience** (internal developers / external partners / public)
|
||||
- **Output format** (Markdown / OpenAPI YAML / Plain prose)
|
||||
- **Output format** (Markdown for developer portals and READMEs / Plain prose for Confluence or Notion — note: OpenAPI YAML is not produced by this skill)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
For each endpoint, produce the following:
|
||||
|
||||
@@ -133,13 +135,13 @@ data = response.json()
|
||||
- [ ] Every parameter is documented (type, required/optional, description)
|
||||
- [ ] Response fields are fully documented with types
|
||||
- [ ] All relevant error codes are listed with resolution guidance
|
||||
- [ ] Code examples are copy-paste runnable (no pseudocode)
|
||||
- [ ] Error codes cover at minimum: 400 (bad request), 401/403 (auth), 404 (not found), 429 (rate limited), 500 (server error) — or explicitly note which don't apply to this endpoint
|
||||
- [ ] Code examples use the actual base URL and a realistic placeholder token — no examples reference undefined variables or "YOUR_ENDPOINT" outside the snippet
|
||||
- [ ] Auth method is clearly stated at the top
|
||||
- [ ] Enum values are listed where applicable
|
||||
- [ ] Pagination documented if the endpoint is a list endpoint
|
||||
|
||||
## Example Trigger Phrases
|
||||
|
||||
## Usage Examples
|
||||
- "Document this API endpoint: [paste spec or description]"
|
||||
- "Turn this Postman collection into developer docs"
|
||||
- "Write API reference docs for [endpoint]"
|
||||
|
||||
@@ -10,6 +10,7 @@ This skill produces a complete Architecture Decision Record (ADR) following the
|
||||
## Required Inputs
|
||||
|
||||
Ask the user for these if not provided:
|
||||
- **ADR number** (sequential number in your ADR registry — e.g. 012; or "next available" if unknown)
|
||||
- **Decision title** (brief, e.g. "Use PostgreSQL as primary datastore")
|
||||
- **Context** (what situation led to this decision needing to be made?)
|
||||
- **Options considered** (at least 2; if only 1 is given, prompt for alternatives that were considered or ruled out)
|
||||
@@ -17,8 +18,9 @@ Ask the user for these if not provided:
|
||||
- **Reason for choice**
|
||||
- **Status** (Proposed / Accepted / Deprecated / Superseded)
|
||||
- **Author and date**
|
||||
- **Team context** (optional — team size, relevant experience, org constraints; helps calibrate formality and depth of the Context section)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
|
||||
@@ -89,13 +91,13 @@ For each option, produce:
|
||||
|
||||
## Implementation Notes
|
||||
|
||||
[Optional but valuable: any specific patterns, gotchas, or guidance for the team implementing based on this decision. Link to relevant tickets, RFCs, or design docs if applicable.]
|
||||
[Include if the decision has non-obvious implementation gotchas, or if there are related tickets/RFCs implementers will need. Skip only if the decision is purely tooling selection with no implementation ambiguity.]
|
||||
|
||||
---
|
||||
|
||||
## Review Date
|
||||
|
||||
[Optional: "This decision should be reviewed if [condition] — e.g. team grows beyond 20 engineers, or traffic exceeds 10M requests/day."]
|
||||
[Include unless the decision is permanent or self-evidently final. State a specific trigger condition — e.g. "Review if team grows beyond 20 engineers or traffic exceeds 10M requests/day" — not just "should be reviewed periodically".]
|
||||
|
||||
---
|
||||
|
||||
@@ -107,10 +109,10 @@ For each option, produce:
|
||||
- [ ] Consequences include *negative* consequences — no decision is consequence-free
|
||||
- [ ] Decision is stated in plain language in the Decision section
|
||||
- [ ] Risks section identifies what would invalidate this decision
|
||||
- [ ] Written for someone with no prior context on this decision
|
||||
|
||||
## Example Trigger Phrases
|
||||
- [ ] Context section states the problem explicitly in its first 1–2 sentences (does not assume the reader knows what problem the team was solving)
|
||||
- [ ] Each rejected option's "Why ruled out" explanation names a specific constraint or trade-off (not a circular statement like "didn't meet our requirements")
|
||||
|
||||
## Usage Examples
|
||||
- "Write an ADR for using [technology]"
|
||||
- "Document our decision to [architectural choice]"
|
||||
- "Create an architecture decision record for [topic]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: changelog-generator
|
||||
description: "Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what changed in a version. Produces a structured changelog section with version header, categorised changes, and migration notes. Optimised for Opus 4.7 and newer models."
