Claude技能库
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
**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。
📖 中文文档
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。
- 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
- 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
# 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
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 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
# 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"
🧠 PM Skills — 1169 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
<p align="center"> <a href="https://mohitagw15856.github.io/pm-claude-skills/"> <img src="web/docs-assets/hero.svg" width="100%" alt="PM Skills — 1169 professional skills your AI assistant can read. Plain markdown, works with Claude, ChatGPT, Gemini, Cursor, and Codex. MIT licensed." /> </a> </p>
Your landlord kept your deposit. Your mom got a medical bill that makes no sense. You got laid off on a Tuesday. Someone you love died, and no one handed you the checklist. Generic AI gives you filler for the moments that matter most. PM Skills gives your AI the exact framework a senior professional would use — for 1,117 real tasks, across work and life.
#### 👉 Start with your moment, not the catalogue → Skill Packs 🍼 New parent · 💼 Just laid off · 🌍 New to this country · 👵 Caring for a parent · 🕊️ Losing someone · 💸 Money in crisis · 🔑 Starting over · 🤖 Getting serious about AI
🐣 New here? Pick a door — each takes about 30 seconds
- Just looking → open the ▶ Playground and run a skill in your browser. Nothing to install, nothing to sign up for.
- You use Claude Code → type
/plugin, search pm-skills, install. Done — ask "decode this lease" and watch. - You use anything else →
npx pm-claude-skills addand pick your tool from the menu (Cursor, Codex, Windsurf, ChatGPT, Gemini…). - Want the guided tour → browse the searchable catalogue site and subscribe to get an email whenever new skills launch.
Nothing here can scare your setup. A skill is a markdown file your AI reads — no runtime, no telemetry, no accounts. Installing copies text files; uninstalling is deleting them. Skeptical? Good instinct: read one first — it's designed to be read by humans too.
Don't know what to look for? Describe your task in plain words at 🔎 find — "my landlord kept my deposit", "board meeting on Thursday" — and it names the skill.
<p align="center"> <a href="https://site-jet-seven-34.vercel.app/#subscribe"><img src="https://img.shields.io/badge/📬_Get_the_newsletter-Subscribe_free-d9605a?style=for-the-badge" alt="Subscribe to the PM Skills newsletter"></a> </p>
Never miss a new skill. New ones drop regularly — subscribe to the newsletter and get a short email with a real example whenever they launch. No spam, unsubscribe anytime. Prefer no email? Follow via RSS or browse the newsletter archive.
---
⚡ Quick start
| You want to… | Do this |
|---|---|
| **Browse the skills** | **[SKILLS.md](SKILLS.md)** — the full catalog · or the [searchable web catalog](https://mohitagw15856.github.io/pm-claude-skills/catalog.html) |
| **Install in Claude Code** | /plugin → search **pm-skills** *(it's in the official Anthropic directory)* — or npx pm-claude-skills add --agent claude |
| **Install in Cursor / Codex / Windsurf / Cline…** | npx pm-claude-skills add --agent cursor *(or codex, windsurf, aider, cline, zed…)* |
| **Use one skill in ChatGPT / Gemini** | Copy it from [exports/chatgpt/](exports/chatgpt/) or [exports/gemini/](exports/gemini/) and paste as instructions |
| **Skills over MCP, in any session** | claude mcp add pm-skills -- npx -y pm-claude-skills-mcp |
No npm install needed — npx pm-claude-skills … always runs the latest. npx pm-claude-skills list shows everything in your terminal. Full per-tool instructions: docs/installation.md.
REAL token counts from the API's usage fields, optional blind judge, sha-pinned receipt.
npx pm-claude-skills prove --skill ./my-skill --tasks tasks.txt --runs 2 --judge npx pm-claude-skills prove --skill ./my-skill --tasks tasks.txt --dry-run # plan + call count, spends nothing
💭 [pm-thinking](plugins/pm-thinking/) — think better
Escape the generic answer and stress-test your own decisions: - the-third-answer — skip the obvious, find the idea worth having - five-minds — one question, five clashing minds, then converge - decision-panel — your call, judged by five advisors - red-team-my-plan — attack it before reality does - devils-advocate-on-demand — fights the "that's great!" bias - poke-holes-in-this — only the weaknesses, no praise
</td> <td width="50%" valign="top">
🎯 [pm-focus](plugins/pm-focus/) — get unstuck
ADHD-friendly executive function (useful for everyone): - where-do-i-start — chaos → one next action - task-to-first-step — beat activation-energy paralysis - overwhelm-triage — everything urgent → a calm short list - the-one-thing — the single highest-leverage move - build-my-memory-file — a MEMORY.md so AI gets you - should-i-send-this — catch the message you'd regret
</td> </tr> </table>
Does your skill actually work? Prove it. Paired A/B — skill on vs off, same tasks,
❓ First-timer questions, straight answers
<details> <summary><b>Is it actually free?</b></summary> Yes — MIT, all 1169 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access. </details>
<details> <summary><b>Do I need an API key?</b></summary> Not to browse, read, install, or use skills inside a tool you already have (Claude Code, ChatGPT, Cursor…). The playground even serves a few sponsor-funded free runs a day. A key only enters the picture for optional extras like running skills from CI. </details>
<details> <summary><b>I'm not a product manager. Is this for me?</b></summary> PM stands for <i>Professional</i> here. Most of the library is decoders for leases and medical bills, salary-negotiation practice, career-moment kits, life admin, and 35 professions from teaching to veterinary. The product-management corner is just where it started. </details>
<details> <summary><b>Will this mess with my existing setup?</b></summary> No. Skills are inert text files in a folder; your assistant reads them when relevant. Remove the folder and it's like they were never there. The CLI never touches anything outside the skills directory it tells you about. </details>
<details> <summary><b>How do I know these are any good?</b></summary> Every skill passes a structural gate (SkillSpec L3) and a security scan in CI; 208 outputs are <a href="https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html">eval-scored in the open</a> (avg 4.8/5), and the <a href="skillbench/REPORT.md">benchmark report</a> publishes the negative findings too. When something's machine-translated or unscored, it's labelled. </details>
丰富的Claude技能库，值得关注
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 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
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
👥 适合人群
🎯 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
- +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
- −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
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。
✅ 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
❓ 常见问题 FAQ
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。
| 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 |
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。