🧠 PM Skills — 466 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes

Big repo? It’s a monorepo on purpose — but you probably need one folder. REPO-MAP.md tells you which, and the skills-only clone is 10 seconds: git clone --filter=blob:none --sparse && git sparse-checkout set skills

💛 The free runs are sponsor-funded. Every sponsor dollar visibly raises the daily cap on the counter above — and sponsors get naming rights, not influence: your name in this README, your logo on the playground, or a Boardroom bench carrying your company’s name. → Become a sponsor

🎉 Now published in the official Anthropic Claude plugin directory — install it straight from the /plugin marketplace in Claude Code.

Generic AI gives you filler. These give you the structure a senior pro actually uses — PRDs, exec updates, launch plans, postmortems — as open-source SKILL.md files. Across 25 professions, not just product management. One source, every AI tool.

🆕 Now plugs into your stack — automate skills in n8n, build apps on Lovable, and run them in your Obsidian vault, all via a read-only REST API on the hosted Worker.

⭐ If this saves you time, star the repo — it’s the #1 way to help others find it.

⚡ Use it in 30 seconds — pick one

Not sure? Start with the Playground. This is a CLI, not a library — you don’t need npm install; npx pm-claude-skills … always runs the latest. Browse everything first with npx pm-claude-skills list.

PM stands for Professional, not just Product Management. 466 professional skills + 4 agent templates across 65 bundles covering 25 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.

A community-built library of professional skills for every field — product management, engineering, customer success, marketing, social media, writers, design, legal, finance, HR, sales, operations, research, and more. Each skill is a structured SKILL.md file that teaches an AI assistant how to produce professional-grade outputs for your workflows. Skills run natively in Claude Code and Hermes Agent (same open SKILL.md standard), and ship as ready-to-paste exports for ChatGPT and Gemini — see Works With.

🆕 v45.0.0 — the spectacle release: ⚔️ Duels — challenge a friend to the identical Gym negotiation or Panel candidate (same hidden state, side-by-side scorecard), 🎓 The Charter — the performance-based, cryptographically verifiable certification, and the library in 3D: 🌌 Galaxy 3D (fly a bloom-lit starfield where your used skills burn brighter), 🏗 the Tower of Claims (your document as a physics tower — data is steel, assumptions are glass, watch it stand or collapse), 🏛 the Stage (Boardroom replays as cinema with a cracking hologram), ✨ holo persona cards, 🏆 the Trophy Forge, 🌃 Skill City, ☄️ the Reckoning orrery. Plus the record going public: first official SkillBench results (Haiku 4.5 vs Sonnet 4.6), evolution loop run #1 (all champions held under blind judging), 3 sha256-pinned registry packs, and a live free-runs-served badge. Earlier — v44, the legendary release: Campaign mode, the Professional Work Handbook (2,297-rule Anti-Pattern Almanac), the Reckoning, the ecosystem package manager, zero-key MCP sampling, pm-skills-tools, the SkillSpec badge & the census. Earlier — v43, the local-first & learning wave: the 🗂 workspace bridge, Boardroom replay links & bench packs, 🎤 The Panel, 🎓 The Academy, 🎁 Wrapped, the evolution loop & pm-method. Earlier — v42: depth (references/ + templates/) on all Production-Ready skills, 🔊 Theatre voices, Firm calibration & the CI smoke suite. Earlier — v41, the modern skills wave: two new domains — 🤖 pm-agentnative (build for non-human users: mcp-server-spec, agent-readiness-audit, agent-era-pricing, human-in-the-loop-design, voice-agent-design) and 🧑‍💼 pm-aiwork (the questions every manager has this year: ai-roi-audit, role-redesign-for-ai, ai-usage-policy, ai-assisted-performance-review, ai-content-audit) — plus 5 singles (ai-code-review, synthetic-user-research, async-decision-memo, brand-impersonation-response, feature-sunset-plan). Also: 🌠 Galaxy shooting stars + a 🎲 Warp button, 🎓 frameable certificates from the arena pages, and 🔌 MCP pairings — skills that act through your connected servers. Earlier — v40: The Firm. v39 (three waves): ⚡ Superpowers: SkillBench (the professional-work benchmark for models) · the community registry (npm-for-skills) · the Interview Gauntlet · CI recipes + ambient hooks · Hugging Face dataset publishing · localization to 8 languages. 🤯 Breathtaking: living artifacts, Document X-ray, The Gym, pm-vision, style-fingerprint, evidence-lock. ✨ Revamped: the playground command bar + Galaxy 2.0 with a guided Sky tour. 466 skills · 66 bundles · 25 professions. → CHANGELOG · all releases.

