product-management
Skill3 starsChanged 23 days agoMITView on GitHub
涵盖从构思到发布的产品管理全生命周期专业知识。包括需求收集、用户故事创建、优先级排序和产品策略。使用此技能进行产品规划、撰写 PRD、定义 MVP 或进行竞品分析时使用。
Files
产品管理技能 (Product Management Skill)
何时使用
触发场景:当用户提出以下请求时,使用本 skill:
- 当需要进行产品规划或撰写 PRD 时
- 当需要创建用户故事或排定需求优先级时
- 当用户要求定义 MVP 或做竞品分析时
描述
涵盖从构思到发布的产品管理全生命周期专业知识。包括需求收集、用户故事创建、优先级排序和产品策略。
能力
1. 需求工程
- 用户访谈与调研:收集定性和定量数据的技巧。
- 问题定义:使用“我们可以如何(How Might We)”语句来构建问题框架。
- PRD 撰写:构建全面的产品需求文档结构。
- 功能性与非功能性:区分系统做什么(功能)和系统如何表现(性能、安全)。
2. 功能优先级排序
- RICE 评分:覆盖面(Reach)、影响力(Impact)、信心(Confidence)、投入(Effort)。
- MoSCoW 方法:必须有(Must have)、应该有(Should have)、可以有(Could have)、不会有(Won't have)。
- Kano 模型:兴奋型、期望型、基本型需求。
- WSJF:加权最短作业优先(用于敏捷开发)。
3. 用户故事地图与定义
- 用户故事格式:“作为一个<角色>,我想要<功能>,以便<利益>。”
- 验收标准:软件产品必须满足的条件,以便被用户接受。
- INVEST 原则:独立的(Independent)、可协商的(Negotiable)、有价值的(Valuable)、可估算的(Estimable)、小的(Small)、可测试的(Testable)。
4. 产品策略与路线图
- 精益画布 (Lean Canvas):单页商业计划书。
- 价值主张设计:将产品特性与用户痛点和收益相匹配。
- 路线图规划:现在、下一步、以后(Now, Next, Later)框架。
模板
用户故事模板
**标题**: [简短描述]
**用户故事**:
作为一个 [用户画像],
我想要 [动作/功能],
以便 [收益/价值].
**验收标准**:
1. [标准 1]
2. [标准 2]
3. [标准 3]
**优先级**: [高/中/低]
**备注**: [额外背景信息]PRD 结构
- 简介:背景、目标、范围。
- 用户画像:目标用户的详细信息。
- 用户故事:针对用户的功能列表。
- 功能需求:具体的系统行为。
- 非功能需求:性能、安全性等。
- UI/UX 指南:线框图或参考。
- 数据分析:用于追踪成功的指标。
最佳实践
- 关注成果,而非产出:通过交付的价值来衡量成功,而不是发布的功能数量。
- 爱上问题:不要过早沉迷于具体的解决方案。
- 尽早验证:在构建主要功能之前,使用原型和设计稿测试假设。
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- travisjneuman/.claude★ 106same name
- vasilyu1983/AI-Agents-public★ 94same name
- tstapler/dotfiles★ 8same name
- HK-hub/AgentSkills★ 6same name
- prayceo/claude-skills-public★ 6same name
- foreturn/product-studio★ 3same name
- PhoenixNest/AGENT-GLOBAL-BASE★ 2same name
- aayushus/skills★ 1same name
- arush361/autoresearch-claude-skills★ 1same name
- michaelsvanbeek/personal-agent-skills★ 1same name
5 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- api-designSkill
- database-designSkill
- design-patternSkill
- enterprise-javaSkill
- frontend-reactSkill
- frontend-svelteSkill
- frontend-vueSkill
- git-guruSkill
- go-developmentSkill
- javascript-typescriptSkill
- product-managementSkill
- python-developmentSkill
- session-summarySkill
- swift-developmentSkill
- swiftui-developmentSkill
- system-architectureSkill
- tech-documentationSkill
- testingSkill
- xcode-managementSkill
- api-designSkill
- database-designSkill
- design-patternSkill
- enterprise-javaSkill
- frontend-reactSkill
- frontend-svelteSkill
- frontend-vueSkill
- git-guruSkill
- go-developmentSkill
- javascript-typescriptSkill
- python-developmentSkill
- session-summarySkill
- swift-developmentSkill
- swiftui-developmentSkill
- system-architectureSkill
- tech-documentationSkill
- testingSkill
- xcode-managementSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

