pm-skills Agent工作流
经 AI Skill Hub 精选评估，pm-skills Agent工作流 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.8 分，适合有一定技术背景的用户使用。
pm-skills Agent工作流 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 7.8 分，是同类 Agent 工作流中的精选推荐。
专为AI代理设计的开源产品管理技能库，包含40个即插即用的预制技能模块。支持Claude Desktop集成，覆盖需求分析、用户研究、竞品分析等核心PM工作，帮助AI助手自动化处理产品管理任务。
pm-skills Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
专为AI代理设计的开源产品管理技能库，包含40个即插即用的预制技能模块。支持Claude Desktop集成，覆盖需求分析、用户研究、竞品分析等核心PM工作，帮助AI助手自动化处理产品管理任务。
pm-skills Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 克隆仓库 git clone https://github.com/product-on-purpose/pm-skills cd pm-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 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 查看帮助 pm-skills --help # 基本运行 pm-skills [options] <input> # 详细使用说明请查阅文档 # https://github.com/product-on-purpose/pm-skills
# pm-skills 配置说明 # 查看配置选项 pm-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_SKILLS_CONFIG="/path/to/config.yml"
简介
<a id="readme-top"></a>
PM-Skills
A curated library of 63 best-practice, plug-and-play product management skills covering the complete product lifecycle - plus templates, workflows, and 95+ real-world sample outputs that set the quality bar.
<p align="center"> <a href="https://github.com/product-on-purpose/pm-skills/issues/new?labels=bug">Report a Bug</a> · <a href="https://github.com/product-on-purpose/pm-skills/issues/new?labels=enhancement">Request a Feature</a> · <a href="https://github.com/product-on-purpose/pm-skills/discussions">Ask a Question</a> </p>
<p align="center"> <img src="https://img.shields.io/badge/Status-Active-success?style=flat-square" alt="Project Status: Active"> <a href="https://github.com/product-on-purpose/pm-skills/blob/main/LICENSE"> <img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=flat-square" alt="License"> </a> <a href="https://github.com/product-on-purpose/pm-skills/releases"> <img src="https://img.shields.io/badge/version-2.18.0-blue.svg?style=flat-square" alt="Version"> </a> <a href="#the-skill-library"> <img src="https://img.shields.io/badge/skills-63-brightgreen.svg?style=flat-square" alt="Skills"> </a> <a href="https://agentskills.io/specification"> <img src="https://img.shields.io/badge/spec-agentskills.io-orange.svg?style=flat-square" alt="Agent Skills Spec"> </a> <a href="https://skills.sh/product-on-purpose/pm-skills"> <img src="https://img.shields.io/badge/skills.sh-install-6f42c1.svg?style=flat-square" alt="Install via skills.sh"> </a> <a href="CONTRIBUTING.md"> <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square" alt="PRs Welcome"> </a> </p>
<p align="center"> <a href="https://github.com/product-on-purpose/pm-skills/stargazers"> <img src="https://img.shields.io/github/stars/product-on-purpose/pm-skills?style=flat-square" alt="Stars"> </a> <a href="https://github.com/product-on-purpose/pm-skills/network/members"> <img src="https://img.shields.io/github/forks/product-on-purpose/pm-skills?style=flat-square" alt="Forks"> </a> <a href="https://github.com/product-on-purpose/pm-skills/issues"> <img src="https://img.shields.io/github/issues/product-on-purpose/pm-skills?style=flat-square" alt="Issues"> </a> <a href="https://github.com/product-on-purpose/pm-skills/graphs/contributors"> <img src="https://img.shields.io/github/contributors/product-on-purpose/pm-skills?style=flat-square" alt="Contributors"> </a> <img src="https://img.shields.io/github/last-commit/product-on-purpose/pm-skills?style=flat-square" alt="Last Commit"> </p>
<p align="center"> <a href="https://github.com/product-on-purpose/pm-skills-mcp"> <img src="https://img.shields.io/badge/MCP_Server-maintenance%20mode-yellow.svg?style=flat-square" alt="MCP Server: Maintenance Mode"> </a> </p>
<p align="center"> <a href="#the-big-idea">About</a> • <a href="#installation-and-setup">Install</a> • <a href="#the-skill-library">Skills</a> • <a href="#sub-agents">Sub-Agents</a> • <a href="#workflows">Workflows</a> • <a href="#learning-and-resources">Learning</a> • <a href="#project-status">Status</a> • <a href="#contributing">Contributing</a> • <a href="#community">Community</a> </p>
---
<details> <summary><strong>Table of Contents</strong></summary>
- Quick Start
- Recent Updates
- The Big Idea
- Who Is This For
- Key Features
- Skill Lifecycle Tools
- Founded On
- Installation and Setup
- How Agent Skills Work
- The Skill Library
- Foundation Skills
- Discover Phase Skills
- Define Phase Skills
- Develop Phase Skills
- Deliver Phase Skills