▶ See it in action — try the live Skill Playground

👆 Pick any skill, fill a short form, and run it with your own key — no install required.

---

🏢 The Firm — don’t run tools, employ a staff

Everything below is pull: you show up and run something. The Firm is push — the endgame the whole library was building toward. Charter a standing team once, then convene: your 💰 CFO, ❤️ Chief Customer Officer, 🛠️ CTO, and 🦈 Head of Strategy (hire 📣 Growth and ⚖️ Counsel too, or excuse anyone) each file a delta-aware memo on their beat — what changed, never a restatement — ending in a falsifiable prediction with a check-by date. Then the staff hold a boardroom session without you and send you the minutes: decisions, asks, dissent preserved. As reality lands, score the predictions — and each staff member’s card shows a live calibration record. You can performance-review your AI staff.

In Claude Code, /firm runs the same session natively — grounded in your FIRM.md, Brain, and git log, minutes saved to firm-minutes/, predictions to the Brain’s ledger. Convene the Firm →

---

✨ The showcase — six things no other skills library does

---

👋 New here? Start in 30 seconds

The problem: Ask any AI for a PRD, an exec update, or a launch plan and you get generic — plausible-sounding filler you still have to rewrite from scratch. The model doesn’t know what “good” actually looks like for professional work.

What this fixes: Each skill is a battle-tested SKILL.md that teaches the AI the real structure, rigour, and judgement a senior professional uses — so the first draft is one you can ship, not one you have to redo.

Try these 5 first — no install needed, run them right in the live Playground:

→ Want proof first? See real sample outputs from each skill. Like what you see? Install in 2 minutes · browse all 451 skills · ⭐ star the repo so others find it.

---

📄 Good content deserves good paper

It’s not just text — the playground exports every result as a professionally typeset PDF (pick a theme; it even tints to your brand colour). Here’s the same skills producing real, designed documents — click any to open the PDF:

Generate yours: run a skill in the Playground, then Download → PDF · Paper / Modern / Technical. Add a Brand color: #hex line to your context and it tints to match (last tile). Personal documents live in the pm-personal bundle (résumé, cover letter, bio, LinkedIn, portfolio, one-pager).

---

📄 The shareable cheatsheet

---

🧠 The Professional Brain — local-first memory for any AI agent

Generic AI forgets everything between sessions, so you re-paste context forever and last quarter’s why evaporates. The Professional Brain is the fix — and it’s the most novel piece here, worth a look on its own:

• Plain markdown, no vector DB — a brain/ folder (knowledge · decisions · hypotheses · stakeholders) your AI reads before answering and writes to after. Grep-able, auditable, Obsidian-compatible — memory you can read and correct by hand, not a black box.
• Provenance over confidence theatre — every fact is tagged [data] [interview] [external] [verbal] [hunch], so a hunch never poses as a measured result.
• It acts, safely — the action-runner turns a skill’s recommendations into real tickets/messages: dry-run, risk-rated, approval-gated, then recorded back. Nothing acts silently.

