requirement-clarifier
Skill1 starsChanged 3 months agoMITView on GitHub
需求澄清。当用户需求模糊、目标不明确、缺少边界条件或验收标准时,通过多轮提问澄清需求,并输出结构化的需求规格文档。Use when requirements are vague, ambiguous, or lack acceptance criteria before implementation.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- zhouey314-cloud/ai-agent-skillstheir own version, first seen Oct 20, 2026
- kj648/requirement-clarifiertheir own version, first seen Aug 27, 2026
- yingzhengzhang06-sys/requirement-clarifiertheir own version, first seen Jun 23, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- kj648/requirement-clarifier★ 2same name
- yingzhengzhang06-sys/requirement-clarifier★ 1same name
- zhouey314-cloud/ai-agent-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 repository28 other files it gives its agents.
- api-contract-designerSkill
- api-testerSkill
- bug-diagnoserSkill
- cache-governorSkill
- ci-cd-setupSkill
- code-migratorSkill
- code-reviewerSkill
- commit-message-writerSkill
- db-migration-reviewerSkill
- db-schema-designerSkill
- dev-env-troubleshooterSkill
- frontend-debugSkill
- git-workflowSkill
- log-analysisSkill
- meeting-minutesSkill
- natural-chinese-writerSkill
- performance-profilerSkill
- release-note-writerSkill
- requirements-reviewerSkill
- security-reviewerSkill
- skill-creator-cnSkill
- skill-style-guideSkill
- sql-reviewerSkill
- task-decomposerSkill
- tdd-workflowSkill
- tech-design-writerSkill
- tech-doc-writerSkill
- weekly-reportSkill
The file
Files
需求澄清
何时使用
- 用户给出一段模糊的功能描述,如"帮我做一个博客系统""我想加个搜索功能";
- 实现前发现需求缺少边界条件、用户场景或验收标准;
- 用户说"需求不太清楚""你先帮我理理";
- 任何可能因理解偏差导致返工的开发任务开始前。
使用步骤
第 1 步:识别需求来源
先确认三件事:
- 需求提出者是谁(产品、老板、客户、自己);
- 这个需求要解决什么问题(而不是"要做什么功能");
- 截止时间或优先级要求。
第 2 步:逐项提问澄清
按以下清单提问,一次只问一组,用户回答后再进入下一组:
| 维度 | 关键问题 |
| 目标 | 这个功能最终要达成什么结果?成功标准是什么? |
| 范围 | 哪些必须做?哪些明确不做? |
| 用户 | 谁在用?使用频率和使用场景? |
| 边界 | 输入是什么?输出是什么?异常情况怎么处理? |
| 验收 | 怎么做才算"完成"?有没有可量化的标准? |
| 约束 | 技术栈、性能、安全、合规、预算、时间限制? |
第 3 步:复述确认
分维度提问清单、最短提问组合和常见坑见 references/QUESTION_TEMPLATES.md。
用一段话复述你对需求的理解,请用户确认或纠正:
我的理解是:你要为【用户】实现【功能】,目标是【结果】,
核心场景是【场景】,验收标准是【标准】,约束是【约束】。
对吗?第 4 步:输出需求规格文档
按 references/SPEC_TEMPLATE.md 的结构整理(直接输出在对话中,或应要求写入文件)。写完用 spec_checker.py 自查,补上标出的缺口(见下面的辅助脚本)。
输入与输出
- 输入:一段需求描述(文字、语音转写、口头说明均可);
- 输出:需求规格文档 + 待确认问题清单。
示例
用户输入: "帮我做一个待办事项 App。"
澄清提问(节选):
- "待办事项 App 要解决什么问题?是个人使用还是团队使用?"
- "需要哪些功能?比如添加、编辑、删除、提醒、分类?"
- "数据存在哪里?本地还是云端?要不要多设备同步?"
- "验收标准是什么?比如:能添加任务、能在今天/明天/逾期之间切换?"
需求规格节选:
## 功能范围
- 必须做:任务的增删改查、完成状态切换、按日期分组
- 不做:提醒推送、多端同步、团队协作
## 验收标准
- 用户能添加任务,输入标题和日期
- 用户能勾选完成,任务进入"已完成"列表
- 任务按日期分组展示(今天/明天/更晚)辅助脚本
scripts/spec_checker.py 检查需求规格文档的完整性:必需章节是否齐全、章节是否为空、验收标准是否含糊、有无未填占位符:
python skills/requirement-clarifier/scripts/spec_checker.py <需求规格.md>模板见 references/SPEC_TEMPLATE.md。脚本只做标记,结论需要人确认。
注意事项
- 不要跳步:不要听完需求就直接写代码,先澄清再实现;
- 不要替用户决定:涉及取舍(如"要不要提醒功能")时,列出选项让用户选;
- 区分"要什么"和"怎么要":用户常直接说方案("加个数据库"),要追问目标("解决什么问题");
- 用户不耐烦时,最少问 3 个最关键的问题(目标、范围、验收),然后输出带"待确认问题"的初稿。
不适用场景
- 需求已经清晰且有明确验收标准;
- 用户只需要简单问答,不需要文档化;
- 纯技术咨询(如"这个 API 怎么用"),不属于需求澄清。
验证方式
- 触发:用"帮我把这个需求理清楚"或一段模糊需求描述触发;
- 检查:输出包含背景、范围、验收标准、边界、待确认问题;
- 跑脚本:
python skills/requirement-clarifier/scripts/spec_checker.py <输出文档>,无"必须"级问题; - 确认:用户对复述内容无异议,或只做了少量修正。
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.