|
||||
description: "Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what changed in a version. Produces a structured changelog section with version header, categorised changes, and migration notes."
|
||||
---
|
||||
|
||||
# Changelog Generator Skill
|
||||
@@ -15,8 +15,10 @@ Ask for these if not provided:
|
||||
- **Release date** (or "today")
|
||||
- **Audience** (developers using an API / end users of a product / internal team — affects language)
|
||||
- **Any breaking changes** (flag these explicitly if known)
|
||||
- **Previous version behaviour** (optional — paste the previous changelog entry or describe what is changing; needed for accurate "Changed" entries)
|
||||
- **Scope** (whole product / specific package or module — e.g. "payments SDK only", "iOS app", "all services")
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
Follow [Keep a Changelog](https://keepachangelog.com) format:
|
||||
|
||||
@@ -52,6 +54,10 @@ Follow [Keep a Changelog](https://keepachangelog.com) format:
|
||||
|
||||
---
|
||||
|
||||
---
|
||||
|
||||
> **Skill guidance — do not include the following section in the delivered changelog:**
|
||||
|
||||
## Formatting Rules Applied
|
||||
|
||||
**Language:** Write for the reader, not the committer. "Add dark mode support" not "implement ThemeProvider with dark palette variant".
|
||||
@@ -72,9 +78,10 @@ Follow [Keep a Changelog](https://keepachangelog.com) format:
|
||||
- [ ] Related commits are grouped into single entries (not listed individually)
|
||||
- [ ] Version and date header is correct
|
||||
- [ ] Empty sections are omitted
|
||||
- [ ] Tone is imperative mood throughout
|
||||
- [ ] No entries start with past-tense verbs (no "Added", "Fixed", "Removed" — use "Add", "Fix", "Remove")
|
||||
- [ ] Every breaking change entry includes a specific migration action (not just "update your code")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a changelog for version [X]" + [paste commits]
|
||||
- "Generate release notes from these commits"
|
||||
- "Turn this git log into a CHANGELOG entry"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: code-review-checklist
|
||||
description: "Generate a tailored code review checklist for any pull request based on the language, type of change, and risk level. Use when asked to review code, check a PR, review a pull request, or generate a code review checklist. Produces a focused checklist with language-specific checks, risk-level-appropriate depth, and a clear approve/request-changes recommendation. Optimised for Opus 4.7 and newer models."
|
||||
description: "Generate a tailored code review checklist for any pull request based on the language, type of change, and risk level. Use when asked to review code, check a PR, review a pull request, or generate a code review checklist. Produces a focused checklist with language-specific checks, risk-level-appropriate depth, and a clear approve/request-changes recommendation."
|
||||
---
|
||||
|
||||
# Code Review Checklist Skill
|
||||
@@ -14,15 +14,19 @@ Ask the user for these if not provided:
|
||||
- **Type of change** (feature / bug fix / refactor / dependency upgrade / security patch / performance)
|
||||
- **Risk level** (low / medium / high / critical)
|
||||
- **PR description** (paste the description or link to the PR)
|
||||
- **Code or diff** (optional — paste key changed files or a `git diff`; significantly improves checklist specificity)
|
||||
- **Author context** (new starter / experienced / external contributor)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### 1. Review Summary
|
||||
**PR:** [Title or reference]
|
||||
---
|
||||
|
||||
# Code Review: [PR Title or Reference]
|
||||
|
||||
### 1. PR Overview
|
||||
**Scope assessment:** [Small / Medium / Large / Too large — should be split]
|
||||
**Recommended review depth:** [Skim / Standard / Deep dive]
|
||||
**Estimated review time:** [Minutes]
|
||||
**Estimated review time:** [e.g. 20–30 min — use 5 min per 50 lines of diff as a rough guide]
|
||||
|
||||
### 2. Correctness Checks
|
||||
|
||||
@@ -94,14 +98,17 @@ Language-specific correctness checks — choose based on the language stated:
|
||||
### 7. Common Pitfalls for This Change Type
|
||||
Based on the change type and language, flag 2-3 things reviewers typically miss for this combination.
