🧠 PM Skills — 454 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes

🧠 PM Skills — 454 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes

💛 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.454 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 (2,237-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. 454 skills · 65 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 whole repo on one poster — the 60-second start path, the six things no other skills library does (Boardroom, Firm, Gauntlet, X-ray, living artifacts, the Gym), install one-liners for every tool, and the infrastructure story. Built to print, share, or drop into a slide — with one link to start.

📥 Markdown · 🖼️ Download PNG · 📄 Download PDF · 🌐 Live poster — regenerate with PAGES=cheatsheet node web/docs-assets/shoot.mjs.

📖 Want the full walkthrough? The Practical Guide is a 15-page,example-driven manual — install → your first skill → worked examples (PRD, exec update, RICE,postmortem) → chaining recipes → the Brain → running anywhere → tips. Download the PDF →

🧠 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

These 454 skills aren't a random catalog — they cover the full arc of professional work, end to end. Wherever you are in the loop, there's a skill for it:

flowchart LR
    A(["🔍 Discover"]) --> B(["🎯 Decide"]) --> C(["🔨 Build"]) --> D(["🚀 Ship"]) --> E(["📊 Measure"]) --> F(["📣 Communicate"])
    F -. "feeds the next discovery" .-> A
    classDef s fill:#1d288b,stroke:#d97757,color:#e7ebf0;
    class A,B,C,D,E,F s;

New here? Start with the top-tier skills, or jump straight to all 451 skills grouped by profession.

🧩 Workflow Recipes — chain skills into one flow

Individual skills are great. Chaining them is the superpower. A recipe runs several skills in sequence and passes each output forward as context — so a fuzzy idea comes out the other end as a finished, joined-up set of artifacts. No other skills library chains across professions like this.

/ship-a-feature  "a referral program for B2B users"

  ambiguity-resolver → prd-template → rice-prioritisation → roadmap-narrative → go-to-market
   frame the problem    spec it        prioritise it        place on roadmap     launch plan
        └──────────────── each stage's output feeds the next ────────────────┘

→ Full detail and how to add your own in WORKFLOWS.md. Recipes run as slash commands in Claude Code, or over MCP via the get_workflow tool.

Got a coding question? Just ❓ Ask — an error, a regex, a git mess, a dependency conflict, "what does this code do?" — and the right developer skill answers instantly (like StackOverflow, but the answer's already written), with a one-click path to the community Q&A for a human follow-up.

Or build your own visually. The Workflow Canvas lets you drag any skills into a custom chain and run it in the browser — each step's output feeds the next. Like n8n, but for professional thinking. Don't know which skills to use? The ✨ Auto-Agent takes a plain-English goal, plans which skills to chain, and runs them for you — each step feeding the next:

🏛️ 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 — 454 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 454 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 454 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 <owner/repo> — 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 <workflow> — 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

Generic output is the #1 complaint with AI. Skill Memory fixes it: tell the skills who you are once, and every skill and recipe produces output already tuned to your product, audience, and voice — no re-typing.

• In Claude Code: run /setup-context (or copy templates/pm-context.example.md → pm-context.md). Skills read it as standing context.
• In the Playground: fill the 🧠 Your context box — it's saved in your browser and prepended to every run.

Without context:  "write an exec update" → generic, you rewrite it
With context:      "write an exec update" → your voice, your metrics,
                    your audience — shippable on the first try

🤖 Run a skill from a GitHub comment (ChatOps)

This repo ships a Skill Bot: comment on any issue or PR and a skill runs and replies inline.

/skill executive-update
Audience: CEO. Period: Q2. Shipped onboarding redesign; activation up; hiring behind plan.

The bot runs the skill and posts the result as a reply. /skill list shows usage. It's gated to repo collaborators (so random commenters can't trigger paid API calls) and needs an ANTHROPIC_API_KEY secret. Copy the workflow into your own repo to give your whole team skill-powered ChatOps.

✅ Eval-verified quality — not just quantity

Grounded in canonical frameworks. These aren't invented prompts — each skill encodes a proven method and cites it: RICE (Intercom), Jobs-to-be-Done (Christensen), Continuous Discovery (Teresa Torres), Porter's Five Forces, the Pyramid Principle (Minto), Google SRE, WCAG, Obviously Awesome (April Dunford), and more. The source shows as a "📚 Based on" line on every skill page and in the Playground.

