📄 工具详情 ⚙️ 安装教程 📚 使用教程
能力标签
🔌 MCP🤖 Agent🔄 工作流💻 CLI📚 RAG🖼 视觉🧠 Claude✨ GPT🕸 采集
Claude技能库
⚡
Claude技能

Claude技能库

基于 Shell · 专为 Claude 深度优化，CLI 一键安装
英文名：pm-claude-skills
⭐ 979 Stars 🍴 177 Forks 💻 Shell 📄 MIT 🏷 AI 7.5分
7.5AI 综合评分
claude_skillagent-skillschatgptclaude-ai
⬇ 下载源码 ZIP ⚙️ 配置说明 📺 TG 频道
✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估，Claude技能库 获评「推荐使用」。这款Claude技能在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.5 分，适合有一定技术背景的用户使用。

📚 深度解析

Claude技能库 是一款基于 Shell 的开源工具，在 GitHub 上收获 1k+ Star，是claude_skill、agent-skills、chatgpt、claude-ai领域中的优质开源项目。开源工具的最大优势在于代码完全透明，你可以审计每一行代码的安全性，也可以根据自身需求进行二次开发和定制。

**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。

**安装与环境准备**
Claude技能库 依赖 Shell 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 Shell 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。

**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 Claude技能库 的版本更新，及时通知重要功能变化。

📋 工具概览

Claude技能库 是一款基于 Shell 开发的开源工具，专注于 claude_skill、agent-skills、chatgpt 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。

GitHub Stars
⭐ 979
开发语言
Shell
支持平台
macOS / Linux
维护状态
正常维护，社区驱动
开源协议
MIT
AI 综合评分
7.5 分
工具类型
Claude技能
Forks
177

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

Claude技能库 是一款基于 Shell 开发的开源工具，专注于 claude_skill、agent-skills、chatgpt 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。

📌 核心特色
  • 专为 Claude 系列模型深度优化的扩展技能
  • 通过 Claude Code CLI 一键安装，配置零门槛
  • 充分利用 Claude 的长上下文和推理能力
  • 支持与 MCP 工具组合使用，扩展能力边界
🎯 主要使用场景
  • 在 Claude 中快速解决特定专业领域的问题
  • 复杂任务的 AI 辅助分析、推理和报告生成
  • 构建个人专属的 AI 技能工具箱
以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。
安装命令
# 克隆仓库
git clone https://github.com/mohitagw15856/pm-claude-skills
cd pm-claude-skills

# 查看安装说明
cat README.md

# 按 README 完成环境依赖安装后即可使用
📋 安装步骤说明
  1. 访问 GitHub 仓库页面
  2. 按照 README 文档完成依赖安装
  3. 根据系统环境完成初始化配置
  4. 参考官方示例或文档开始使用
  5. 遇到问题可在 GitHub Issues 中查找解答
以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。
常用命令 / 代码示例
# 查看帮助
pm-claude-skills --help

# 基本运行
pm-claude-skills [options] <input>

# 详细使用说明请查阅文档
# https://github.com/mohitagw15856/pm-claude-skills
以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。
配置示例
# pm-claude-skills 配置说明
# 查看配置选项
pm-claude-skills --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量（覆盖配置文件）
export PM_CLAUDE_SKILLS_CONFIG="/path/to/config.yml"
📑 README 深度解析 真实文档 完整度 40/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

🧠 PM Skills — 174 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes

Open-source Agent Skills (SKILL.md) + subagents + slash commands for every profession — one source, every AI coding tool.

Stars npm npm downloads Skills Subagents Commands Personas Platforms SkillCheck Security Audit Version Install License Sponsor

🆕 What's New in v21.0.0 — Workflow Recipes, Eval-Verified Quality & a Smarter Playground

The 174 skills become a system, not just a catalog.

