Pm Claude Skills

_{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 astakeholder 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.

[PM Skills: the senior colleague's notes for any AI assistant. A request in plain words loads the right skill: a deposit dispute, a PRD, a Chinese weekly report, a Korean tax settlement.]

[Live numbers: skills, bundles, GitHub stars, weekly npm downloads and translated skills, refreshed daily]

▶ 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

[Stars] [Version] [npm] [In the official Anthropic plugin directory] [Listed in awesome-claude-skills] [Open in GitHub Codespaces] [SkillCheck] [SkillSpec conformance level, graded live] [License]

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: 1314 of them, one markdown file each. (PM stands for Professional. Yes, we get asked.)

PM Skills is an open-source library of 1314 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

🔄 Keep it updated

Skills improve every week. Whichever way you installed, updating is one step.

Stuck? The FAQ answers the common questions in English, 简体中文, 繁體中文, 日本語, 한국어, Español and Português.

🌅 Claude Duet, OpenAI Dots and other proactive agents

PM Skills works with Claude Duet, Anthropic's proactive agent. Duet uses the skills in your Claude account, so every skill here can run inside it. Agents that work while you're away fail in new ways: briefs that pad, uncited claims, acting instead of drafting, saying "done" about a draft. So 21 Duet-ready skills are built for unattended use. They keep briefs short and cited, draft instead of sending, and always ask before anything is sent, posted, paid, signed or deleted.

[How PM Skills works inside Claude Duet: your apps are checked every few hours, a Duet-ready skill turns what it finds into a short cited brief and drafts, and anything outward waits at an approval gate for your yes.]

[Set up your always-on agent in five steps: audit, standing orders, approval policy, brief and alerts, kill switch; then install with Add to Claude, a starter pack or the whole bundle.]

_{The five skills: prepare-for-duet · standing-orders · approval-policy-designer · morning-brief-designer and interrupt-rules · agent-kill-switch-plan}

Watchers for a small business: cash-watch, payroll-eve-check, signature-pipeline-watch, crm-hygiene-sweep and store-watch. They cover Stripe, Xero, QuickBooks, Gusto, DocuSign, HubSpot and Shopify. For teams: shared-agent-charter, for a Dot or a shared agent in Slack or Teams.

[Illustration with invented data: the morning brief the five watchers would give a small candle shop, with what needs you, what waits on others, what to watch, and two planted scams reported rather than obeyed.]

Get started

• Into Claude and Duet: press ⬇ Add to Claude on any skill's page, then upload the ZIP in claude.ai (Settings, Skills, Upload skill).
• A starter pack of 3 or 4 skills (founder, freelancer, shop owner, team lead, business ops) on the Duet page, or npx pm-claude-skills add --agent claude --skills standing-orders,cash-watch,store-watch.
• The whole bundle: npx pm-claude-skills add --bundle pm-duet.

Test it safely: the injection drill has 12 planted instructions to check whether your agent reports or obeys them. The fake-apps sandbox gives invented Gmail, Stripe and Shopify data where every send or payment is refused and logged.

Honest status: every one of these skills is designed for Duet. None has been tested on Duet yet, because it's a waitlisted research preview. File a Tested on Duet report and a skill moves up a tier, with your name on it. They're written to work with Dots and Muse too: see how the three compare.

🥊 The demo

[Animated before and after: the same request answered by a generic AI and by a skill. A lease gets vague advice on the left and ranked clauses with real money on the right; a PRD request gets platitudes versus a problem, metrics and user stories; a Chinese weekly report gets filler versus results, risks and a dated plan.]

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

🧭 How it works

[How a skill turns a request into a finished document: you ask in plain words, your AI picks the matching skill by its description, follows the skill file (framework, template, quality checks) and returns the finished document. Skills reach your AI through the installer, the MCP server or the REST API.]

🧑‍🤝‍🧑 Pick your path

[Product manager: PRDs, updates, meeting notes. 3 starter skills.] [Engineer: PRs, errors, code review. 3 starter skills.] [Job seeker: applying and interviewing. 3 starter skills.] [Student: exams, notes, applications. 3 starter skills.] [Founder: ideas, runway, fundraising. 3 starter skills.] [中文用户, for Chinese speakers: weekly reports, civil service exams. 3 starter skills.]

_{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 one is a real bundle in plugins/.

[Pick the job you have this week: thirteen bundles, from turning research into decisions and writing the PRD to reading before you sign and landing the next job, each with its number of skills.]

Install any bundle: /plugin install pm-decoders@pm-claude-skills, or npx pm-claude-skills add --bundle pm-decoders. All 153 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

[What's new, release by release: v82.0.0 China for everyone, v83.0.0 For everyone, everywhere, v83.1.0 Duet-ready and v83.2.0 Duet support, the latest.]

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:

[Trust and quality in numbers: skills that pass SkillCheck on every change, skills with eval cases, measured skills and their average score, hostile documents in the injection suite, translations, and how many high-stakes skills have an expert review.]

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

[The library grows a skill at a time: plant one of your own. One markdown file, one PR.]

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

[Avatars of the people who have contributed to PM Skills]

[Levels of contribution: report or fix a bug, translate a skill, write a skill, review, maintain, with how many people have done each]

_{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

[Star history chart for PM Skills, with markers for star milestones and major releases]

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. 1314 skills · 153 bundles · 35 professions · every commit gated. The long version lives in the Showcase.