And measured, not just claimed. An eval harness runs each skill against a held-out test case, then an LLM judge (Opus 4.8) rates the output on four dimensions — structure, completeness, usefulness, grounding — averaged across two models. 208 skills are eval-scored today (and climbing); the rest are reviewed against the authoring standard. PRs are auto-checked for structure; eval scoring is run deliberately (after merge) via the Evaluate selected bundles Action and published to the leaderboard.

The qualitative half — real time saved. Scores measure quality; case studies measure outcomes. See the kind of before → after a skill delivers (PRD: ~2 days → ~25 min), and add your own 2-minute ROI story — we'll feature it.

The loop actually catches bad skills. A recent run flagged three skills scoring ~2/5 because they asked for missing inputs instead of delivering. We added a "work from a brief" rule, re-ran, and they jumped to 4.75/5:

That's not luck — it's a self-improving pipeline (/improve) that critiques and rewrites a skill, keeping the change only if the score goes up. See the 🏆 leaderboard for live scores; run it yourself with node evals/run-evals.mjs.

See the difference for yourself. The Playground's Compare toggle runs the same inputs with and without the skill, side by side — structured, shippable output on the left; generic mush on the right:

Already have a draft? Flip on 📝 Critique mode in the Playground — or use the standalone Grade your work tool — to paste an existing PRD/roadmap/update and get a rubric score, ranked gaps, and a redline graded against the skill's framework. Before you ship, run /red-team to stress-test the plan against a room of hostile expert personas.

This whole thing is an open, reproducible benchmark for AI professional work: every contributed skill is auto-checked for structure on its PR, then eval-scored on the rubric after merge. The easiest way to add one is Skill Studio — describe a skill in your browser, generate a compliant SKILL.md, and open a pull request in one click (or use the form →).

⚖️ How it compares

Most skill repos are a folder of prompts. This one is a system — measured, composable, and usable in the browser:

🚀 Quick Install (2 minutes)

Not sure where to start? Pick by what you want:

• Just try it (0 install): open the live Playground and run any skill.
• Use it in Claude Code: npx pm-claude-skills add --agent claude (or the /plugin route below).
• Have it in every session: add the MCP server (one line, below).

⚠️ You don't need npm install pm-claude-skills — it's a CLI, not a library, so there's nothing to import. Use npx pm-claude-skills … (it always runs the latest). npm install just downloads it and does nothing on its own.

With the skills CLI (the open agent-skills installer that works across Claude Code, Cursor, Codex, OpenCode & 60+ agents) — pick from all 451 interactively:

npx skills add mohitagw15856/pm-claude-skills            # browse & pick (auto-detects your agent)
npx skills add mohitagw15856/pm-claude-skills --list     # just preview the catalog
npx skills add mohitagw15856/pm-claude-skills --skill prd-template   # grab one
npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install all 451

Or our own installer — via the pm-claude-skills npm package (Windows/macOS/Linux, needs Node), which also installs subagents, slash commands & cross-tool exports:

npx pm-claude-skills add --agent claude     # or: codex · cursor · hermes · openclaw

Or one-line MCP — make all 451 skills + 5 workflow recipes available in every session of any MCP client (Claude Code, Claude Desktop, Cursor, Windsurf), no per-file install:

claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Your assistant can then "search the skills for churn" or "run the ship-a-feature workflow" on demand. Details: mcp/README.md.

In Claude Cowork — open the plugin browser → Add from GitHub → enter mohitagw15856/pm-claude-skills, then add the bundles you want. No CLI needed.

In Claude Code — it's in the official Anthropic plugin directory, so you can browse to it in the /plugin marketplace, or add it directly:

/plugin marketplace add mohitagw15856/pm-claude-skills

Or install by profession:

claude plugin install pm-essentials@pm-claude-skills # Core PM + Word tracked changes

claude plugin install pm-delivery@pm-claude-skills # Delivery + PowerPoint auditor

claude plugin install pm-engineering@pm-claude-skills # Engineering (35 skills) 🆕

claude plugin install pm-cs@pm-claude-skills # Customer Success 🆕

claude plugin install pm-data@pm-claude-skills # Data + chart data extractor

claude plugin install pm-legal@pm-claude-skills # Legal

claude plugin install pm-finance@pm-claude-skills # Finance

claude plugin install pm-hr@pm-claude-skills # HR

claude plugin install pm-sales@pm-claude-skills # Sales

claude plugin install pm-operations@pm-claude-skills # Operations

claude plugin install pm-research@pm-claude-skills # Research & Healthcare

claude plugin install pm-cross@pm-claude-skills # Cross-profession

claude plugin install pm-figma@pm-claude-skills # Figma

claude plugin install pm-social@pm-claude-skills # Social Media 🆕

claude plugin install pm-writers@pm-claude-skills # Writers & Content Creators 🆕

Or clone and symlink for auto-updates:

git clone https://github.com/mohitagw15856/pm-claude-skills.git ~/pm-claude-skillsmkdir -p ~/.claude/skillsln -s ~/pm-claude-skills/skills/* ~/.claude/skills/

🌍 Use It Anywhere — the AI Ecosystem

The same 451 skills reach you through every channel — pick whatever fits your stack:

208 of 451 skills are eval-scored, averaging 4.8/5 — see the leaderboard.

🧠 Give your skills memory: the Professional Brain is a local markdown folder skills read, write back to, and act on. It's a folder + one file to start — 5-minute Quickstart.

🔌 Works With — Cross-Tool Compatibility

These skills were built for Claude Code, but they aren't locked to it. Each SKILL.md istwo portable parts: a small frontmatter block (name + description) and amarkdown body that is just a well-structured set of instructions and output templates.The body is plain English — so it works anywhere a capable model reads instructions.

There are two kinds of support. Native SKILL.md agents read the file as-is andauto-discover skills from the description frontmatter. Other tools take the markdownbody as a system prompt — for those we ship ready-made exports.

In your editor (VS Code / Cursor): the vscode-extension/ brings all 451 skills into the Command Palette — search and insert a skill as context for Copilot/Cursor chat, copy it, or open it in the Playground.

What's verified vs. what varies: the skill bodies — the frameworks, rubrics, andoutput templates that do the actual work — are model-agnostic and have been used acrossClaude and other chat LLMs. Native SKILL.md agents (Claude Code, Hermes) also get theconvenience layer: automatic skill discovery from the description. On chat LLMs you pastethe body in manually and lose only the auto-triggering, not the substance.

Ready-to-use exports

You don't have to strip frontmatter by hand. Every skill is exported to platform-readyfiles under exports/, generated from the same source so nothing ismaintained twice:

• ChatGPT — copy any exports/chatgpt/<bundle>/<skill>/SYSTEM_PROMPT.md straight into a Custom GPT's instructions.
• Google Gemini — copy any exports/gemini/<bundle>/<skill>/GEM_INSTRUCTIONS.md into a Gem's instructions.
• Cursor (.mdc) · Windsurf (.md) · Aider (.md) — generated rule/conventions files in exports/cursor/, exports/windsurf/, exports/aider/ (or use the installers below).

One-command install for coding agents

Cross-platform (Windows, macOS, Linux) — recommended. One Node command installs every skill where your agent discovers them. No git, no bash:

npx pm-claude-skills add --agent claude     # skills + subagents + commands → ~/.claude/
npx pm-claude-skills add --agent codex      # OpenAI Codex (or: hermes · openclaw)
npx pm-claude-skills add --agent cursor     # .mdc rules → ./.cursor/rules
npx pm-claude-skills add --agent windsurf   # .md rules → ./.windsurf/rules
npx pm-claude-skills add --agent aider      # conventions → load with: aider --read
npx pm-claude-skills search board           # find skills by name/description
npx pm-claude-skills search launch --json   # machine-readable (Raycast/Alfred/scripts)
npx pm-claude-skills list                   # all supported agents + default paths

Add --link (symlink), --target <path>, or --dry-run to any add.

Shell one-liners (macOS / Linux / Git Bash / WSL — not PowerShell):

bash <(curl -fsSL https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/scripts/codex-install.sh)
bash <(curl -fsSL https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/scripts/openclaw-install.sh)
bash <(curl -fsSL https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/scripts/cursor-install.sh)

Windows / PowerShell: use the npx command above (the bash <(curl …) form is a Unix idiom and won't run in PowerShell).

Already cloned? ./scripts/install.sh --agent <name> (or python3 scripts/sync-hermes-skills.py for Hermes) does the same from your checkout.