  • 🧩 Workflow Recipes — chain skills into one flow, each output feeding the next: /ship-a-feature, /close-the-quarter, /launch-a-product, /rescue-an-account, /run-discovery. Run as slash commands or over MCP. See WORKFLOWS.md.
  • ✅ Eval-verified quality — real scores (structure, completeness, usefulness, grounding; judged by Opus 4.8) now show as badges in the Playground and leaderboard. Eval coverage grew from 6 → 15 skills.
  • 🔌 One-click MCP — claude mcp add pm-skills -- npx -y pm-claude-skills-mcp makes every skill + recipe available in Claude Code, Claude Desktop, Cursor, and Windsurf, plus new list_workflows/get_workflow tools.
  • 🎛️ Playground upgrades — a "which skill do I need?" recommender, a with/without Compare toggle, shareable deep-links that prefill inputs, and eval-score badges.
  • 📄 Sample-output gallery — 18 real example outputs so you can see what a skill produces before running it.
  • 🗓️ Skill of the week — a scheduled workflow that composes weekly social posts.

🆕 What's New in v20.2.0 — Community PRs & New Skill

  • New skill: YouTube Script Writer (experimental) — retention-optimized video scripts with hook variations, a video/audio cue table, and SEO metadata. Thanks @prajwal-28 (#50). Now 174 skills.
  • Feature-prioritisation helper — a dependency-free Python script that computes RICE/ICE rankings consistently across sessions. Thanks @zeotrix (#48).
  • Safer installs + robust parsing — the CLI refuses system-critical install targets, and skillcheck tolerates CRLF/whitespace in frontmatter. Thanks @MatrixNeoKozak (#47).
  • Catalog reconciled to 174 — the headline, badge, and skill catalog now reflect the true count, with entries added for Skill Security Auditor, Launch Readiness, and YouTube Script Writer.

<details> <summary><strong>v20.1.0 — Star Nudges & Eval Hardening</strong> (click to expand)</summary>

  • Star the repo, from anywhere you use it — tasteful, non-spammy CTAs (no postinstall): after a successful npx pm-claude-skills add, in --help, in list, in the MCP server banner, below the README badges, and a funding link on npm.
  • One-click leaderboard in CI — the "Update Skill Leaderboard" workflow runs the evals with your ANTHROPIC_API_KEY secret and opens a results PR; merge it to publish real numbers.
  • Faster, hang-proof evals — per-request timeout + retries in the API client and concurrent eval runs, so a CI run finishes in minutes and can't stall.

</details>

<details> <summary><strong>v20.0.0 — Agentic Tooling</strong> (click to expand)</summary>

The library starts doing the work, not just describing it:

  • GitHub Action (action/) — run any skill in a repo's CI (auto PR descriptions, changelogs, release notes, reviews). uses: mohitagw15856/pm-claude-skills/action@main. We dogfood it to write this repo's own PR descriptions.
  • generate command — npx pm-claude-skills generate --from <url|file> turns your docs into a standard-compliant SKILL.md.
  • Skill evals + Leaderboard — LLM-as-judge scoring of skills across models, rendered as a public leaderboard.

</details>

<details> <summary><strong>v19.0.0 — Security Auditor, Personas & Catalog</strong> (click to expand)</summary>

  • Skill Security Auditor — scans every skill (and its scripts) for prompt injection, exfiltration, unsafe code, secrets, hidden text; HIGH fails CI. Plus a skill-security-auditor skill.
  • 4 personas (output-styles), an orchestration guide, a server-rendered skill catalog, and a public roadmap.

</details>

<details> <summary><strong>v18.0.0 — Windsurf, Aider & an MCP Server</strong> (click to expand)</summary>

  • Two more install targets — Windsurf and Aider (now 5 export platforms / 7 tools).
  • MCP server (npx pm-claude-skills-mcp) — search & pull skills on demand from MCP clients.
  • Automated npm publishing workflow; README hero demo placement.

