requirements-analysis
Skill0 starsChanged 8 months agoMITView on GitHub
从产品原型或用户描述中梳理功能点与细节要求,产出结构化需求文档。全栈工作流第 1 阶段。
9 other projects use a version of this.
Adopted by
Most recently taken up by
- MsNan/bishe-doc-skillstheir own version, first seen Oct 25, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- balaji-balu/spec-contractstheir own version, first seen Oct 13, 2026
- Alteriom/ai-dev-skillstheir own version, first seen Oct 11, 2026
- m16khb-org/issueopstheir own version, first seen Sep 24, 2026
- karthikrshet/aiskillstheir own version, first seen Aug 20, 2026
Used with
Projects with it also use code-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- m16khb-org/issueops★ 6same name
- viacheslav-tronko/claude-code-harness★ 6same name
- karthikrshet/aiskills★ 4same name
- yinhunfeixue/software_development_skills★ 4same name
- balaji-balu/spec-contracts★ 1same name
- KMaruthi2002/universal-llm-skills★ 1same name
- youjun011/skills★ 1same name
- Alteriom/ai-dev-skills★ 0same name
- MsNan/bishe-doc-skills★ 0same name
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 repository10 other files it gives its agents.
- .claude/skills/CLAUDE.mdCLAUDE.md
- code-developmentSkill
- dev-workflowSkill
- history-managerSkill
- program-designSkill
- self-verificationSkill
- task-breakdownSkill
- technical-reviewSkill
- technology-selectionSkill
- unit-testingSkill
The file
Files
需求分析
何时使用
- 用户描述了产品想法、提供了原型文档或需求草稿,需要整理成可执行需求时。
- 全栈工作流第 1 阶段,由编排器调用。
与用户交流(必须)
本阶段在主对话中执行,需与用户多轮对话,不得臆造需求。
交互原则
- 对模糊点必须用 1~3 轮提问补全,等待用户回复后再写入文档。
- 所有决策点都应以结构化选项呈现,让用户选择而非自由输入。例如向用户提供编号选项("请选择 1/2/3"),可同时选多个时说明"可多选"。
- 允许用户在选项之外补充说明(如选了"其他"后追加描述)。
- 一次不要问超过 3 个问题,避免用户信息过载。
执行要点
- 原型/文档识别:若用户提供了产品原型截图、PRD 文档或草稿,先提取其中的功能描述与页面流程。
- 功能点梳理:按「功能模块 → 功能点」提取列表,不遗漏、不臆造。每个功能点含简要描述与输入输出。
- 用户故事:核心功能点转写为用户故事格式(As a ... I want ... So that ...)。
- 验收标准:每个功能点附 1~3 条验收标准(Given/When/Then 或要点式)。
- 细节追问:对模糊点(角色、边界、数据来源、异常情况)用 1~3 轮简短提问补全,等待用户回复后再写入。
- 输出格式:使用 templates/requirements-template.md 填写并产出需求文档。
结构化提问引导
以下每组为一轮提问。每轮向用户呈现结构化选项,用户选择后再进入下一轮。
第 1 轮:基础信息
向用户确认以下内容(可合并为一组选项):
Q1 — 是否有原型图或设计稿?
- A. 有(原型图/设计稿/Figma 链接等)
- B. 有参考网站或竞品
- C. 都没有,从零开始
Q2 — 项目涉及哪些端?
- A. 前端 + 后端(全栈)
- B. 仅前端
- C. 仅后端
Q3 — 用户角色?(可多选)
- A. 仅单角色(无权限区分)
- B. 普通用户 + 管理员
- C. 多角色(3 种及以上),请简要说明
第 2 轮:前端 UI/UX 偏好(Q1 选 C 时必问)
若用户没有原型图/设计稿,向用户呈现以下选项:
Q4 — 整体风格?
- A. 现代简约(参考 Linear / Notion)
- B. 商务正式(参考企业后台)
- C. 科技感 / 仪表盘风格
- D. 其他(请补充或提供参考网站)
Q5 — 主色调?
- A. 蓝色系
- B. 绿色系
- C. 紫色系
- D. 暗色系(深色背景)
- E. 其他(请说明色值或偏好)
Q6 — 布局方式?
- A. 侧边栏导航(左侧菜单 + 右侧内容)
- B. 顶部导航栏
- C. 无导航(单页/落地页)
- D. 其他
Q7 — 响应式需求?
- A. 仅桌面端
- B. 桌面 + 平板
- C. 全端适配(桌面 + 平板 + 手机)
- D. 移动端优先
Q8 — 是否需要暗色模式?
- A. 需要
- B. 不需要
- C. 后续再说
第 3 轮:后端架构偏好(项目涉及后端且未明确时必问)
Q9 — API 风格?
- A. RESTful
- B. GraphQL
- C. 无偏好,你来推荐
Q10 — 认证方式?
- A. JWT(无状态)
- B. Session(有状态)
- C. OAuth2 第三方登录
- D. 暂不需要认证
Q11 — 数据库偏好?
- A. MySQL
- B. PostgreSQL
- C. MongoDB
- D. SQLite(轻量/嵌入式)
- E. 无偏好
Q12 — 是否需要 API 文档自动生成(Swagger/OpenAPI)?
- A. 需要
- B. 不需要
- C. 后续再说
第 4 轮:补充确认
根据用户前面的回答,对仍有模糊的业务流程、异常分支、非功能需求进行针对性追问。此轮可使用开放式问题。
辅助资料
- 完整示例输出:examples/sample-output.md — 展示一份合格需求文档的完整结构与内容深度
- 编写参考:reference.md — 用户故事 INVEST 原则、验收标准写法、常见追问清单
产出
- 一份按模板填写的需求文档,供「技术选型」与后续阶段使用。
文档与状态
- 产出写入
docs/{current_iteration_id}/requirements-{requirements_id}.md。 - 开始前:调用
history-managerskill 的get-phase requirements和check-file确认是否已完成。 - 完成后:调用
history-managerskill 的set-phase requirements {requirements_id}记录并推进状态。
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.