→ Read the architecture · 5-min Quickstart · try it in the browser

---

🔄 One library, the whole professional workflow

---

🧩 Workflow Recipes — chain skills into one flow

🏛️ The Boardroom — your document vs. five AI executives

Every tool above helps you write the document. The Boardroom is where you find out if it survives a leadership team — before the real one sees it.

Paste a PRD, launch plan, investor pitch, or strategy memo. A bench of five AI executives — 💰 a CFO who kills anything that can’t show its maths, 🛠️ a CTO who asks what breaks at 10×, ❤️ a Chief Customer Officer channelling your angriest user, ⚖️ a General Counsel who reads every superlative as a future lawsuit, and 🦈 a sceptical VC who’s seen 400 decks this year — debate it live in structured rounds:

1. Opening statements — each executive’s three sharpest points, severity-tagged BLOCKER / RISK / QUESTION
2. Cross-examination — they argue with each other, concede points, and update positions
3. The verdict — a neutral Chair weighs the arguments and issues a decision memo: ✅ approve / 🟡 conditions / 🔴 rework / ⛔ reject, risks ranked with owners, and the 3–5 changes that would survive the room

Seat or excuse executives, set the grill level (🤝 constructive → 🔥 brutal), and download the decision memo. Runs entirely in your browser with your own key — same as the playground. Convene the board →

It anchors a whole pressure-test suite — and with 🔊 Theatre mode the executives now speak their turns aloud in distinct voices, while 🎙 lets you answer the Defense and the Gauntlet’s interviewer out loud (browser speech, zero API):

• 🔏 Attestations — every verdict exports as a tamper-evident record (SHA-256 of the exact text + session facts + verdict). Anyone can check it at verify.html: paste the document and the attestation, and a single changed character fails the match. As AI-drafted documents flood teams, “was this ever pressure-tested?” becomes checkable.
• 🛡️ The Defense — the Boardroom reviews the document; this reviews you. The executives cross-examine you live, one question at a time; you answer; a neutral Chair scores your defense (command of the facts, evidence over assertion, honesty about unknowns, composure) and tells you exactly what to prepare before the real meeting. Saying “I don’t know” honestly scores better than bluffing.
• 🥊 The Gym — practice with hidden state: negotiate a salary, renewal, vendor deal, or exec pushback against a counterparty with a secret bottom line, hidden pressures, and subtle tells. Only the debrief reveals what was actually achievable — and scores you against it, with drills. Scores persist locally, so you can watch yourself improve.
• 🩻 Document X-ray — see the evidence skeleton under your prose: every sentence heat-mapped as data · sourced · assertion · superlative · assumption, load-bearing sentences outlined, and the weakest claims listed to fix first — before someone in the meeting finds them for you.

And two upgrades to how skills feel: the playground now renders 🎛 living artifacts — for RICE, roadmaps, journey maps, and health scorecards the output includes an interactive component (drag a confidence slider on the RICE board and watch the ranking re-sort live) — and 📷 pm-vision lets you attach whiteboard photos, competitor screenshots, or slide photos so vision-first skills (whiteboard-to-spec, screenshot-teardown, deck-autopsy) read the pixels as the primary input. Want outputs in your voice, with your evidence? style-fingerprint and evidence-lock do exactly that.

🔮 The library as infrastructure — the frontier bets

Beyond running skills, the repo is becoming infrastructure for whatever agents come next:

And the browser extension (v1.1) now lints your own writing against any skill’s Quality Checks and Anti-Patterns — select text anywhere, get pass/fail verdicts with specific notes. Grammarly for professional judgment. → extension/

🏆 The Interview Gauntlet — from job posting to signed offer

The most requested arc, as one experience: the Gauntlet decodes what a job posting actually wants, forges your raw experiences into metric-led interview stories mapped to the decoded requirements, cross-examines you live as the hiring manager (five questions that build on your answers — honest “I don’t know” beats bluffing), then puts you on the phone with a recruiter whose approval band you can’t see. You leave with a readiness score /100, the tells in your answers quoted back at you, and the three preparations that would most move the score. 🎓 Practice → 🎯 Realistic → 🔥 Brutal.