</details>

<details> <summary><strong>v17.0.0 — Agents, Commands & the npx CLI</strong> (click to expand)</summary>

The library grows past "just skills" and gets one-command, cross-platform install:

  • npx pm-claude-skills add --agent <tool> — a cross-platform Node installer (Windows/macOS/Linux, no bash, no git).
  • 4 Claude Code subagents (agents/) and 6 slash commands (commands/); --agent claude installs skills + agents + commands together.
  • Cursor .mdc exports, a SkillCheck validator + CI badge, and a skill scaffolder (npm run new-skill).
  • One-line shell installers plus a unified scripts/install.sh.

</details>

<details> <summary><strong>v16.0.0 — Multi-Platform</strong> (click to expand)</summary>

The library stops being Claude-only and becomes a portable, single-source-of-truth project:

  • Runs on more platforms. Native install for Hermes Agent (same open SKILL.md standard), plus ready-to-paste ChatGPT and Gemini exports generated from every skill.
  • One source, many targets. scripts/build-exports.mjs renders per-platform files from each SKILL.md body — nothing maintained twice — with a PLATFORMS registry and a CI guard that fails on drift.
  • Three stdlib Python helpers for flagship skills (sprint capacity, RICE scoring, customer-health scoring).
  • Explicit skill tiers (TIERS.md + skill-tiers.json) and an upgraded Skill Playground (tier filter + "use in another tool" copy panel).
  • Repo hygiene: CHANGELOG.md, SKILL-AUTHORING-STANDARD.md, refreshed SECURITY.md, .gitignore, Related Projects.

</details>

<details> <summary><strong>Release history — v6.0.0 → v15.0.0</strong> (click to expand)</summary>

🆕 What's New in v15.0.0 — Skill Playground (browser UI) 🌐

Run any skill without installing anything — a zero-backend web app that executes skills in your browser with your own Claude API key. Tile gallery with search and bundle filter, click-to-run forms auto-generated from each skill's inputs, live streaming output with copy / download, and an auto-deploy to GitHub Pages on every push to main. ▶ Live: mohitagw15856.github.io/pm-claude-skills

🆕 What's New in v14.0.0 — Writers & Content Creators + 7 Community Skills

12 new community-inspired skills across 4 bundles:

🆕 What's New in v13.0.0 — Social Media Profession

5 new skills — a complete Social Media profession bundle:

SkillBundleWhat It Does
**Social Media Audit** 🆕pm-socialScored audit across all platforms — profile completeness, content performance, competitive benchmarking, and a prioritised action plan
**Influencer Brief** 🆕pm-socialComplete creator partnership brief with deliverables, creative guidelines, approval workflow, commercial terms, and campaign measurement
**Community Management Playbook** 🆕pm-socialResponse frameworks, moderation rules, escalation tiers, DM templates, tone-of-voice guidance, and community health metrics
**Social Ad Campaign** 🆕pm-socialFull-funnel paid social campaign plan with audience targeting, ad set architecture, copy for every format (video, static, carousel, lead gen), budget allocation, and A/B testing plan
**Viral Content Framework** 🆕pm-socialPsychology of sharing, 6 proven hook formulas, 5 content structures, platform-specific playbooks for LinkedIn/TikTok/Instagram/X/YouTube, and a repeatable content testing system

The library now includes 167 skills across 18 professions + 4 working agent templates.

Install the new bundle:

claude plugin install pm-social@pm-claude-skills

---

🆕 What's New in v12.0.0 — 150 Skills Milestone

15 new skills across 10 bundles:

SkillBundleWhat It Does
**Cohort Analysis** 🆕pm-dataRetention curves, LTV projection, behavioural segmentation, and churn leading indicators — with SQL reference queries
**Data Pipeline Spec** 🆕pm-dataETL/ELT pipeline design with sources, transforms, SLAs, DQ rules, error handling, and security/compliance notes
**Renewal Playbook** 🆕pm-csRenewal brief with health snapshot, stakeholder map, value story, commercial scenarios, objection responses, and a 16-week timeline
**Customer Success Plan** 🆕pm-csJoint success plan with business goals, success metrics, milestone roadmap, mutual commitments, and escalation path
**360-Degree Feedback Template** 🆕pm-peopleEither a complete survey instrument with GWT acceptance criteria, or a structured narrative feedback report with themes and development actions
**Team Health Check** 🆕pm-peopleSpotify-model health assessment across 7 dimensions — delivery, safety, morale, speed, purpose, and collaboration — with facilitation guide
**Risk Register** 🆕pm-operationsL×I risk scoring, RAG heat map, top-risk executive summary, and per-risk mitigation and contingency plans
**RACI Matrix** 🆕pm-operationsComplete RACI with role definitions, decision map, anti-pattern guide, and a communication template for all involved teams
**Social Media Strategy** 🆕pm-gtmAudience profile, platform rationale, content pillars, posting cadence, tone of voice, KPIs, and a 4-week starter calendar
**Product Positioning Doc** 🆕pm-gtmApril Dunford-style positioning doc with category, target customer, competitive alternatives, differentiation, proof points, messaging hierarchy, and persona messaging
**Customer Journey Map** 🆕pm-discoveryStage-by-stage journey from awareness to advocacy with touchpoints, emotions, pain points, an emotion curve, and prioritised opportunities
**User Story Writer** 🆕pm-deliveryProduction-ready user stories with Given/When/Then ACs, edge cases, out-of-scope, definition of done, and epic decomposition
**AI Ethics Review** 🆕pm-advancedStructured ethical review covering fairness, bias, transparency, privacy, safety, accountability, and societal impact — with risk tier and pre-deployment checklist
**Partnership Proposal** 🆕pm-salesB2B partnership proposal with mutual value, commercial model, joint GTM plan, governance, and risks
**Design System Audit** 🆕pm-designComponent coverage audit, token consistency, documentation quality, WCAG 2.2 accessibility, adoption barriers, and a remediation roadmap

The library now includes 150 skills across 16 professions + 4 working agent templates.

---

🆕 What's New in v10.0.0

Two star milestones unlocked — 8 new skills shipped:

Customer Success bundle (250 ⭐ milestone):

SkillBundleWhat It Does
**Customer Health Scorecard** 🆕pm-csWeighted health score across adoption, engagement, outcomes, support, and commercial — with RAG status and renewal forecast
**QBR Deck** 🆕pm-csSlide-by-slide quarterly business review structure with talking points, value narrative, and mutual commitments
**Escalation Brief** 🆕pm-csStructured escalation brief for at-risk accounts — root cause, business impact, resolution plan, and decision required
**Churn Analysis** 🆕pm-csChurn rate breakdown by category and segment, early warning signals, and prioritised interventions

Engineering expansion (500 ⭐ milestone):

SkillBundleWhat It Does
**CI/CD Playbook** 🆕pm-engineeringComplete pipeline playbook covering every stage, rollback procedures, secrets management, and on-call responsibilities
**SLO & Error Budget** 🆕pm-engineeringSLI definitions, SLO targets, error budget calculation, burn rate alerts, and error budget policy
**Developer Onboarding Doc** 🆕pm-engineeringEverything a new engineer needs in their first week — architecture, local setup, testing, deployment, and key contacts
**On-Call Runbook** 🆕pm-engineeringPer-alert response procedures, escalation matrix, diagnostic cheat sheet, and handoff template

The library now includes 114 skills across 16 professions + 4 working agent templates.