The skill body in skills/<name>/SKILL.md is the single source of truth. Regenerate thechat-LLM / Cursor exports (or add a new platform — it's a few lines in the PLATFORMS registry) with:

node scripts/build-exports.mjs            # regenerate all platform exports
node scripts/build-exports.mjs --check    # CI: fail if exports are stale

Prefer a hand-curated ChatGPT collection? There's also a companion Custom GPT library built from the same frameworks.

🤖 Subagents & Slash Commands

It's not just skills. The library also ships Claude Code subagents and slash commands built on top of the strongest skills, so common workflows are one delegation or one command away.

Subagents (agents/) — focused personas Claude delegates to automatically by description:

Slash commands (commands/) — run a skill on whatever you pass:

/prd · /rice · /sprint-plan · /health-scorecard · /retro · /exec-summary

Personas (output-styles/) — Claude Code output styles that change the assistant's whole voice and default skill loadout. Switch with /output-style:

Startup CTO · Growth Marketer · Solo Founder · Product Leader

Install everything for Claude Code in one go (skills + subagents + commands + personas):

npx pm-claude-skills add --agent claude   # ~/.claude/{skills,agents,commands,output-styles}

Commands whose skill ships a Python helper (RICE, sprint capacity, customer health) run it to compute results, not estimate them. To string these together, see the orchestration patterns (skill chains & multi-agent handoffs).

🧩 MCP Server — Skills on Demand

For MCP clients (Claude Desktop, Cline, …), there's a zero-dependency MCP server so your assistant searches and pulls skills on demand instead of installing 172 files. It exposes three tools — list_skills, search_skills, get_skill — over stdio (no network, nothing leaves your machine).

{
  "mcpServers": {
    "pm-claude-skills": { "command": "npx", "args": ["-y", "pm-claude-skills-mcp"] }
  }
}

Then ask: "search the skills for customer churn, then apply the best one to my account." Full setup in mcp/README.md.

🔌 Skills that act on your data. Run pm-skills alongside a data server (filesystem, GitHub, Postgres, Drive…) and a skill works on your real sources: "draft the PRD from GitHub issue #123," "run churn-analysis on exports/q2.csv," "open an issue per product-launch-checklist item." Copy-paste configs + worked recipes in connectors/.

pm-skills needs no auth. To connect GitHub, Slack, Notion, etc., you add that provider's MCP server with its own token/OAuth once in your client — then every skill can use it. (filesystem = a folder you grant; GitHub = a PAT; Slack/Notion = OAuth.)

⚙️ AI-Powered Tooling

Three ways to put the library to work beyond installing files:

🤖 Run a skill in your CI — GitHub Action. Auto-write PR descriptions, changelogs, release notes, or run a code-review checklist on every PR:

- uses: mohitagw15856/pm-claude-skills/action@main
  with:
    skill: pr-description-writer
    input: ${{ steps.diff.outputs.text }}
    api_key: ${{ secrets.ANTHROPIC_API_KEY }}

🏗️ Turn your docs into a skill — generate. Point it at a URL or file and it writes a SKILL.md that follows the authoring standard:

ANTHROPIC_API_KEY=sk-ant-… npx pm-claude-skills generate --from ./team-process.md

🏆 Skill Leaderboard — evals. An LLM-as-judge harness scores each skill across Claude models on structure, completeness, usefulness, and grounding. View the leaderboard →

Score the whole library, cheaply. npm run eval:gen-cases writes a representative input for all 451 skills (curated cases kept verbatim; the rest auto-generated), then npm run eval:all runs the full pass on Haiku for ~$2 total. The weakest scorers can then be auto-rewritten with npm run improve -- <skill> (/improve), which keeps a change only if the score goes up.

🌐 Skill Playground — Try Any Skill in Your Browser

▶ Live: mohitagw15856.github.io/pm-claude-skills · 📚 Browse the full skill catalog

Don't want to install anything yet? Run any of these skills from a zero-backend web app using your own Claude, OpenAI, or Gemini key. Pick a provider, pick a skill, fill in the auto-generated form, and the result streams back live. Your key is stored only in your browser (localStorage) and sent directly to the provider you chose — nothing touches a server we own.

