69d4fab0b3
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
5.4 KiB
5.4 KiB
Changelog
All notable changes to this project are documented here.
The format is based on Keep a Changelog, and this project broadly follows Semantic Versioning: each new wave of skills bumps the major version, extensions and fixes bump minor / patch.
Unreleased
Added
- Multi-platform export generator.
scripts/build-exports.mjsrenders every skill into platform-ready files underexports/from a single source of truth (theSKILL.mdbody), so content is never maintained twice. Ships ChatGPT (exports/chatgpt/.../SYSTEM_PROMPT.md) and Google Gemini (exports/gemini/.../GEM_INSTRUCTIONS.md) exports, plus aPLATFORMSregistry that makes adding Cursor/etc. a few lines. Includes a--checkmode and acheck-generatedCI workflow that fails if exports orweb/skills.jsondrift. - Programmatic helpers (stdlib Python) for three flagship skills. Each runs with
zero dependencies and computes part of the work instead of estimating by hand:
sprint-planning/scripts/capacity_calculator.py— recommended sprint commitment from team size, availability, velocity, and carry-over (caps at 80% of velocity).rice-prioritisation/scripts/rice_calculator.py— calculates and ranks RICE scores from JSON/CSV and auto-flags quick wins, moonshots, and low-confidence items.cs-health-scorecard/scripts/health_score.py— weighted health total out of 100 with RAG banding and weight validation.
CHANGELOG.md— this file, back-filled from the release history.SKILL-AUTHORING-STANDARD.md— the canonical structure every SKILL.md follows (frontmatter, required sections, quality bar, anti-patterns).- Skill tiers — a
TIERS.mdreference and README section marking skills as Production-Ready, Stable, or Experimental so new users start with the strongest work. - Cross-tool compatibility — README now documents which platforms the skills work on (Claude Code natively; the SKILL.md bodies port to other agents and chat LLMs).
- Skill Playground upgrades — the hosted web app gains a tier filter and per-tile
tier badges, plus a "Use this skill in another tool" panel that copies the
instructions formatted for ChatGPT, Gemini, or raw. Tier data comes from a single
machine-readable source,
skill-tiers.json.
Fixed
web/skills.jsonis now deterministic. Removed the wall-clockgeneratedAtfield (it was unused by the UI and made every rebuild differ), so the newcheck-generatedCI step can reliably verify the index is in sync with the source skills.- Related Projects — README section linking to other community Claude Skills
libraries and the
awesome-claude-skills/awesome-claude-codelists.
Changed
SECURITY.mdsupported-versions table updated to the current release line.
14.0.0 — Writers & Content Creators + 7 Community Skills
Added
- New profession Writers & Content Creators (
pm-writers): Instagram Post Downloader, AEO Optimizer, Thumbnail Creator, Substack Notes Scraper, Notes Humanizer. pm-cross(+3): Sycophancy Challenger, Last 30 Days Research, NotebookLM Connector.pm-operations(+2): Email Triage, Morning Intelligence.pm-engineering(+2): Context Mode, Claude Superpowers.
Library now spans 167 skills across 18 professions + 4 agent templates.
[13.0.0] — Social Media Profession
Added
- New bundle
pm-social: Social Media Audit, Influencer Brief, Community Management Playbook, Social Ad Campaign, Viral Content Framework.
[12.0.0] — 150 Skills Milestone
Added
- 15 skills across 10 bundles, including Cohort Analysis, Data Pipeline Spec, Renewal Playbook, Customer Success Plan, 360-Degree Feedback Template, Team Health Check, Risk Register, RACI Matrix, Social Media Strategy, Product Positioning Doc, Customer Journey Map, User Story Writer, AI Ethics Review, Partnership Proposal, Design System Audit.
Library reached 150 skills across 16 professions.
[11.0.0] — Engineering Expansion (500 ⭐)
Added
pm-engineeringexpanded to 35 skills — CI/CD, SLOs, capacity planning, DR plans, threat models, schema/migration design, and more.
[10.0.0] — Customer Success + Engineering
Added
- Customer Success bundle (
pm-cs, 250 ⭐ milestone): Customer Health Scorecard, QBR Deck, Escalation Brief, Churn Analysis. - Engineering (500 ⭐ milestone): CI/CD Playbook, SLO & Error Budget, Developer Onboarding Doc, On-Call Runbook — plus Debugging Log Analyser, PR Description Writer, System Design Interview, Changelog Generator, Test Strategy Doc, Runbook Writer.
Library reached 114 skills across 16 professions.
[6.0.0] — 100 Skills Milestone
Added
- Quality rebuild across all existing skills, plus 10 Figma skills.
- 7 new skills: Teaching Lesson Plan, SEO Content Brief, Media Pitch, Change Management Plan, Workshop Facilitation Guide, Sales Forecasting Model, Tax Planning Checklist.
Earlier releases (v1.0.0 – v5.0.0) predate this changelog. See the article series for the full history of how the library grew from the first PM toolkit to 100+ skills.