|
||||
|
||||
---
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Checklist is tailored to the stated language (not generic)
|
||||
- [ ] Change-type-specific section is included
|
||||
- [ ] Risk-appropriate depth matches stated risk level
|
||||
- [ ] Decision framework is explicit
|
||||
- [ ] Decision framework includes at least one named blocking condition and one named non-blocking comment condition
|
||||
- [ ] Common pitfalls are specific to the stated language + change-type combo (not generic advice like "watch out for bugs")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Generate a code review checklist for [PR description]"
|
||||
- "What should I check in this pull request?"
|
||||
- "Give me a code review checklist for a [language] [change type]"
|
||||
- "Review checklist for a high-risk PR in [language]"
|
||||
- "Review checklist for a high-risk PR in [language]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: debugging-log-analyser
|
||||
description: "Parse error logs, stack traces, and crash reports into a structured root cause diagnosis. Use when sharing a log, stack trace, error output, or crash dump. Produces a structured diagnosis with probable root cause, affected code path, suggested fix, and next debugging steps. Optimised for Opus 4.7 and newer models."
|
||||
description: "Parse error logs, stack traces, and crash reports into a structured root cause diagnosis. Use when sharing a log, stack trace, error output, or crash dump. Produces a structured diagnosis with probable root cause, affected code path, suggested fix, and next debugging steps."
|
||||
---
|
||||
|
||||
# Debugging Log Analyser Skill
|
||||
@@ -12,14 +12,19 @@ Parses raw error logs, stack traces, and crash reports into a structured diagnos
|
||||
Ask for these if not provided:
|
||||
- **The log / stack trace / error output** (paste directly or describe the error)
|
||||
- **Language and framework** (e.g. Node.js + Express, Python + Django, Java Spring, Go)
|
||||
- **Context** (what the user was doing when the error occurred)
|
||||
- **Context** (what changed before this started — e.g. recent deploy, config change, increased traffic, new input data; or "nothing changed" is also useful)
|
||||
- **Frequency** (one-off / intermittent / consistent / regression after a specific change)
|
||||
- **Environment** (local dev / staging / production)
|
||||
- **What they've already tried** (if anything)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
|
||||
# Debugging Report: [Service/App Name]
|
||||
|
||||
### 1. Error Classification
|
||||
**Error type:** [Runtime exception / Build error / Config error / Network error / Memory/resource error / Unknown]
|
||||
**Error type:** [Runtime exception / Build error / Config error / Network error / Memory error / Unknown]
|
||||
**Severity:** [Fatal / Critical / Warning / Informational]
|
||||
**Recurrence pattern:** [One-off / Intermittent / Consistent / On-startup / Under load]
|
||||
|
||||
@@ -64,14 +69,17 @@ One or two concrete things that would prevent this class of error recurring:
|
||||
- Add monitoring/alerting for [condition]
|
||||
- Test that covers [scenario]
|
||||
|
||||
---
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Root cause is specific (not "there might be a null pointer issue")
|
||||
- [ ] At least one concrete code-level fix is suggested
|
||||
- [ ] Next steps are actionable commands, not vague advice
|
||||
- [ ] Language-specific idioms are used correctly
|
||||
- [ ] Suggested fix references the actual language/framework in the input (not a generic fix that could apply to any language)
|
||||
- [ ] Confidence level includes a stated reason (not just "High" or "Low" with no explanation)
|
||||
- [ ] Prevention is proactive (not just "add error handling")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Why is this crashing?" + [paste log]
|
||||
- "Can you analyse this stack trace?"
|
||||
- "I'm getting this error, what does it mean?"
|
||||
|
||||
@@ -5,7 +5,7 @@ description: "Write a structured incident postmortem or post-incident review. Us
|
||||
|
||||
# Incident Postmortem Skill
|
||||
|
||||
This skill produces a complete, blameless incident postmortem document following industry-standard format. Output is ready to share with engineering teams, leadership, and affected stakeholders.
|
||||
This skill produces a complete, blameless incident postmortem document following industry-standard format. Output enforces blameless framing throughout — system gaps over individual failures — and drives toward specific, closeable action items rather than vague process commitments.