Run it locally:

git clone https://github.com/mohitagw15856/pm-claude-skills.git
cd pm-claude-skills
node web/build-skills.mjs               # generate the skill index (skills.json)
cd web && python3 -m http.server 8000   # serve over HTTP (not file://)
# open http://localhost:8000 and paste a key from console.anthropic.com

It's fully static — deploy the web/ folder to GitHub Pages, Netlify, or Vercel with no environment variables. Full details in web/README.md.

📦 Plugin Directory

Not sure which plugin to install? Here's what each one covers:

🎬 See It in Action

Debugging Log Analyser — paste a stack trace or error log, get a structured root cause diagnosis with probable cause, affected code path, a specific fix, and next debugging steps.

PR Description Writer — share your diff or commit list, get a reviewer-friendly PR description with summary, changes made, testing steps, and reviewer notes.

Sprint Planning Skill — paste your sprint goals and backlog items, get a complete structured sprint plan with capacity, commitments, risks, and a day-one kickoff agenda.

📹 Drop a demo in Discussions and we'll feature it here.

🤖 Building Blocks for Agent Templates

On May 5, 2026, Anthropic released their first agent templates — pre-packaged Claude agents that combine skills, connectors, and subagents into ready-to-run workflows for financial services.

This library is the largest open-source collection of professional skills available — covering 20 professions beyond financial services. The 451 skills here are the building blocks for agent templates outside of finance.

What is an agent template?

An agent template packages three things into one runnable workflow:

A skill alone gives Claude a structured output format. An agent template gives Claude a complete workflow — pulling data, running specialised analysis, producing the output, and routing it where it needs to go.

How to use this library to build your own agent template

Pick a recurring workflow on your team. Identify which existing skills cover the structured outputs that workflow needs. Add the connectors that let Claude reach the data. Add subagents for the analytical sub-tasks. That's the template.

Examples of agent templates this library supports:

Available agent templates

The pm-claude-skills library now includes four working agent templates, each built from existing skills in this library combined with subagents and connectors. All four follow the architecture Anthropic introduced for financial services agent templates on May 5, 2026.

Each template includes:

• Working orchestration script
• Two or more focused subagents
• Connector configurations with documented setup
• Working examples (input + output)
• Smoke test for verifying installations

How to install a template

All templates are part of the main library — installing the marketplace gives you all four.

/plugin marketplace add mohitagw15856/pm-claude-skills

Then navigate to the template you want and follow its README:

cd templates/pm-sprint-agent # or pm-discovery-agent, etc.cat README.md # full setup instructions

Building your own template

If you want to build a template for a workflow not covered above — Legal Contract Review, Sales Pursuit, Finance Board Pack, HR Onboarding, Marketing Campaign — see the template contribution guide.

The pattern is consistent: pick a multi-step workflow, identify which existing skills cover the structured outputs, add connectors for data access, and define subagents for specialised analysis. The four templates above are reference implementations.

It combines four skills, two connectors, and two subagents into a single workflow that handles end-to-end sprint planning.

Documentation, working orchestration script, and example outputs are included in the template folder.

More templates will follow. If you want to contribute one, see the template contribution guide.

📋 Changelog

Latest: v45.0.0 — the spectacle release: ⚔️ Duels, 🎓 the verifiable Charter, and the library in 3D (Galaxy 3D, the collapsing Tower of Claims, the Stage, holo cards, the Trophy Forge, Skill City, the orrery) — plus the first official SkillBench results and the first evolution-loop run (454 skills, 65 bundles) · v44: Campaign mode, the Handbook, the Reckoning, the ecosystem package manager, zero-key MCP sampling, pm-skills-tools, the badge & the census · v43: the workspace bridge, replay links & bench packs, The Panel, The Academy, Wrapped, the evolution loop & pm-method · v42: depth on all Production-Ready skills, arena voices, Firm calibration & the web-tests safety net · v41, modern skills: pm-agentnative + pm-aiwork (15 skills for the agent era), Galaxy cosmic events, 🎓 certificates & MCP pairings · v40: The Firm · v39, three waves: SkillBench, the community registry, the Interview Gauntlet, living artifacts, Document X-ray, The Gym, pm-vision, i18n, HF publishing, CI recipes & the Galaxy Sky tour. 454 skills across 65 bundles, 25 professions. Every tagged release has complete notes on the Releases page.

