🧠 PM Skills — 822 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes

What is PM Skills?

PM Skills is an open-source library of 822 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.

Decode a lease before you sign it. Write a PRD your team can execute. Simulate the promotion committee before the real one meets. Check the weather with zero API keys. Generic AI gives you filler; these give you the structure a senior professional actually uses.

Works natively in Claude Code and Hermes Agent, with ready-to-paste exports for ChatGPT, Gemini, Cursor, Codex and 8 more tools. (PM stands for Professional, not just Product Management.)

Related MCP server: Awesome Agent Skills MCP Server

🐣 New here? Pick a door — each takes about 30 seconds

1. Just looking → open the ▶ Playground and run a skill in your browser. Nothing to install, nothing to sign up for.

2. You use Claude Code → type /plugin, search pm-skills, install. Done — ask "decode this lease" and watch.

3. You use anything else → npx pm-claude-skills add and pick your tool from the menu (Cursor, Codex, Windsurf, ChatGPT, Gemini…).

Nothing here can scare your setup. A skill is a markdown file your AI reads — no runtime, no telemetry, no accounts. Installing copies text files; uninstalling is deleting them. Skeptical? Good instinct: read one first — it's designed to be read by humans too.

Don't know what to look for? Describe your task in plain words at 🔎 find — "my landlord kept my deposit", "board meeting on Thursday" — and it names the skill.

💬 What can I ask it to do?

Anything below is a real ask that activates a real skill — say it in your own words, the description does the routing:

…all 822 asks live in the catalog.

⚡ Quick start

No npm install needed — npx pm-claude-skills … always runs the latest. npx pm-claude-skills list shows everything in your terminal. Full per-tool instructions: docs/installation.md.

📚 The skills

Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules — not vibes), a concrete output template, quality checks, and anti-patterns. All 822 pass the SkillSpec L3 gate and a security audit in CI.

For everyone — life's paperwork and decisions

For professionals — 35 fields

…plus HR, sales, operations, research, healthcare, educators, writers, social media, and more — the full profession index, or by bundle in plugins/ (104 bundles). Install any bundle: /plugin install pm-decoders@pm-skills.

Meta

Before installing anyone's skills (including these): skill-vetting — a security read for SKILL.md files. The library's own standard lives in SKILLSPEC.md; every skill's level is enforced in CI.

🔍 What does a skill look like?

A skill is a single markdown file with a name, a description that tells the assistant when to activate it, and a body containing the working framework: required inputs, decision rules or severity scales, a concrete output template, quality checks, and anti-patterns. The assistant reads it and gains the judgment; humans can read, audit, and edit the same file. No runtime, no lock-in.

---
name: lease-decoder
description: "Decode a residential lease into plain English and rank the
  clauses that can hurt you. Use when someone asks 'what am I signing'…"
---
## Framework: Severity Scale
- 🔴 Can cost you real money — auto-renewal into a full new term, break
  penalties beyond re-rental costs, deposit conditions written to fail…

That's the whole trick: it's markdown. Your agent reads it and gains the judgment; you can read it too, audit it, edit it, or write your own. No lock-in, no runtime, no telemetry.

💸 Cut your token bill

The pm-tokens bundle optimizes every stage of your agent's token journey — no API keys, stdlib Python, nothing leaves your machine. Five habits, typically 30–60% off a session's token flow:

# 1. Map the repo instead of reading it (~3% of the cost of reading everything)
python3 skills/repo-map/scripts/repo_map.py .

# 2. Crush bulk before it enters context (98% smaller on uniform JSON; errors always survive)
python3 skills/context-crusher/scripts/context_crush.py --mode json --file response.json

# 3. Measure what anything costs — at YOUR prices, times YOUR call volume
python3 skills/token-cost/scripts/token_cost.py --file CLAUDE.md --price-in 3 --calls 200

Plus the judgment skills: token-diet (output costs 3–5× input — diet it where safe), context-budget (cache-aware layout: stable first, volatile last), and session-handoff (resume at ~5% of transcript size). See your own breakdown in the 🪙 Token Dashboard — paste what rides in your context, get computed per-piece savings, all in-browser. The full how-to: docs/SAVE-TOKENS.md.

🤝 Make the most of the cowork skills

The pm-cowork bundle is 100 skills for the office work an AI coworker actually does. Install it (/plugin install pm-cowork@pm-skills), then — the whole trick — describe your mess, don't name the skill: say "my inbox is 4,000 deep", "nobody reads my status updates", "this spreadsheet came from someone who left" — the right skill activates on the ask.

Start where it hurts:

Three habits that compound: (1) The weekly review is the keystone — it feeds task-triage-matrix, deep-work-blocking, and personal-wip-limits automatically. (2) The skills chain on purpose — email-to-tasks feeds the task triage; the meeting audit feeds async-instead; delegation-brief hands off what the triage says to shed — follow the links inside each skill. (3) Teams adopt one norm at a time — start with agenda-or-cancel or working-agreements, let it stick, then add the next; the ten-norms-on-Monday rollout is how none of them survive.