|
||||
|
||||
## Required Inputs
|
||||
|
||||
@@ -20,8 +20,10 @@ Ask the user for these if not provided:
|
||||
- **How it was resolved**
|
||||
- **Initial thoughts on root cause**
|
||||
- **Action items already identified** (optional)
|
||||
- **Responders** (who was on-call or responded — names or roles; used for the timeline, not for blame)
|
||||
- **Customer or external communications sent** (optional — any status page updates, emails, or support messages with timestamps)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
|
||||
@@ -131,13 +133,14 @@ Rules for action items:
|
||||
|
||||
- [ ] Timeline has no blame-focused language
|
||||
- [ ] Root cause is specific (not "human error")
|
||||
- [ ] Root cause answers "why did this happen?" not just "what happened?" — it names a system or process gap, not a symptom
|
||||
- [ ] Contributing factors explain the systemic gaps
|
||||
- [ ] Every action item has an owner and due date
|
||||
- [ ] "What went well" section is genuine, not token
|
||||
- [ ] No action item contains vague language like "improve monitoring", "increase resilience", or "better testing" — each must name a specific change
|
||||
- [ ] Executive summary is readable by non-technical leadership
|
||||
|
||||
## Example Trigger Phrases
|
||||
|
||||
## Usage Examples
|
||||
- "Write a postmortem for the [incident name] outage"
|
||||
- "Help me write a P1 incident report"
|
||||
- "Generate an RCA document for [service] going down on [date]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: pr-description-writer
|
||||
description: "Write a clear, structured pull request description from a git diff, branch summary, or commit list. Use when asked to write a PR description, draft a pull request, or document code changes. Produces a description with summary, motivation, changes made, testing steps, and reviewer guidance. Optimised for Opus 4.7 and newer models."
|
||||
description: "Write a clear, structured pull request description from a git diff, branch summary, or commit list. Use when asked to write a PR description, draft a pull request, or document code changes. Produces a description with summary, motivation, changes made, testing steps, and reviewer guidance."
|
||||
---
|
||||
|
||||
# PR Description Writer Skill
|
||||
@@ -15,8 +15,10 @@ Ask for these if not provided:
|
||||
- **How to test it** (any specific steps a reviewer needs to verify it works)
|
||||
- **Risk level** (low / medium / high — affects how much reviewer guidance to include)
|
||||
- **PR type** (feature / bug fix / refactor / dependency upgrade / config change / hotfix)
|
||||
- **Target branch** (e.g. main / develop / release/2.4 — affects risk framing and reviewer guidance)
|
||||
- **Linked issue or ticket** (e.g. JIRA-1234, GitHub #567 — or "none")
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### Title
|
||||
A clear, imperative-mood title under 72 characters:
|
||||
@@ -43,7 +45,7 @@ Bullet list of specific changes — one bullet per logical change, not per file:
|
||||
### Screenshots / Demo
|
||||
[If UI change: include before/after screenshots or a screen recording]
|
||||
[If API change: include example request/response]
|
||||
[If no visual change: this section can be omitted]
|
||||
[If no visual change and no API contract change: omit this section entirely — do not leave it as a placeholder]
|
||||
|
||||
### How to Test
|
||||
Step-by-step instructions a reviewer can follow:
|
||||
@@ -76,10 +78,11 @@ Flag anything that warrants extra attention:
|
||||
- [ ] Title is imperative mood and under 72 characters
|
||||
- [ ] Summary explains what AND why (not just what)
|
||||
- [ ] Changes list describes logical changes (not file-by-file changes)
|
||||
- [ ] Title starts with a valid type prefix (feat / fix / refactor / chore / deps / config / hotfix) and is under 72 characters
|
||||
- [ ] Testing steps are reproducible by someone unfamiliar with the code
|
||||
- [ ] Risk-appropriate reviewer guidance is included
|
||||
- [ ] For high-risk PRs, Reviewer Notes flags at least one specific area of concern or deliberate trade-off; for low-risk PRs, Reviewer Notes is either omitted or kept to one line
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a PR description for these changes" + [paste diff or description]
|
||||
- "Draft a pull request for [feature]"
|
||||
- "I need a PR description — here's what I changed"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: runbook-writer
|
||||
description: "Write an operational runbook for a service, incident type, or deployment procedure. Use when asked to write a runbook, create an ops guide, document an operational procedure, or prepare an incident response playbook. Produces a runbook with overview, prerequisites, step-by-step procedures, rollback steps, troubleshooting table, and escalation paths. Optimised for Opus 4.7 and newer models."
|
||||
description: "Write an operational runbook for a service, incident type, or deployment procedure. Use when asked to write a runbook, create an ops guide, document an operational procedure, or prepare an incident response playbook. Produces a runbook with overview, prerequisites, step-by-step procedures, rollback steps, troubleshooting table, and escalation paths."