- Measure Phase Skills
- Iterate Phase Skills
- Tool Family: Foundation Sprint
- Tool Family: Design Sprint
- Standalone Tool Skill
- Utility Skills
- Sub-Agents
- Workflows
- Library Examples
- Learning and Resources
- Project Status
- Contributing
- Community
- FAQ
- About the Author
</details>
---
Key Features
- ✅ 63 Production-Ready Skills covering the complete product lifecycle (30 phase skills + 8 foundation skills + 10 utility skills + 15 tool skills for structured workshop methodologies)
- ✅ Triple Diamond Framework organizing Discover, Define, Develop, Deliver, Measure, and Iterate phases
- ✅ Tool Families for the Foundation Sprint (2-day strategic alignment) and Design Sprint (5-day prototype-and-test) workshop methodologies
- ✅ 4 Active Orchestration Sub-Agents (pm-critic, pm-skill-auditor, pm-changelog-curator, pm-release-conductor) for Claude Code, with dispatch skills extending the pattern to Codex, Cursor, Windsurf, Copilot, and Gemini CLI
- ✅ 12 Workflows for common PM processes including Feature Kickoff, Lean Startup, Triple Diamond, and foundation-to-design end-to-end arc
- ✅ 70 Slash Commands for Claude Code users - instant access to every skill, workflow, and sub-agent
- ✅ Auto-Discovery via AGENTS.md in GitHub Copilot, Cursor, and Windsurf
- ✅ Agent Skills Spec compliant - works across AI assistants
- ✅ Apache 2.0 Licensed for commercial and personal use
Skill Lifecycle Tools = Custom Skill Builder
PM-Skills includes three utility skills that form a complete Create - Validate - Iterate lifecycle for building and managing skills:
Create new skill
from an idea"]:::create Validate["/pm-skill-validate
Audit structure
and quality"]:::validate Decision{"Findings?"}:::decision Ship["Ship
to library"]:::ship Iterate["/pm-skill-iterate
Apply targeted
improvements"]:::iterate Create --> Validate Validate --> Decision Decision -- "PASS" --> Ship Decision -- "WARN / FAIL" --> Iterate Iterate --> Validate
Why this matters: Skills are living artifacts that evolve. The builder creates them, the validator catches drift and quality gaps, and the iterator applies fixes. Together they keep the library consistent as it grows.
| Tool & Command | What it does |
|---|---|
**Builder:** /pm-skill-builder | Creates a new skill from an idea. Runs gap analysis against existing skills, classifies by type and phase, generates draft files to a staging area, and promotes on confirmation. |
**Validator:** /pm-skill-validate | Audits an existing skill against structural conventions and quality criteria. Produces a report with severity-graded findings and actionable recommendations. |
**Iterator:** /pm-skill-iterate | Applies targeted improvements to a skill based on feedback or a validation report. Previews changes, writes on confirmation, and suggests a version bump. |
🔗 More resources:
- PM Skill Lifecycle Guide - Full workflow for creating, validating, and iterating skills, including the builder-validator-iterator cycle with worked examples.
- Creating PM Skills - Authoring guide for contributing new skills to the library.
- Skill Template - The canonical three-file template every skill must follow; copy this as your starting point.
Installation and Setup
Featured Install Paths
Claude Code - Plugin Marketplace (recommended)
/plugin marketplace add product-on-purpose/pm-skills
/plugin install pm-skills@pm-skills-marketplaceAll 63 skills and their slash commands become available immediately. No clone required.
Cross-Agent via skills CLI (Cursor, Copilot, Cline, and others)
npx skills add product-on-purpose/pm-skillsThe open skills CLI from Vercel Labs scans the skills/ directory and installs all 63 skills into your agent's default skills directory. Works with Claude Code, Cursor, GitHub Copilot, Cline, and any other agent that supports the skills ecosystem. Discoverable via skills.sh/product-on-purpose/pm-skills.
Telemetry is anonymous and opt-out via DISABLE_TELEMETRY=1 or DO_NOT_TRACK=1.
Git Clone (manual path, everything included)
git clone https://github.com/product-on-purpose/pm-skills.git
cd pm-skillsGives you the full repo: skill files, slash commands, sample library, workflows, and documentation. Use this path when you want local access to sample outputs, plan to customize skills, or prefer not to depend on a CLI.
Optional: after cloning, run ./scripts/sync-claude.sh (macOS/Linux) or ./scripts/sync-claude.ps1 (Windows) to populate .claude/skills/ for agents that use that discovery path.