---

🎤 The Panel — you’re the interviewer now

The Gauntlet trains you to be interviewed; the Panel trains the harder, rarer skill: telling a great candidate from a great talker. The AI plays a candidate with a hidden archetype — genuinely strong, polished-but-evasive, or a confident bluffer whose stories wobble under a second follow-up. You ask the questions, you write the hire/no-hire recommendation before the reveal, and a hiring coach scores your technique: evidence-pinning, follow-up discipline, and the tells you caught or missed.

🎓 The Academy & 🎁 Wrapped — learn it, then see your story

The Academy turns the library’s own Anti-Patterns into three learning tracks (🎯 executive communication, 🔬 discovery & evidence, ⚙️ work discipline) — 18 spot-the-flaw drills with explanations that quote the exact skill rule, no API key needed, each track examined live in an arena, certificate on graduation. And Wrapped plays your practice back as an animated story from purely local data — personal bests, imposters caught, prediction calibration, your earned persona title — with a canvas share card. Nothing leaves the machine.

🗂 Local-first, all the way down

Connect the Firm or the Boardroom to a real folder on disk (the 🗂 chip, Chromium): minutes, verdicts, transcripts, and predictions land as markdown files — point Claude Code at the same folder and the web arenas and the CLI become one product. Share a whole Boardroom session as a replay link where the URL fragment is the data (gzip, no server). Swap the Boardroom’s bench for the 🦈 fundraising, 🏥 healthcare, or 🚀 seed-stage preset — or build your own executive, or publish a bench pack for others. Teams? A folder convention, not a backend — a shared git repo of brain/ + firm-minutes/ + boardroom/ is auth, audit, review, and sync we never have to build. Run npx pm-claude-skills doctor for a read-only checkup of your whole setup, ℞ included.

---

🌌 The library in 3D

• Galaxy 3D — 466 skills as a bloom-lit starfield you fly through; your sky is yours (stars you’ve run burn brighter). Skill City — the same idea as a dusk skyline: windows light up in buildings you’ve used.
• The Tower of Claims — your document as a physics tower: data is steel, assumptions are glass, and the stress test shows the argument stand or collapse. Keyless demo built in.
• The Stage — any Boardroom replay as a cinematic 3D scene: the hologram document cracks as objections land; the verdict seals it gold or shatters it.
• ⚔️ Duels — challenge links from the Gym and the Panel: your friend faces the identical hidden scenario, side-by-side scorecard at the end. The Charter — the performance-based, cryptographically verifiable certification. The Trophy Forge — cast it in spinning gold.

🗺 The Campaign, the Book, and the Ledger

• Your First 90 Days — campaign mode: one story across every arena. You join a fictional Series A startup, and your real arena scores write the plot — lose the Gym negotiation and the account churns; get fooled in the Panel and the bad hire haunts Week 10. Replayable, saves locally, certificate at Day 90.
• The Professional Work Handbook — the library as a book: 11 chapters of craft (the Production-Ready tier in full) + the Anti-Pattern Almanac: 2,237 rules of professional judgment from all 466 skills. Printable (PDF), free, regenerated every release.
• The Reckoning — your prediction ledger: confidences, due dates, resurfacing, and a personal calibration curve with a Brier score. Also in the CLI: npx pm-claude-skills reckoning. When you say 80%, does it happen 80% of the time? Now you’ll know.
• 🔏 The chain of trust — security scan → sha256 content pinning in the registry → install lockfile + npx pm-claude-skills verify drift detection → npm provenance. Verifiable end to end, no trust in us required.

