_{English · 简体中文 · 繁體中文 · 한국어 · 日本語 · Español · Português (BR)}

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

One request to your AI, one finished deliverable back: the PRD, the stakeholder update and the decision call, at a senior product manager's standard.

Try it right now. Install below, then paste this into your assistant:

Here are my discovery notes from six customer calls: [paste your notes].
Turn them into a one-page PRD, a risk register with owners, and a
stakeholder update I can send to leadership today.

Your assistant loads user-interview-synthesis, prd-template and stakeholder-update and returns the three documents, not advice about writing them. Not a PM? The same library covers engineers, job seekers, students, founders and 中文用户, below.

▶ Playground · ⚡ Install · 📚 All skills · 📘 Worked examples · 🏆 Best AI for your job · ❓ How do I…? · 🖼 Showcase · 🌳 Tech tree · 🇨🇳 简体中文 · 繁體中文 · 한국어 · 🆕 Changelog

Your landlord kept your deposit. You got laid off on a Tuesday. Your boss wants the PRD by Friday. Generic AI is a very confident intern. PM Skills is the senior colleague's notes: 1285 of them, one markdown file each. (PM stands for Professional. Yes, we get asked.)

PM Skills is an open-source library of 1285 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.

⚡ Install in 30 seconds

npx pm-claude-skills add                                            # any tool: Cursor, Codex, Windsurf, Cline, Zed…
# In Claude Code:  /plugin → search pm-skills   (official Anthropic directory)
npx --registry=https://registry.npmmirror.com pm-claude-skills add  # 中国大陆镜像

Then just say what you need: "Decode this job ad and tell me where I am weak." Nothing here can break your setup: a skill is a markdown file your AI reads; installing copies text files, uninstalling deletes them. Read one first. Per-tool instructions: docs/installation.md · ChatGPT and Gemini: copy from exports/ · MCP: claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

🥊 The demo

More to see: the Showcase gallery has the Playground, the tech tree, Galaxy 3D and Skill City.

🧭 How it works

A skill is one plain-markdown SKILL.md file: a description that tells your assistant when to load it, plus the working framework, output template and quality checks it follows. The installer (npx pm-claude-skills add) copies the skills you choose into the config folder of the tool you use, so they load only when a request matches. The MCP server serves skills on demand to any MCP client instead, and the same package exposes a read-only REST API for n8n, Make and other automations. No runtime, no account, nothing resident: uninstalling deletes text files.

🧑‍🤝‍🧑 Pick your path

_{None of these you? docs/start has all six paths, a map of every bundle by what you want to do, a four-question quiz and a five-level quest log. Mid-something big? Skill Packs start from your moment: a new baby, a layoff, a move, a loss.}

🗺 What you can do

The product-management core first, then the bundles everyone borrows. Each row is a real bundle in plugins/.

Install any bundle: /plugin install pm-decoders@pm-claude-skills, or npx pm-claude-skills add --bundle pm-decoders. All 152 bundles with every skill and install command: docs/catalogue.md · every skill in one page: SKILLS.md · chain them: WORKFLOWS.md

🇨🇳 中文用户

用中文提问即可。 十三个面向中文用户的技能包：周报述职（pm-china-work）、考公考研（pm-china-exams）、劳动合同与补偿（pm-china-life）、外贸、制造业、合规、出海等，73 个技能有简体中文版、27 个有繁体中文版。 国内安装：npx --registry=https://registry.npmmirror.com pm-claude-skills add，镜像与离线包见 docs/CHINA.md。 试着说："帮我写周报" · "公司要裁我，能拿多少补偿？" · "下个月公务员面试，帮我模拟一轮。" 完整中文说明（技能包全表、常见问题、国内工具与本地模型、海报与分享卡）：简体中文 README · 港台用户：繁體中文 README

🆕 What's new

Everything older: CHANGELOG.md · the write-ups: docs/WHATS-NEW.md · most-wanted skills and votes: the tech tree

✅ Trust and quality

An honest summary of what is checked, measured and still unreviewed, computed from the repo on every change:

• Checked on every change, in CI: structure (SkillCheck, all 1,285 skills at the L3 gate), a security audit, a near-duplicate check, a count-drift check, translation parity (178 translations in 10 languages), and a prompt-injection suite of 15 hostile documents. A change that fails any of them does not merge.
• Eval cases: 389 of the 1,285 skills carry eval cases (evals/cases.json), and 140 have a worked example in examples/.
• Measured scores: 28 skills have blind-judged scores on the leaderboard (average 4.4/5 across the models tested); the benchmark report publishes the negative findings too. Everything unscored is unscored, not assumed good.
• Human review: of the 154 skills rated high-stakes in risk tiers, 0 have a current review by a qualified professional. The expert-review programme and its ranked queue exist for exactly this; if you hold a relevant credential, reviewing one skill is the most valuable contribution available.
• Reported savings: none recorded yet. Tell us what a skill saved you: hours and money only, added up in public on the Wall of Wins.

• It rewrites itself, in public: the weakest skills are periodically rewritten by a model and kept only if a judge scores the rewrite higher; every attempt, including the losses, is in the evolution log.
• Honesty rules baked in: decoders end with a not-advice line (the severity scale), calculators name what they do not model, simulators debrief out of character. PM Skills is not a substitute for a professional.

Privacy, stated plainly: everything installable runs locally. Skills are inert markdown on your machine; the CLI, the exports and the local MCP server send nothing anywhere, and telemetry is off unless you set PM_SKILLS_TELEMETRY=1 (skill name only, never content). The two things that do leave your machine are your prompts to whichever model provider you chose, and requests to the hosted playground or hosted MCP if you opt to use them. Full statements: docs/TELEMETRY.md · report a vulnerability: SECURITY.md · licence: MIT. Verify a release: npx pm-claude-skills verify --release (signed SBOM, Sigstore provenance).

🙌 Community

• Show and Tell: share what a skill produced, including what it got wrong: open a Show and Tell. The best entries become showcases.
• Vote on what gets built next: the tech tree ranks open skill requests by 👍; the top three are in research.
• Roadmap: confirmed direction in ROADMAP.md, the live signals behind it in docs/roadmap.md.
• Chat: TODO, a Discord or GitHub Discussions link goes here once the maintainer enables one; until then, issues are the front door.

🤝 Contributing

Add a skill by PR (the standard, CONTRIBUTING), request one and watch it appear on the tech tree, or claim a good first translation. 中文贡献者：Gitee Issue 也可以。

Contributors

_{Credits follow the all-contributors spec (.all-contributorsrc). Contributed and not listed? Open a pull request running node scripts/build-contributors.mjs --add <your-login> <type>, or ask in an issue. Translators: pick a skill from the claim board.}

Star history

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.

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

---

Built by Mohit with Claude. 1285 skills · 152 bundles · 35 professions · every commit gated. The long version lives in the Showcase.