The check-generated CI step was failing with "web/skills.json is stale"
because build-skills.mjs stamped a wall-clock generatedAt into the file, so
every rebuild differed and git diff --exit-code never matched.
- web/build-skills.mjs: drop the unused generatedAt timestamp -> deterministic
output the CI staleness check can verify. Also tags each skill with its tier.
- skill-tiers.json: single machine-readable source for tier membership
(Production-Ready / Experimental); TIERS.md points to it.
Playground upgrades (hosted on GitHub Pages):
- Tier filter (Production-Ready / Stable / Experimental) + per-tile tier badges.
- "Use this skill in another tool" panel: copy the instructions formatted for
ChatGPT, Gemini, or raw — mirrors the generated exports/ files.
- web/README documents the new options and the deterministic build.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016JWn5jRD5tcEFKrubjQ6Px
Proves the PLATFORMS registry extends cleanly: adds Gemini (Gem instructions)
alongside ChatGPT, generated from the same SKILL.md source.
- scripts/build-exports.mjs: register `gemini` -> exports/gemini/<bundle>/<skill>/
GEM_INSTRUCTIONS.md (body + a one-line role primer from the description).
- Fix: the root exports/README.md now always lists every registered platform,
so `--platform x` no longer drops the others from the overview.
- exports/gemini/: 172 generated Gem instruction files + index.
- README "Ready-to-use exports" and CHANGELOG now list Gemini.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016JWn5jRD5tcEFKrubjQ6Px
Make the library multi-platform without duplicating content. Each
skills/<name>/SKILL.md body remains the single source of truth; a new
generator renders platform-ready exports from it.
- scripts/build-exports.mjs — dependency-free Node generator with a PLATFORMS
registry so new platforms (Gemini, Cursor, …) are a few lines. Ships ChatGPT
exports at exports/chatgpt/<bundle>/<skill>/SYSTEM_PROMPT.md (172 skills),
plus generated index READMEs. Supports --platform and --check.
- exports/ — generated ChatGPT system prompts, ready to paste into a Custom GPT.
- .github/workflows/check-generated.yml — fails a PR if exports or
web/skills.json drift from the source skills.
- README "Works With" now documents the ready-to-use exports and regen command.
- CHANGELOG + SKILL-AUTHORING-STANDARD note the generated artifacts.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016JWn5jRD5tcEFKrubjQ6Px
Five improvements to position the library as a serious engineering project:
1. Cross-tool compatibility — new README "Works With" section honestly
documenting where skills run (Claude Code natively; SKILL.md bodies
port to other agents and chat LLMs as system prompts).
2. Python helper scripts (stdlib-only) for the three strongest skills:
- sprint-planning: capacity_calculator.py (recommended commitment)
- rice-prioritisation: rice_calculator.py (ranks, flags quick wins/moonshots)
- cs-health-scorecard: health_score.py (weighted total + RAG)
Each is wired into its SKILL.md and synced to the plugin copies.
3. Explicit skill tiering — TIERS.md + README section marking 46
Production-Ready skills and calling out Experimental (external-dependency)
ones; everything else is Stable.
4. Repository hygiene — new CHANGELOG.md (Keep a Changelog format) and
SKILL-AUTHORING-STANDARD.md; refreshed SECURITY.md version table and
helper-script disclosure; added .gitignore.
5. Related Projects — README section linking to alirezarezvani/claude-skills
and the major awesome-claude-skills / awesome-claude-code lists.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016JWn5jRD5tcEFKrubjQ6Px
- Streaming loop swallowed errors: a mid-stream error event (e.g.
overloaded_error) was thrown inside the same try/catch used to skip
unparseable SSE lines, so it was silently ignored and the run reported
"Done." with truncated output. Separate JSON parsing from event handling
so real errors surface to the user.
- Raise max_tokens 4096 -> 8192 to avoid truncating long skill outputs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
On push to main, rebuild web/skills.json from the SKILL.md files and publish
web/ to GitHub Pages, so the live site always reflects the current skill
library. Manual runs supported via workflow_dispatch.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A zero-backend static web app to run any of the 172 skills directly in the
browser using the user's own Claude API key (stored only in localStorage,
sent straight to api.anthropic.com).