|
||||
---
|
||||
|
||||
# Runbook Writer Skill
|
||||
@@ -15,14 +15,16 @@ Ask for these if not provided:
|
||||
- **System/service name and what it does** (brief description)
|
||||
- **Audience** (new on-call engineers / experienced SREs / DevOps team)
|
||||
- **Tech stack** (where relevant — e.g. Kubernetes, AWS RDS, Node.js)
|
||||
- **Monitoring tools** (e.g. Grafana, Datadog, CloudWatch, Splunk — used to name specific dashboards and alert links in the steps)
|
||||
- **Key environment details** (e.g. Kubernetes cluster name, AWS account/region, relevant namespaces or resource names — paste what's relevant for exact commands)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
---
|
||||
**Runbook:** [Runbook Title]
|
||||
**Service:** [Service Name]
|
||||
**Type:** [Deployment / Incident Response / Maintenance / DR]
|
||||
**Last Updated:** [Date]
|
||||
**Last Updated:** [Insert today's date in YYYY-MM-DD format]
|
||||
**Owner:** [Team or person]
|
||||
**Severity:** [P1 / P2 / P3 — if incident-type]
|
||||
|
||||
@@ -133,10 +135,11 @@ After completing the runbook:
|
||||
- [ ] Expected output is specified for each step so engineer knows if it worked
|
||||
- [ ] Failure path is explicit for each step (not "if it fails, investigate")
|
||||
- [ ] Rollback procedure is complete and independently testable
|
||||
- [ ] Escalation paths name specific contacts, not just team names
|
||||
- [ ] Escalation table has no cells containing only "[Team name]" — every row must either have a real contact or be explicitly flagged as [FILL IN: on-call rotation link]
|
||||
- [ ] Rollback section contains at least one concrete command (not left as "[rollback command]" placeholder)
|
||||
- [ ] Runbook can be followed by someone who has never touched this system
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a runbook for [service] deployment"
|
||||
- "Create an incident response runbook for [alert type]"
|
||||
- "I need a runbook for [procedure]"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: system-design-interview
|
||||
description: "Structure a complete system design answer for interview questions or real architecture sessions. Use when asked to design a system, answer a system design interview question, or architect a solution at scale. Produces a structured answer covering requirements, capacity estimates, high-level design, component deep-dives, trade-offs, and follow-up considerations. Optimised for Opus 4.7 and newer models."
|
||||
description: "Structure a complete system design answer for interview questions or real architecture sessions. Use when asked to design a system, answer a system design interview question, or architect a solution at scale. Produces a structured answer covering requirements, capacity estimates, high-level design, component deep-dives, trade-offs, and follow-up considerations."
|
||||
---
|
||||
|
||||
# System Design Interview Skill
|
||||
@@ -14,8 +14,10 @@ Ask for these if not provided:
|
||||
- **Scope** (interview prep / real architecture decision / practice run)
|
||||
- **Scale target** (rough numbers: DAU, requests/sec, data volume — or "assume typical web scale")
|
||||
- **Constraints or priorities** (e.g. prioritise availability over consistency, minimise cost, low-latency reads)
|
||||
- **Time available** (interview context only: 30 / 45 / 60 minutes — skip for real architecture sessions)
|
||||
- **Emphasis** (optional — any area to go deeper on, e.g. "focus on the DB design" or "spend more time on scaling")
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### 1. Clarifying Questions
|
||||
Before designing, list 4–6 questions that would change the design. Examples:
|
||||
@@ -62,12 +64,7 @@ Then proceed with stated assumptions if answering an interview question.
|
||||
|
||||
### 5. High-Level Architecture
|
||||
|
||||
```
|
||||
[Client] → [CDN/Edge] → [Load Balancer] → [API Servers] → [Cache] → [DB]
|
||||
→ [Message Queue] → [Workers]
|
||||
```
|
||||
|
||||
Describe each layer in 1–2 sentences explaining its role and technology choice.
|
||||
Draw an ASCII diagram specific to this system. Do not default to the client→CDN→LB→API→Cache→DB template unless it genuinely applies. Label each component with the specific technology chosen (e.g. "Kafka" not "Message Queue", "PostgreSQL" not "DB"). Describe each component in 1–2 sentences explaining its role and why that technology was chosen.