SkillBundleWhat It Does
**Debugging Log Analyser** 🆕pm-engineeringParse stack traces and error logs into a structured root cause diagnosis with a specific fix
**PR Description Writer** 🆕pm-engineeringWrite reviewer-friendly PR descriptions from a diff, commit list, or change summary
**System Design Interview** 🆕pm-engineeringStructure complete system design answers with capacity estimates, component deep-dives, and trade-offs
**Changelog Generator** 🆕pm-engineeringConvert git commits into a polished, user-facing changelog following Keep a Changelog format
**Test Strategy Doc** 🆕pm-engineeringWrite a complete test strategy with risk assessment, test types, coverage targets, and P0/P1 test cases
**Runbook Writer** 🆕pm-engineeringWrite operational runbooks for deployments, incidents, and maintenance with exact commands and rollback steps

The pm-engineering bundle now has 10 skills — the most complete engineering toolkit in the library.

Read the full story: Part 14 — I Rebuilt All 93 Skills and Added 7 More: What 100 Skills Taught Me About What Makes a Great Skill

---

🚀 Quick Install (2 minutes)

Any tool, one command — via the pm-claude-skills npm package (Windows/macOS/Linux, needs Node):

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

Or one-line MCP — make all 174 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 Code, run:

/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-skills mkdir -p ~/.claude/skills ln -s ~/pm-claude-skills/skills/* ~/.claude/skills/

---

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 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 the chat-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.

---

🤖 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 17 professions beyond financial services. The 174 skills here are the building blocks for agent templates outside of finance.

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:

TemplateSkills usedConnectors neededSubagents
**PM Sprint Agent**sprint-planning, sprint-brief, retro, project-status-reportLinear or Jira, SlackCapacity analyst, risk scorer
**Legal Contract Review Agent**contract-review, nda-analyser, compliance-checklistGoogle Drive or SharePointClause-by-clause risk scorer
**PM Discovery Agent**discovery-interview-guide, user-interview-synthesis, assumption-mapperGranola or Otter, NotionTheme synthesiser
**Sales Pursuit Agent**sales-battlecard, discovery-call-prep, proposal-writer, account-planSalesforce or HubSpot, GongCompetitive intel analyst
**HR Onboarding Agent**onboarding-plan, job-description-writer, change-management-planWorkday or BambooHR, SlackFirst-week scheduler
**Finance Board Pack Agent**investor-update, board-deck-narrative, financial-model-narrativeNetSuite or Xero, Google DriveKPI variance analyst
**Marketing Launch Agent**go-to-market, content-calendar, email-campaign, media-pitchHubSpot, NotionChannel strategist

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.

---

🔄 One library, the whole professional workflow

These 174 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:

  DISCOVER  →   DECIDE   →    BUILD    →    SHIP    →   MEASURE   →  COMMUNICATE
 ──────────   ──────────   ──────────   ──────────   ──────────   ─────────────
  frame the    prioritise    design &     launch &     track &      report up
  problem,     & spec the    engineer     release      analyse      & out
  research     work          the work     the work     results
        └────────────────────── feeds the next discovery ──────────────────────┘
PhaseWhat you're doingStart with these skills
**🔍 Discover**Frame the problem, research, validateambiguity-resolver · user-research-synthesis · competitive-analysis · discovery-interview-guide
**🎯 Decide**Prioritise, spec, set goalsrice-prioritisation · prd-template · okr-builder · roadmap-narrative
**🔨 Build**Design & engineer the worktechnical-spec-template · design-critique · sprint-planning · architecture-decision-record
**🚀 Ship**Launch & releasego-to-market · launch-readiness · product-launch-checklist · runbook-writer
**📊 Measure**Track outcomes & analysemetrics-framework · cohort-analysis · ab-test-planner · churn-analysis
**📣 Communicate**Report up and outexecutive-update · board-deck-narrative · stakeholder-update · qbr-deck
New here? Start with the top-tier skills, or jump straight to all 174 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 ────────────────┘
RecipeWhat it doesLifecycle
/ship-a-featureidea → PRD → priority → roadmap → launch planDiscover → Ship
/close-the-quartermetrics → churn → exec update → board deckMeasure → Communicate
/launch-a-productcompetitors → positioning → GTM → checklist → press releaseDecide → Ship
/rescue-an-accounthealth score → churn cause → escalation → renewal planMeasure → Communicate
/run-discoveryframe → interview guide → synthesis → prioritiseDiscover → Decide

→ 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.