🔬 Prove it, and stop paying rent

Two CLI tools for the trust-and-cost problems the ecosystem keeps hand-waving — both keyless-to-inspect, both one command:

# Does your skill actually work? Prove it. Paired A/B — skill on vs off, same tasks,
# REAL token counts from the API's usage fields, optional blind judge, sha-pinned receipt.
npx pm-claude-skills prove --skill ./my-skill --tasks tasks.txt --runs 2 --judge
npx pm-claude-skills prove --skill ./my-skill --tasks tasks.txt --dry-run   # plan + call count, spends nothing

# Your MCP servers are charging you rent. Measure it: per-server token cost,
# unused-in-N-days flags, "disconnect these three, save X tokens per message".
npx pm-claude-skills mcp-audit --connect

prove exists because the ecosystem is full of "65% better!" claims and almost none are measured — it's the honest-broker harness (the JetBrains "advertised 65%, measured 8.5%" story is exactly why). mcp-audit reads your Claude configs, speaks real MCP to each server to count its schema tokens, and scans your session logs for what you actually use. See also the 📊 AI Spend page — every agent's cost (Claude Code, Codex, Copilot) in one meter, all in-browser.

Agent safety: the pm-seatbelt bundle is the pre-flight checklist before an agent touches email, the browser, or files — least-privilege reviews, prompt-injection spotting, and the blast-radius drill for going autonomous. And RFC 0002 — HANDOFF.md is a dead-simple session-handoff convention (your agent, but it remembers Monday) — a file, not a server, with reference hooks.

✅ Quality, not just quantity

• Every skill passes the SkillSpec L3 gate — structure, framework, quality checks, anti-patterns — enforced in CI on every commit

• Eval-scored — 208 scored outputs, avg 4.8/5, judged blind

• Security-audited — a dedicated CI workflow sweeps every skill and script; calculators are stdlib-only and deterministic with byte-exact output tests

• Honest by design — decoders end with a not-legal-advice line, calculators name what they don't model, simulators debrief out of character, and skills that shouldn't ghostwrite (student statements) coach instead

🎁 Beyond the skills (the bonus material)

The library grew an ecosystem — all optional, all linked from the full showcase:

▶ Skill Playground — try any skill in your browser, no install · 📸 the Gallery — the creative side, in screenshots · Anti-Pattern Museum — 2,900+ shareable rules · The Handbook (also a real printed book) · Workflow recipes · Subagents & slash commands · MCP server + REST API · n8n / Slack / Obsidian integrations · The Boardroom · SkillBench · Org Edition · 🇪🇸 🇫🇷 🇨🇳 🇯🇵 translations

📄 The one-page cheatsheet

The whole library on one poster — start path, standout features, and install one-liners for every tool. Print it, share it, drop it in a slide.

🖼️ PNG · 📄 PDF · 🌐 Live poster · 📥 Markdown

🆕 Latest

v67.0.0 — the everywhere wave: six new rooms — the trades (quotes, stage payments, apprentices), the committee (AGMs, treasurers, the council mic), open-source maintainers, aging parents (the talks, the sibling summit), the kitchen, the band — plus used-car/mechanic-quote decoders, the group-trip fixer, and 🌱 daily practice; 822 skills, 104 bundles. v66 — new-gen; pm-newgen — decode your first brand deal, clip the podcast, prep tonight's D&D, fix the dating profile honestly, vibe-check the weekend app, keep the flat peaceful, climb ranked on purpose, flip thrift finds, plan the micro-retirement, get your attention back; 822 skills, 104 bundles. v65 — pm-2027; ten skills for problems you don't have yet (but will) — offboard an AI coworker, drill the deepfake wire-fraud call, hire your agent like an employee, declare context bankruptcy, send your position to meetings instead of your body, publish your personal API, simulate the reorg before announcing it; 822 skills, 104 bundles. v64 — game night; pm-tabletop — teach any board game in 5 minutes, settle rules arguments fairly, plan the lineup, design your own game, and spar the Catan trade against a hidden agenda with a scored debrief; 822 skills, 104 bundles. v63.1 — pixel confetti: pixel-gif-maker — custom retro Slack GIFs (scroll, pulse, party, sparkle) from a pure-stdlib deterministic encoder; 822 skills. And v63.0.0 — the dead mentors: history's sharpest operators, resurrected as skills — Machiavelli reads your reorg (with the honest counterweight built in), Sun Tzu decides fight/reshape/decline, Franklin's decision algebra settles the offer you keep flip-flopping on, Marcus Aurelius debriefs the day that went badly, and Arnold Bennett (1908) finds your inner day — real methods from public-domain classics, chapter-cited, never misquoted. Earlier — v62.2, the distribution wave (SkillScan, telemetry, SkillBench v2, quiz, wins, WhatsApp); v62.1, nine frontiers. Full history: CHANGELOG · releases

❓ First-timer questions, straight answers

🤝 Contributing

Add a skill via PR (the standard, CONTRIBUTING), request one via issue, or publish your own repo to the community index and earn the badge. Translations follow the pattern in skills-i18n/.

❤️ Support

If a skill saved you real money or a real mistake, star the repo — it's how others find it. Sponsors fund the playground's free runs and get naming rights, not influence: become a sponsor.

📄 License

MIT — use them, fork them, ship them at work. Skills are judgment, and judgment wants to be free.

*Built by Mohit with Claude. 822 skills · 104 bundles · 35 professions · every commit gated. The long version of this README — every feature, wave, and frontier bet — lives in the Showcase.*