|
||||
|
||||
### 6. Component Deep-Dive
|
||||
|
||||
@@ -122,12 +119,13 @@ Things to tackle in production but out of scope for this design session:
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Clarifying questions are design-changing (not generic filler)
|
||||
- [ ] Capacity estimates use real numbers (not just "it scales")
|
||||
- [ ] Capacity estimates show the arithmetic: DAU → requests/day → requests/sec → storage per record → total storage, so the numbers can be sanity-checked
|
||||
- [ ] Every row in the Trade-offs table has a non-empty Trade-off column (no rows where the trade-off is blank or says "none")
|
||||
- [ ] At least 2 component deep-dives with technology choices justified
|
||||
- [ ] Trade-offs section is honest (not just benefits of chosen approach)
|
||||
- [ ] Data flow is described end-to-end for the critical path
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Help me answer a system design interview: [question]"
|
||||
- "Design [system] for a system design interview"
|
||||
- "How would I architect [system] at scale?"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: test-strategy-doc
|
||||
description: "Write a test strategy document from a feature spec, PRD, or system description. Use when asked to create a test plan, write a test strategy, define QA approach, or plan testing for a feature or release. Produces a complete test strategy with scope, risk assessment, test types, coverage targets, and a prioritised test case outline. Optimised for Opus 4.7 and newer models."
|
||||
description: "Write a test strategy document from a feature spec, PRD, or system description. Use when asked to create a test plan, write a test strategy, define QA approach, or plan testing for a feature or release. Produces a complete test strategy with scope, risk assessment, test types, coverage targets, and a prioritised test case outline."
|
||||
---
|
||||
|
||||
# Test Strategy Document Skill
|
||||
@@ -11,12 +11,14 @@ Produces a complete test strategy from a feature spec, PRD, or system descriptio
|
||||
|
||||
Ask for these if not provided:
|
||||
- **Feature or system being tested** (paste a spec, PRD, or describe it in plain English)
|
||||
- **Tech stack** (language, framework, testing tools already in use if known)
|
||||
- **Tech stack** (language and framework — e.g. TypeScript + React, Python + FastAPI)
|
||||
- **Existing test coverage** (e.g. "we have unit tests but no E2E tests", "we use Jest + Playwright already", or "starting from scratch")
|
||||
- **Deployment cadence** (e.g. continuous deployment / weekly releases / quarterly — affects what must be automated vs. manual)
|
||||
- **Risk level** (low / medium / high / critical — affects depth and coverage requirements)
|
||||
- **Timeline** (when does this need to ship — affects prioritisation)
|
||||
- **Team context** (who is doing the testing — developers / dedicated QA / both)
|
||||
|
||||
## Output Structure
|
||||
## Output Format
|
||||
|
||||
### 1. Test Scope
|
||||
|
||||
@@ -66,7 +68,7 @@ Identify the highest-risk areas first — these drive depth and coverage:
|
||||
- **Tools:** [e.g. Playwright, Cypress, Selenium]
|
||||
- **Focus areas:** [The 3–5 most critical user flows]
|
||||
|
||||
**Performance Tests** *(include only if risk is medium+)*
|
||||
**Performance Tests** *(include if any row in the Risk Assessment table has performance as a risk factor, regardless of overall risk level)*
|
||||
- **What:** Load, stress, or latency testing
|
||||
- **Targets:** [Specific numbers — e.g. 200 req/sec at p95 < 200ms]
|
||||
- **Tools:** [e.g. k6, Locust, JMeter]
|
||||
@@ -115,11 +117,12 @@ Testing is complete when:
|
||||
|
||||
## Quality Checks
|
||||
- [ ] Risk table is populated and drives test priority (not filled in generically)
|
||||
- [ ] P0 test cases cover the highest-risk paths specifically
|
||||
- [ ] Every "P0 — exhaustive" row in the Risk Assessment table has at least one corresponding P0 test case
|
||||
- [ ] "Out of scope" section names at least one explicit exclusion (not left blank)
|
||||
- [ ] Each test type names a concrete tool (not "some testing framework")
|
||||
- [ ] Definition of Done is measurable (not "tests are done when QA is happy")
|
||||
|
||||
## Example Trigger Phrases
|
||||
## Usage Examples
|
||||
- "Write a test strategy for [feature]" + [paste spec or PRD]
|
||||
- "Create a test plan for [system]"
|
||||
- "How should we test [feature]?"
|
||||
|
||||
Reference in New Issue
Block a user