Skills are portable to Google Gemini, enabling professional-grade outputs in Gemini sessions.
Skills run natively in Hermes Agent, following the same open SKILL.md standard.
Automate skills in n8n workflows via a read-only REST API on the hosted Worker.
Run skills in your Obsidian vault via a read-only REST API.
English · 简体中文 · 繁體中文 · 한국어 · 日本語 · Español · Português (BR)
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.
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: 1295 of them, one markdown file each. (PM stands for Professional. Yes, we get asked.)
PM Skills is an open-source library of 1295 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.
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
Related MCP server: Awesome Agent Skills MCP Server
More to see: the Showcase gallery has the Playground, the tech tree, Galaxy 3D and Skill City.
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.
The product-management core first, then the bundles everyone borrows. Each row is a real bundle in plugins/.
Your job this week | Bundle | What you get | What you bring |
Turn research into decisions | Interview guides, job stories, synthesis with quotes and prevalence | Transcripts or raw notes | |
Write the PRD and the updates | PRD, meeting notes, stakeholder updates, competitive analysis | A feature brief; your goals | |
Plan the quarter | OKRs, RICE/MoSCoW/Kano prioritisation, roadmap narrative | A backlog and a company goal | |
Ship the sprint and the launch | Sprint plans, tech specs, A/B test plans, launch checklists | Stories, capacity, dates | |
Read the numbers | Metrics frameworks, cohort and churn analysis, dashboard briefs | Your metrics or a CSV | |
Watch the market | Competitor teardowns, signal tracking, stakeholder influence maps | Competitor names and sources | |
Launch and sell it | GTM plans, content calendars, email campaigns | A product and an audience | |
Keep the customers | Health scorecards, QBR decks, churn analysis, renewal playbooks | Account data, close notes | |
Make the hard call | Typed ship-or-slip, renew-or-churn, hire-or-pass calls with probabilities | The decision's real state | |
Escape the average answer | Red-teaming, five clashing minds, decision panels | A plan or question worth attacking | |
Read before you sign | Leases, bills, benefits and contracts decoded with the money maths | The document itself | |
Land the next job | JD decoding, outreach, interview prep, follow-up sequences | The JD and your CV | |
用中文工作 | 周报、述职、复盘，中国职场的写法 | 你的工作记录 |
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
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
Release | What it adds | Try saying |
v83.0.0 For everyone, everywhere | Easy Read, Teach me, voice and mixed-language questions, local rules for your place, a skill for every form, newcomer, informal-economy, disability and after-a-disaster skills, the library offline on a Raspberry Pi, a USSD menu for any phone, right-click any file, skill apps, partner checks and an expert-graded jobs exam | "Explain this P60 to me" · "मेरा landlord deposit नहीं दे रहा" |
v82.0.0 China for everyone, Korea and Southeast Asia | Teachers, parents, trade and manufacturing packs, 适老化, Korean, Japanese and Southeast Asian packs, lite skills for local models, Word and WPS add-ins, team sync | "帮我写一份新课标教案" · "연말정산 어떻게 해요?" |
Reaching everyone (v83): read any skill in Easy Read, have it teach you instead of doing it, ask by voice in your own language (Hinglish and Taglish included), look up any form, open a skill as an app, or use it with no internet: on a Raspberry Pi, over USSD on a basic phone, or from the right-click menu with a free local model.
Everything older: CHANGELOG.md · the write-ups: docs/WHATS-NEW.md · most-wanted skills and votes: the tech tree
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 1,295 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: 399 of the 1,295 skills carry eval cases (evals/cases.json), and 150 have a worked example in examples/.
Measured scores: 399 skills have blind-judged scores on the leaderboard (average 4.6/5 across the models tested); the benchmark report publishes the negative findings too. Everything unscored is unscored, not assumed good.
Human review: of the 161 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.
Checked by people who do the job: organisations can vouch for skills as partners, and the jobs exam has AI answers marked blind by working professionals on their own marking schemes. Both start empty and fill only with real participants.
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).
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.
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。
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.
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. 1295 skills · 152 bundles · 35 professions · every commit gated. The long version lives in the Showcase.*
This server cannot be deployed
Search 1,400+ agent skills for Claude Code, Codex and Cursor, with install commands and proofs.
Contextual prompts and agent skills for 140+ AI platforms.
Agent skills for Claude, Codex and Cursor: find, install and load skills from one connector.
Agent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.