---

📦 Plugin Directory

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

PluginSkillsBest for
**pm-essentials**competitive-analysis, meeting-notes, prd-template, stakeholder-update, user-research-synthesis, docx-tracked-changesThe core PM toolkit — start here if you're new. Covers the documents you write every week: PRDs, stakeholder updates, meeting notes, and competitive analysis.
**pm-advanced**ai-ethics-review, ai-product-canvas, experiment-designer, design-handoff-brief, multi-source-signal-synthesiserFor PMs working on AI products or running sophisticated experiments. Covers ethical review of AI features, AI-native product canvases, and experiment design.
**pm-analytics**data-analysis-standard, product-health-analysis, retention-analysisTurn raw data into PM-ready narratives. Use when you need to frame an analysis, explain health metrics to leadership, or diagnose retention drop-offs.
**pm-business**board-deck-narrative, investor-update, job-applicationFor PMs operating at the business layer — writing board narratives, investor updates, or crafting a standout job application.
**pm-cross**executive-summary, grant-proposal, last-30-days-research, notebooklm-connector, press-release, sycophancy-challenger, teaching-lesson-planCross-profession utility skills that work outside a single domain — writing executive summaries, press releases, running research, and challenging sycophantic AI output.
**pm-cs**churn-analysis, cs-escalation-brief, cs-health-scorecard, customer-success-plan, qbr-deck, renewal-playbookFor PMs or CSMs responsible for retention. Covers churn diagnosis, escalation briefs, QBR decks, health scorecards, and renewal plays.
**pm-data**chart-data-extractor, cohort-analysis, dashboard-brief, data-pipeline-spec, metrics-framework, sql-query-explainerData-heavy work: extracting insights from charts, building metrics frameworks, explaining SQL queries, designing dashboards, and speccing data pipelines.
**pm-delivery**ab-test-planner, go-to-market-planner, pptx-slide-auditor, product-launch-checklist, retro-analysis, sprint-brief, sprint-planning, technical-spec-template, user-story-writerEverything you need to ship: sprint planning, user stories, launch checklists, A/B test design, retros, and PowerPoint auditing. The most-used plugin for day-to-day delivery.
**pm-design**accessibility-audit, design-critique, design-system-audit, ux-research-planFor PMs who work closely with design. Covers accessibility audits, structured design critiques, design system reviews, and UX research planning.
**pm-discovery**assumption-mapper, customer-journey-map, discovery-interview-guide, job-story-mapper, user-interview-synthesisThe discovery toolkit: map assumptions, build journey maps, write interview guides, synthesise user interviews, and reframe features as job stories.
**pm-engineering**37 skills across API docs, architecture, CI/CD, incident response, security, observability, and moreThe largest plugin — built for PMs embedded in engineering teams. Covers technical specs, runbooks, on-call processes, architecture decisions, and engineering hiring.
**pm-figma**figma-annotation-guide, figma-component-audit, figma-design-brief, figma-design-critique-pm, figma-design-qa, figma-design-review, figma-prototype-plan, figma-spacing-system, figma-user-flow-planner, figma-variant-matrixPurpose-built for Figma workflows. Covers design QA, component audits, spacing systems, user flow planning, variant matrices, and design briefs — all from a PM perspective.
**pm-finance**budget-variance-analysis, financial-due-diligence, financial-model-narrative, investor-pitch-deck, tax-planning-checklistFor PMs who touch financials — explaining budget variances, building investor pitch decks, narrating financial models, and running due diligence reviews.
**pm-gtm**competitor-teardown, content-calendar, email-campaign, go-to-market, media-pitch, product-positioning-doc, seo-content-brief, social-media-strategyThe go-to-market toolkit: positioning docs, competitor teardowns, GTM plans, content calendars, email campaigns, and SEO briefs. Best for PMs who own launch and demand.
**pm-hr**change-management-plan, employee-engagement-survey, job-description-writer, onboarding-plan, redundancy-consultationPeople operations skills — writing job descriptions, managing change, designing onboarding, running engagement surveys, and handling redundancy consultations.
**pm-legal**compliance-checklist, contract-review, legal-brief, nda-analyserFor PMs navigating legal and compliance work: reviewing NDAs, summarising contracts, creating compliance checklists, and preparing legal briefs.
**pm-operations**email-triage, morning-intelligence, process-documentation, project-status-report, raci-matrix, risk-register, sop-writer, vendor-evaluation, workshop-facilitation-guideOperational efficiency skills — managing your inbox, running status reports, documenting processes, evaluating vendors, writing SOPs, and facilitating workshops.
**pm-people**360-feedback-template, hiring-rubric, performance-review, team-health-check, team-offsite-plannerFor people managers and team leads: writing performance reviews, running 360 feedback, designing hiring rubrics, checking team health, and planning offsites.
**pm-planning**feature-prioritisation, okr-builder, pricing-strategy, rice-impact-matrix, rice-prioritisation, roadmap-narrative, roadmap-presentationStrategic planning from roadmaps to OKRs — prioritising features with RICE, writing roadmap narratives, setting pricing, building OKRs, and presenting strategy to stakeholders.
**pm-research**clinical-case-summary, literature-review, patient-communication, research-protocolFor PMs in healthcare and research settings. Covers clinical case summaries, literature reviews, research protocols, and patient-facing communication.
**pm-rituals**pm-weekly-reviewA single powerful skill for the PM weekly review ritual — reflecting on progress, blockers, and priorities in a structured, consistent format.
**pm-sales**account-plan, discovery-call-prep, partnership-proposal, proposal-writer, sales-battlecard, sales-forecasting-modelFor PMs who work alongside sales — writing battlecards, preparing for discovery calls, building account plans, crafting partnership proposals, and forecasting.
**pm-social**community-management-playbook, influencer-brief, social-ad-campaign, social-media-audit, viral-content-frameworkSocial media and community skills: running ad campaigns, briefing influencers, auditing social presence, building community playbooks, and designing viral content.
**pm-strategy**ambiguity-resolver, competitive-intelligence-monitor, competitor-signal-tracker, executive-update, stakeholder-influence-mapper, strategic-narrative-generatorSenior PM and strategic work — resolving ambiguity, tracking competitive signals, mapping stakeholder influence, writing executive updates, and building strategic narratives.
**pm-writers**aeo-optimizer, instagram-post-downloader, notes-humanizer, substack-notes-scraper, thumbnail-creatorFor content creators and writers using Claude: optimising for AI search engines, humanising notes, scraping research from Substack, and generating thumbnail concepts.