Additional Install Methods
For Claude.ai, MCP clients, OpenCode, Windsurf, and ChatGPT, see the full Platform Setup Guide for step-by-step instructions.
| Platform | How | Guide |
|---|---|---|
| Claude.ai / Claude Desktop | ZIP upload to Project Files | [Platform guide](docs/getting-started/getting-started-by-platform.md#claudeai--claude-desktop) |
| MCP Server (any MCP client) | npx pm-skills-mcp | [pm-skills-mcp repo](https://github.com/product-on-purpose/pm-skills-mcp) |
| GitHub Copilot | AGENTS.md auto-discovery from clone | [Platform guide](docs/getting-started/getting-started-by-platform.md#github-copilot) |
| OpenCode | Direct skill loading from clone | [Platform guide](docs/getting-started/getting-started-by-platform.md#opencode) |
| Cursor / Windsurf | AGENTS.md auto-discovery | [Platform guide](docs/getting-started/getting-started-by-platform.md#cursor--windsurf) |
| VS Code (Cline / Continue) | AGENTS.md auto-discovery | [Platform guide](docs/getting-started/getting-started-by-platform.md#vs-code-cline--continue) |
| ChatGPT / other LLMs | Copy SKILL.md into conversation | [Platform guide](docs/getting-started/getting-started-by-platform.md#chatgpt--other-llms) |
More resources:
- Getting Started Guide - Detailed walkthrough for new users covering all install methods, the sync helper script, and your first skill run end-to-end.
- Quickstart Reference - Short-form reference card with just the essential commands.
<p align="right">(<a href="#readme-top">back to top</a>)</p>
---
Quick Start
After installing, you'll have 70 slash commands available (like /prd, /hypothesis, /user-stories) plus access to templates, workflows, sub-agents, and 95+ sample outputs.
Claude Code (recommended):
/plugin marketplace add product-on-purpose/pm-skills
/plugin install pm-skills@pm-skills-marketplaceCross-agent (Cursor, Copilot, Cline, and others via the open skills CLI):
npx skills add product-on-purpose/pm-skillsClone or download:
git clone https://github.com/product-on-purpose/pm-skills.git
More resources:
- Getting Started Guide - Detailed walkthrough for new users covering clone, sync helper, and first skill run. The path to take if any of the quick start steps above leave gaps.
- Setup by Platform - Step-by-step install for Claude.ai, Codex, Cursor, Windsurf, GitHub Copilot, VS Code extensions, and ChatGPT.
- Quickstart Reference - Short-form reference card for users who just need the commands.
<p align="right">(<a href="#readme-top">back to top</a>)</p>
---
Library Examples
Why Examples Matter More Than You Think
When you ask an AI to write a PRD, the output quality is anchored to its training data average. That average is mediocre. The examples in this library are the floor, not the ceiling. They are the quality signal your agent calibrates against before writing anything.
There are two layers of examples:
- Skill-level
EXAMPLE.md- every skill ships with a worked example sitting right next to the SKILL.md. This is what the agent reads at the moment it runs the skill. - Library samples (
library/skill-output-samples/) - 95+ full outputs across three narrative threads. These are for you, not just the agent: read them before a skill run to calibrate expectations, or browse them to understand what a skill you haven't used actually produces.
Workflows (skill chaining)
Workflows combine multiple skills into guided, end-to-end processes that mirror how experienced product managers actually work. Each workflow provides a sequence of skills with handoff guidance between steps so context flows naturally from discovery through delivery.
| Workflow | Best for | Skills included |
|---|---|---|
| **[Foundation to Design](_workflows/foundation-to-design.md)** | End-to-end strategic alignment into prototype-and-test | foundation-sprint-* + design-sprint-* |
| **[Foundation Sprint](_workflows/foundation-sprint.md)** | 2-day strategic alignment only | All 7 foundation-sprint skills |
| **[Design Sprint](_workflows/design-sprint.md)** | 5-day prototype-and-test only | All 7 design-sprint skills |
| **[Feature Kickoff](_workflows/feature-kickoff.md)** | New features | problem-statement, hypothesis, prd, user-stories, launch-checklist |
| **[Lean Startup](_workflows/lean-startup.md)** | Rapid validation | hypothesis, experiment-design, experiment-results, pivot-decision |
| **[Triple Diamond](_workflows/triple-diamond.md)** | Major initiatives | Full 30 phase-skill flow across 6 phases |
| **[Customer Discovery](_workflows/customer-discovery.md)** | Research synthesis | Raw research into a validated problem statement |
| **[Sprint Planning](_workflows/sprint-planning.md)** | Sprint prep | Sprint-ready stories from a backlog |
<p align="right">(<a href="#readme-top">back to top</a>)</p>
---
专业化产品管理工具库，40个精心策划的技能模块覆盖PM核心工作。与Claude深度集成，架构成熟。社区活跃度一般，持续维护需观察。
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 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）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 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）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
- +Apache-2.0 协议，可免费商用
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
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。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
AI Skill Hub 点评：pm-skills Agent工作流 的核心功能完整，质量良好。对于自动化工程师和运维人员来说，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-skills |
| 原始描述 | 开源AI工作流：Curated, plug-and-play product management skills for AI agents. 40 skills across。⭐212 · PowerShell |
| Topics | AI代理工作流产品管理Claude集成可复用技能 |
| GitHub | https://github.com/product-on-purpose/pm-skills |
| License | Apache-2.0 |
| 语言 | PowerShell |
收录时间：2026-05-16 · 更新时间：2026-05-19 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。