- build-skills.mjs: generates skills.json from skills/*/SKILL.md, parsing
frontmatter, the Required Inputs section (-> form fields), and a one-line
summary for each skill tile.
- Tile gallery with bundle tag, title, and one-line description; search +
bundle filter; click a tile to open an auto-generated input form.
- Streams output via the Anthropic Messages API (direct browser access),
with copy/download, model picker, and Show/Hide key toggle.
- Product Notes logo in the header.
- README: add Skill Playground section + screenshot, a table of contents,
and collapse the long changelog and full skills list into <details> blocks.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Processed 27 skills: teaching-lesson-plan through feature-prioritisation and all figma skills.
Added Anti-Patterns sections to all 27 skills.
Added Quality Checks section to financial-due-diligence (was missing entirely).
Converted user-research-synthesis Quality Standards to binary checkbox format.
Rewrote descriptions for figma-design-critique-pm, figma-design-qa, figma-design-review,
team-health-check, and user-interview-synthesis.
https://claude.ai/code/session_01MuGKn3a3Gbqoe8uM5Lmuqt
Processed 24 skills: pr-description-writer through tax-planning-checklist.
Added Anti-Patterns sections to all 24 skills.
Added Required Inputs section to product-launch-checklist.
Rewrote descriptions for retro-analysis, substack-notes-scraper, and sycophancy-challenger.
https://claude.ai/code/session_01MuGKn3a3Gbqoe8uM5Lmuqt
Processed 29 skills: content-calendar through pptx-slide-auditor.
Added Anti-Patterns sections to all 29 skills.
Rewrote descriptions for instagram-post-downloader and job-application.
https://claude.ai/code/session_01MuGKn3a3Gbqoe8uM5Lmuqt
- Add Anti-Patterns section (3-5 binary checkboxes) to all modified skills
- Fix Quality Checks to use binary checkbox format where needed
- Rewrite descriptions to verb-when-produces format where needed
- Add Required Inputs sections to skills missing them
- Fix email-triage frontmatter YAML quoting
https://claude.ai/code/session_01MuGKn3a3Gbqoe8uM5Lmuqt
New profession: Social Media (Skills 151–155)
Skills added:
- social-media-audit: Scored platform audit with competitive benchmarking and prioritised action plan
- influencer-brief: Complete creator partnership brief with deliverables, approval workflow, and commercial terms
- community-management-playbook: Response frameworks, moderation rules, escalation tiers, and DM templates
- social-ad-campaign: Full-funnel paid social plan with ad copy for every format and A/B testing plan
- viral-content-framework: 6 hook formulas, 5 content structures, platform playbooks, and content testing system
Changes:
- Added plugins/pm-social/ bundle with all 5 skills
- Updated .claude-plugin/marketplace.json to v13.0.0 (155 skills, 17 professions, 24 bundles)
- Updated README.md: title, badges, description, What's New section, All Skills table, plugin bundle list
https://claude.ai/code/session_01E4bTUWxx4Zo5rsFpad5X5B
Renamed ## Example Trigger Phrases → ## Usage Examples to make the section
clearly human-facing documentation rather than a system instruction.
Restores content that was removed in the previous quality pass.
Skills updated (both skills/ and plugins/pm-engineering/skills/):
code-review-checklist, debugging-log-analyser, changelog-generator,
pr-description-writer, system-design-interview, test-strategy-doc,
runbook-writer, incident-postmortem, api-docs-writer,
architecture-decision-record
https://claude.ai/code/session_01C3HwChrccJd145vJ6Z7ajF
pm-engineering grows from 14 to 35 skills (v4.0.0), completing the full
25-skill promise made at the 500-star milestone. The library grows from
114 to 135 total skills.