Full Keep a Changelog-format history — every release back to the start — is in CHANGELOG.md.

📚 The Article Series

This repo was built alongside a published 16-part article series on Medium.

🏷️ Skill Tiers — Start With the Strongest

A 451-skill library doesn't have 451 equally-mature skills, and pretending otherwisewastes your time. Skills are tiered honestly so you can start with the best work:

• 🟢 Production-Ready (50) — battle-tested, stable output, used in real work. Includes the three skills with computed Python helpers (sprint planning, RICE, customer health). Start here.
• 🔵 Stable — solid, reliable, well-structured; the default for most of the library.
• 🟡 Experimental — newer or dependent on an external tool/API/scrape (Gemini, Gmail, browser automation, social scraping). Useful, but more setup and more moving parts.

👉 Full breakdown: TIERS.md — every Production-Ready and Experimental skill listed by name.

If you're new, install pm-essentials and try a couple of Production-Ready skills before going wide.

🗂️ All 451 Skills

Every skill, grouped by profession. Browse the full per-skill catalog → SKILLS.md · searchable live catalog · run any skill in the browser

Full per-skill detail (folder paths, descriptions, "🆕" markers) lives in SKILLS.md — auto-generated, always current.

❤️ Sponsor This Work

Building and maintaining 454 skills across 65 bundles takes real time — testing skills against new model releases, building new ones from community requests, writing the article series, and keeping documentation current.

If these skills save you time at work — or you're a company that wants your logo in front of the PMs, engineers, and operators who use them daily — become a sponsor → (or ☕ buy me a coffee).

Full details and where the money goes: SPONSORS.md.

Our sponsors: be the first — your logo goes right here.

🌐 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-rowpull 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 — noteval-scored or security-audited (that's the curated library above). Wantyour skill in the curated library instead? See Contributing below.

🤝 Contributing — Add Your Skill

This is an open-source community library. If you've built a skill that saves you time, share it here.

Two ways to share: contribute a skill into the curated library (eval-scored, in the playground/MCP/exports) via the quality-gated flow below — or, if you'd rather keep it in your own repo, list it in Community Skills with a one-row PR and earn a "Featured in PM Skills Community" badge for your repo (community-maintained, not eval-scored).

New here? See the Roadmap & good first issues for starter tasks. Found a bug? Open a bug report →.

How to contribute:

1. Fork this repo
2. Scaffold a skill that already passes validation: npm run new-skill -- --name your-skill-name(or copy the template below into skills/your-skill-name/SKILL.md)
3. Fill in the sections, then check it: npm run skillcheck
4. Raise a pull request with a short description of what the skill does and why you built it

Every PR is gated by SkillCheck (structure — node scripts/skillcheck.mjs) and the Skill Security Auditor (safety — node scripts/skill-audit.mjs, which flags prompt-injection / exfiltration / unsafe code). Both must pass.

SKILL.md template:

name: your-skill-namedescription: "One sentence. Use when [trigger condition]. Produces [output description]."

Skill Title

[Instructions for Claude to follow when this skill is invoked]

What makes a good skill:

• Solves a recurring professional workflow (not a one-off task)
• Has a clear trigger description so Claude knows when to activate it
• Produces consistent, structured output
• Works without needing extensive setup or context

Before you submit: read the Skill Authoring Standard — it documents the exact section structure, frontmatter rules, and quality bar every skill in this library follows (including optional stdlib-only helper scripts).

Skills wishlist (most requested — up for grabs):

Have a skill idea? Add it to SKILL_REQUEST.md, open an issue, or raise it in Discussions. Most-voted requests get built first.

Contributors get credited in this README and in the article series. 🙌

📦 All Plugin Bundles

Install the whole library or just the bundles you need:

Install everything

/plugin marketplace add mohitagw15856/pm-claude-skills

Install by profession

claude plugin install pm-essentials@pm-claude-skills

claude plugin install pm-discovery@pm-claude-skills

claude plugin install pm-planning@pm-claude-skills

claude plugin install pm-delivery@pm-claude-skills

claude plugin install pm-analytics@pm-claude-skills

claude plugin install pm-strategy@pm-claude-skills

claude plugin install pm-advanced@pm-claude-skills

claude plugin install pm-rituals@pm-claude-skills

claude plugin install pm-gtm@pm-claude-skills

claude plugin install pm-engineering@pm-claude-skills # Engineering (35 skills)

claude plugin install pm-cs@pm-claude-skills # Customer Success

claude plugin install pm-data@pm-claude-skills

claude plugin install pm-people@pm-claude-skills

claude plugin install pm-design@pm-claude-skills

claude plugin install pm-business@pm-claude-skills

claude plugin install pm-legal@pm-claude-skills

claude plugin install pm-finance@pm-claude-skills

claude plugin install pm-hr@pm-claude-skills

claude plugin install pm-sales@pm-claude-skills

claude plugin install pm-operations@pm-claude-skills

claude plugin install pm-research@pm-claude-skills

claude plugin install pm-cross@pm-claude-skills

claude plugin install pm-figma@pm-claude-skills

claude plugin install pm-social@pm-claude-skills # Social Media 🆕

claude plugin install pm-writers@pm-claude-skills # Writers & Content Creators 🆕

🤖 Companion Repository — ChatGPT Custom GPTs

If you use ChatGPT instead of Claude Code, there's a companion repo with the same professional frameworks built as Custom GPT system prompts:

professional-gpt-library — 10 starter GPTs across 8 professions, MIT licence.

Read the full breakdown: Part 12 — I Built the Same Skills Library for ChatGPT

🔗 Related Projects

Claude Skills is a fast-growing open ecosystem. If this library doesn't have what youneed, these community projects are worth a look — and if you maintain one of the listsbelow, a reciprocal link is always welcome. 🙌

Other skill libraries

• alirezarezvani/claude-skills — a large engineering-leaning library (300+ skills, agents, and commands) with explicit multi-tool support across Claude Code, Codex, Gemini CLI, Cursor, and more.

Curated "awesome" lists (great for discovery)

• hesreallyhim/awesome-claude-code — the broad list of skills, hooks, slash-commands, and plugins for Claude Code.
• travisvn/awesome-claude-skills — curated Claude Skills, resources, and tools.
• karanb192/awesome-claude-skills — verified skills for Claude Code, Claude.ai, and the API.
• ComposioHQ/awesome-claude-skills — skills and tools for customizing Claude workflows.

From this author

• ContentGoldMine — the automation layer of the creator stack. This library teaches the craft (pm-creator: hooks, repurposing, short-form, newsletters); ContentGoldMine runs it end-to-end — one URL → 5 platform formats, viral-scored, with carousel images and auto-publishing to X/LinkedIn. See the cross-tool recipe.
• professional-gpt-library — the same frameworks rebuilt as ChatGPT Custom GPTs.

Maintain a Claude Skills project and want to be listed here? Open a PR or an issue.

🛠️ Custom Skills for Your Team

The 155 skills in this library are built for general professional workflows. But the most powerful version of Claude Skills is one built specifically for your team — your templates, your terminology, your processes, your quality standards.

What custom skills look like in practice:

• A law firm's contract review skill trained on their specific clause library and risk tolerance
• A SaaS company's sprint brief skill that knows their engineering conventions and definition of done
• A finance team's board pack skill that follows their exact narrative structure and slide format
• An HR team's job description skill that reflects their values language and includes their specific benefits

The difference between a generic skill and one built for your context is significant. Generic skills eliminate the blank page. Custom skills eliminate the rework.

If you want skills built for your team's specific workflows — get in touch.

Include a brief description of your team, the workflows you want to automate, and the tools you use. I'll come back to you within 48 hours.

📖 How Skills Work

Skills are markdown files that Claude reads dynamically. When you describe a task, Claude scans available skill descriptions (~100 tokens) and loads the full skill only when relevant. This means:

• Skills are efficient — they only use tokens when triggered
• Multiple skills can coexist without slowing Claude down
• Personal skills (~/.claude/skills/) work across all your projects
• Plugin skills install via the Claude Code marketplace with one command

Learn more: Anthropic's Skills documentation

⭐ Star Milestones

Stars unlock the next wave of skills and features. We've hit every milestone so far — here's the track record, and what's next:

⭐ Star this repo to unlock the next milestone → — we're at 2,000⭐ next.

Want a specific skill built? Vote or request in SKILL_REQUEST.md.

📈 Star History

Built and maintained by Mohit Aggarwal | Product Notes publication | 💖 Sponsor my work