---

🎯 aiskill88 AI 点评 A 级 2026-06-17

丰富的Claude技能库，值得关注

📚 实用指南（长尾问题）
适合谁
  • 构建多智能体协作系统的 Agent 开发者
最佳实践
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
部署方案
  • 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
pm-claude-skills 中文教程pm-claude-skills 安装报错怎么办pm-claude-skills Agent 工作流pm-claude-skills 与同类工具对比pm-claude-skills 最佳实践pm-claude-skills 适合谁用

⚡ 核心功能

👥 适合谁
  • 构建多智能体协作系统的 Agent 开发者
⭐ 最佳实践
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）

👥 适合人群

Claude 重度用户AI 研究者和开发者需要专业领域 AI 增强的专家

🎯 使用场景

  • 在 Claude 中快速解决特定专业领域的问题
  • 复杂任务的 AI 辅助分析、推理和报告生成
  • 构建个人专属的 AI 技能工具箱

⚖️ 优点与不足

✅ 优点
  • +MIT 协议，可免费商用
  • +深度优化 Claude 使用体验
  • +CLI 一键安装，极度便捷
  • +官方支持，稳定可靠
⚠️ 不足
  • −仅限 Claude 用户使用，受平台限制
  • −功能边界受当前 Claude 模型能力约束
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。