New skills added (21):
- security-threat-model: STRIDE-based threat model with trust boundaries, per-component threat enumeration, risk scores, and mitigations
- performance-budget: Performance budgets for Core Web Vitals and backend latency SLOs with CI enforcement
- database-schema-design: Schema documentation with ER diagram, DDL definitions, index strategy, and access pattern analysis
- database-migration-plan: Zero-downtime expand-contract migration plan with per-step rollback and data validation queries
- technical-debt-register: Debt inventory with impact scoring, effort estimates, and quarterly resolution roadmap
- rfc-writer: Engineering RFC covering problem, proposed solution, alternatives-with-rejection-reasons, and rollout plan
- capacity-planning: Traffic forecasts, resource requirements by tier, scaling strategy, and infrastructure roadmap
- load-testing-plan: Load test plan with baseline/stress/spike/soak scenarios, k6/Locust skeleton, and CI gates
- disaster-recovery-plan: DR plan with RPO/RTO targets, per-scenario runbooks, game day testing, and communication templates
- feature-flag-guide: Feature flag lifecycle — taxonomy, rollout strategy, monitoring requirements, cleanup policy, governance
- dependency-audit: CVE vulnerabilities, license compliance, outdated packages, and 30-day remediation plan
- service-catalog-entry: Microservice catalog entry with SLAs, API contract, data classification, and runbook links
- monitoring-setup-guide: Four golden signals, alert rules spec, log schema, tracing setup, dashboard layout spec
- local-dev-setup: Local development guide — prerequisites, env vars, Docker deps, test commands, 5 failure fixes
- api-versioning-strategy: Versioning scheme, lifecycle policy, breaking change classification table, deprecation process
- infra-as-code-review: IaC review for Terraform/CloudFormation/Pulumi with severity-classified findings
- engineering-weekly-report: Consistent weekly status — shipped/blocked, metrics, decisions, risks, next week
- tech-radar: ThoughtWorks-format radar with Adopt/Trial/Assess/Hold, blip rationales, maintenance process
- sprint-velocity-analysis: Velocity trends, completion patterns, improvement recommendations, capacity forecast
- microservices-decomposition: Domain-driven service boundaries, communication patterns, data ownership, migration plan
- engineering-hiring-rubric: Technical interview rubric with level expectations, coding/system design scorecards, debrief guide
Also:
- plugin.json bumped to v4.0.0 with all 35 skills listed
- marketplace.json updated to v11.0.0, library count 135
- README updated: skill count, all section numbers, engineering table expanded, star milestone marked complete
https://claude.ai/code/session_01C3HwChrccJd145vJ6Z7ajF
Reposition the library without changing the repo name or URLs.
Adds 'PM stands for Professional' tagline to README header and
marketplace.json description to reflect the library now covering
16 professions beyond product management.
This release adds three new agent templates to the library, bringing the total to four.
New templates:
- PM Discovery Agent: synthesises customer interviews from Notion or Google Drive,
identifies cross-interview themes, scores assumption confidence, generates follow-up questions
- PM Stakeholder Comms Agent: detects audience type (executive/investor/stakeholder/board),
pulls activity from Linear/Jira/Drive, drafts in audience-appropriate format
- PM Launch Agent: end-to-end launch coordination with channel-specific content,
calendar, success metrics, and launch checklist
Each template follows the established pattern: README, AGENT.md, orchestrate.sh,
2 subagents, connectors with example configs, examples, smoke test.
Total file count: 37 new files across 3 templates.
Updated README to position library as 4-template collection.
Bumped marketplace.json from v8.0.0 to v9.0.0.
- Added templates/pm-sprint-agent/ directory with full agent template
- AGENT.md system prompt with explicit step-by-step workflow
- 2 subagents: capacity-analyst and risk-scorer
- 2 connectors: linear and jira (with example configs)
- Symlinked skills from main library: sprint-planning, sprint-brief
- orchestrate.sh end-to-end workflow script
- examples/ folder with input and output examples
- tests/ folder with smoke test
- Updated README to position skills as building blocks for agent templates
- Added Anthropic agent templates announcement reference (May 5, 2026)
- Bumped marketplace.json to v8.0.0
- Listed 7 candidate agent templates this library supports
This is the first agent template in the library. More to follow.
mohitagw15856
Claude
Mohit