🌐 Infrastructure for the whole ecosystem

• pm-skills-tools — all 466 skills as agent tools: OpenAI function schemas, Vercel AI SDK adapters, pick()/search() runtime. npm i pm-skills-tools and your agent wields the library.
• The SkillSpec badge — any skills repo can wear its live-graded conformance level: ![SkillSpec](https://img.shields.io/endpoint?url=…/badge?repo=you/yours).
• The State of Agent Skills — the census of the public SKILL.md ecosystem (counts, conformance pyramid, security hits), regenerated from GitHub code search. The observatory, not just a participant.
• Every protocol — MCP (with zero-key sampling) · A2A · AGENTS.md · function calling · REST.
• The Apprentice — a ready-to-run Agent SDK agent grounded in your brain and your skills’ Quality Checks. Fork it.
• council (cross-vendor adversarial review) · migrate (convert prompt libraries into skills) · chief-of-staff hook (every session opens with your predictions due and latest verdicts).

📦 The ecosystem toolchain — beyond this library

• npx pm-claude-skills install — install skills from any public GitHub repo, security-scanned and SkillSpec-graded on the way in; flagged skills are never installed. The package manager for the whole skills ecosystem, with auditing as the value add.
• npx pm-claude-skills chain — run a whole recipe headless (chain --list): each skill feeds the next, and --deck/--doc finish with a real .pptx/.docx. Raw notes in, board-ready deck out, one command.
• npx pm-claude-skills init — the 60-second professional workspace: brain/, standing context, arena folders, CLAUDE.md wiring. Then doctor keeps it healthy.
• run_skill over MCP with zero API key — the MCP server executes skills via MCP sampling: the generation runs on your client’s model, no key needed by anyone.
• skillspec-check — the eslint for SKILL.md, as a standalone npm package + pre-commit hook: lint ANY repo’s skills against the standard (--min-level 2 as a CI gate).
• Boardroom doc review in CI — PRs touching docs get a CFO/CTO/CCO critique with a 🟢/🟡/🔴 Chair verdict as a PR comment. Documents get code review.
• 🧮 Skills that do math — cohort-curve-model, runway-monte-carlo, pricing-sensitivity-model: each ships a stdlib script that computes (curve fitting, 5,000-path simulation, survey crossings) and emits a real .xlsx with live formulas.

---

🧠 Skill Memory — set your context once, every skill uses it

---

🤖 Run a skill from a GitHub comment (ChatOps)

---

✅ Eval-verified quality — not just quantity

---

⚖️ How it compares

---

🚀 Quick Install (2 minutes)

---

🌍 Use It Anywhere — the AI Ecosystem

---

🔌 Works With — Cross-Tool Compatibility

---

🤖 Subagents & Slash Commands

---

🧩 MCP Server — Skills on Demand

---

⚙️ AI-Powered Tooling

---

🌐 Skill Playground — Try Any Skill in Your Browser

---

📦 Plugin Directory

---

🎬 See It in Action

---

🤖 Building Blocks for Agent Templates

---

📋 Changelog

---

📚 The Article Series

---

🏷️ Skill Tiers — Start With the Strongest

---

🗂️ All 451 Skills

---

❤️ Sponsor This Work

---

🌐 Community Skills — get listed, earn the badge

Built your own skills? List them in the Community Skills directory — a place to showcase skill repos and packs that follow the SKILL.md standard. It’s a one-row pull request, and once it’s merged you earn a badge to show off in your own repo:

[![Featured in PM Skills Community](https://mohitagw15856.github.io/pm-claude-skills/assets/community-badge.svg)](https://github.com/mohitagw15856/pm-claude-skills/blob/main/COMMUNITY-SKILLS.md)

Community listings live in their authors’ own repos and are community-maintained — not eval-scored or security-audited (that’s the curated library above). Want your skill in the curated library instead? See Contributing below.

---

🤝 Contributing — Add Your Skill

---

📦 All Plugin Bundles

---

🤖 Companion Repository — ChatGPT Custom GPTs

---

🔗 Related Projects

---

🛠️ Custom Skills for Your Team

---

📖 How Skills Work

---

⭐ Star Milestones

---