🔗 相关工具推荐

科学智能代理
将任何AI代理转化为AI科学家，开源Claude技能
小红书创作者助手
AI助手，图文轮播规划、视觉导演、封面内页设计
Claude代码技能
精选100+Claude代码技能，18个原创可安装技能
AI编码代理编排器
Claude技能
📚 相关教程推荐
如何安装 Skill
帮助中心 · AI Skill Hub
可安装 Skill
帮助中心 · AI Skill Hub
Claude vs ChatGPT 2025 开发者场景深度对比：代码、工具调用、长文本哪个更强
帮助中心 · AI Skill Hub
Claude vs ChatGPT 2025 开发者场景深度对比：代码、工具调用、长文本哪个更强
帮助中心 · AI Skill Hub
📰 相关 AI 新闻
AI Agent 自主化能力最新进展
AI 资讯 · 知识关联
AI 前沿资讯：How many tabs do you currently…
AI 资讯 · 知识关联
ChatGPT 最新动态与实用技巧
AI 资讯 · 知识关联
AI 前沿资讯：NEA’s Tiffany Luck says enterp…
AI 资讯 · 知识关联
🍿 AI 圈相关吃瓜
配了5个 MCP 工具，Claude 一个都没用
AI 圈观察
AutoGPT 自主完成了任务：把我的文件夹全部重命名了
AI 圈观察
Filesystem MCP 帮 Claude 找文件，找了整个 node_modules
AI 圈观察
🗺️ 相关解决方案
mcp
mcp-server-setup
agent
ai-agent-workflow
workflow
ai-workflow-templates
cli
cli-productivity
🧩 你可能还需要
基于当前 Skill 的能力图谱，自动补全的工具组合
技能寻求者
MCP · Agent · 工作流
MemOS智能记忆系统
MCP · Agent · 工作流
total-agent-memory MCP工具
为Claude Code和Codex CLI提供持久化记忆功能的开源MCP工具。自动提取知识图谱，支持多轮对话上下文保留，适合需要长期记忆和
natively-cluely-ai-assistant — Claude Skill 中文使用文档
免费开源的AI面试助手，实时转录，隐蔽模式，局部RAG，BYOK。无订阅，防止数据泄露。
CrewAI 多代理协作平台
MCP · Agent · 工作流
Synthadoc
MCP · Agent · 工作流

❓ 常见问题 FAQ

pm-claude-skills 是一款Shell开发的AI辅助工具。开源Claude技能：167 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude。⭐979 · Shell 主要应用场景包括：为Claude提供专业的Agent技能。
💡 AI Skill Hub 点评

AI Skill Hub 点评：Claude技能库 的核心功能完整，质量良好。对于Claude 重度用户来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载，无需跳转 GitHub

📚 深入学习 Claude技能库
查看分步骤安装教程和完整使用指南，快速上手这款工具
⚙️ 安装教程 📚 使用教程
🌐 原始信息
原始名称 pm-claude-skills
原始描述 开源Claude技能：167 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude。⭐979 · Shell
Topics claude_skillagent-skillschatgptclaude-ai
GitHub https://github.com/mohitagw15856/pm-claude-skills
License MIT
语言 Shell
🔗 原始来源
🐙 GitHub 仓库  https://github.com/mohitagw15856/pm-claude-skills 🌐 官方网站  https://medium.com/product-powerhouse/claude-skills-the-ai-feature-thats-quietly-changing-how-product-managers-work-aad5d8d0640a

收录时间：2026-06-17 · 更新时间：2026-06-27 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。

📺 订阅 AI Skill Hub Daily Telegram 频道
每天 8 条精选 AI Skill、MCP、Agent 与自动化工具推送
加入频道 →