product-brief
Skill82 starsChanged yesterdayMITView on GitHub
通过 Mom Test 风格的结构化问卷访谈,把"一句话产品想法"收敛成一份陌生工程师也能看懂的产品 Brief,含定位、用户、痛点、场景、边界、能力边界与成功指标,支持快速、标准、深度三档 × 自主与委托决策模式,并完成 AI 轨道判定。当用户说"帮我把这个 idea 整理成文档"、"写个产品 brief 或 PRD"、"帮我梳理一下产品需求和背景"、"我有个想法你帮我理清楚"时使用。用户要的是从调研到开发的完整一条龙时,改用 Vibe_helper 全流程。English: Mom Test style interview that turns a one-sentence idea into an engineer-ready product brief with boundaries, capability limits for AI products, and AI-track detection, in three depth tiers. Use when the user asks to "turn this idea into a document", "write a brief or PRD", or "help me clarify this idea"; for the full research-to-handoff pipeline use Vibe_helper instead.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- mannobeats/hyper-tastetheir own version, first seen Nov 16, 2026
- Job-Yang/jobbyang-ai-skillstheir own version, first seen Nov 6, 2026
- Job-Yang/jobyang-ai-skillstheir own version, first seen Nov 6, 2026
- MarkTripoli/skillstheir own version, first seen Nov 1, 2026
- vindreshsingh/engineering-skillstheir own version, first seen Oct 20, 2026
- rterakedis/leanwheel-skillstheir own version, first seen Oct 17, 2026
Used with
Projects with it also use decision-log and setup.
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.
nandanosqlSkilldecision-log
Document product decisions with context, alternatives considered, rationale, and revisit criteria. Creates institutional memory that prevents re-litigating settled decisions.
Also in 3 projects that use this
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- emotixco/claude-skills-founder★ 796same name
- davekilleen/Dex★ 509same name
- Job-Yang/jobbyang-ai-skills★ 100same name
- Job-Yang/jobyang-ai-skills★ 100same name
- lglucas/ai-dev-operating-system★ 12same name
- MarkTripoli/skills★ 2same name
- rterakedis/leanwheel-skills★ 2same name
- tolgalogy/agentic-development-framework★ 2same name
- erik-kroon/skills★ 1same name
- mannobeats/hyper-taste★ 1same name
2 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 repository5 other files it gives its agents.
- competitive-analysisSkill
- requirements-layeringSkill
- tech-frameworkSkill
- user-voiceSkill
- Vibe_helperSkill
The file
Files
Product Brief:从模糊想法到结构化 Brief
语言规则:全程跟随用户语言。提问、01 与 02 的正文用用户的语言;编号文件名与小节标题保持模板原样。
把用户脑子里的一段口语描述,变成一份消除所有模糊词的产品 Brief。这份文档是后续一切工作,含竞品调研、需求分层、开发,的地基。
在 Vibe_helper 全流程中对应 Stage 1 加 Stage 2,读写同一套文件;单独使用时本 skill 独立完成全流程。
输入
- 用户给的一段话或一个名字,最常见
- 已有
02-brief.md说明用户是想修订:先读现有文档,问"要改哪里",不要重新访谈 - 已有竞品或调研材料则直接吸收进 Brief 的"现有方案"部分
信息不足时按 references/questionnaire.md 的问卷访谈,不要脑补答案。
深度档位,开场确认,默认标准
| 档位 | 访谈 | 产出 |
| 快速 | 4 组核心问题:定位、用户、核心功能、成功标准 | 一页 Brief |
| 标准,默认 | 完整问卷 7 组,模糊处追问 1–2 轮 | 完整 Brief |
| 深度 | 完整问卷,追问 2 轮,加"上一次遇到这个问题"完整叙事 | 完整 Brief 加待验证假设清单 |
步骤
- 访谈:按
references/questionnaire.md。核心纪律是 Mom Test:问过去的真实行为,不问未来的意愿。"你上一次遇到这个问题是什么时候、怎么解决的"远比"你会用吗"可信。答不出"上次遇到"即需求存疑信号,记入"待补充/存疑"。第 0 组先收已有材料,用户自有的研究与数据直接吸收,标 [A:用户提供];末组必问 AI 轨道判定,含 AI 扮演什么角色、拿掉 AI 剩什么、AI 答错时用户看到什么。开场顺带确认决策模式,自主或委托 - 落盘
01-问卷.md,深度档必做;快速档可直接并进 Brief 的"访谈记录"节。带版本头 v1,含 AI 轨道判定小节 - 组装状态卡 v1 并确认:按
references/context-assembly.md生成00-状态.mdv1,内容为问卷纪要:定位、用户、功能清单原始、约束、成功标准、存疑项、AI 轨道判定、决策模式。展示给用户:"这是我对问卷的记录,有没有记错的、漏掉的?"用户同意才写 Brief;快速档与 Brief 确认门合并为一次停顿;委托模式给回执式确认 - 重写成 Brief:按
references/prompt-refinement.md模板与好、坏对照。要点:第一屏决策面板;具体到可执行,说"3 步压到 1 步"而不是"提升效率";明确不做什么与做什么同等重要;AI 轨道必写能力边界,含适用域、水平线、不保证,敢承诺不过头;功能清单保留用户原话不评判 - 确认门:自主模式展示 Brief,明确问"以上理解是否准确?有没有要补充或修改的?"修正最多 3 轮,超过 3 轮改为列分歧点逐条拍板。委托模式:出决策回执,≤5 项代定取舍用白话且可否决,另拿 Brief 关键事实问 2 道白话题,答对即过。落盘前跑陌生人回译自检:新会话只读 Brief 复述,偏离处即歧义处
- 用户确认后落盘
02-brief.md,版本头 v1;委托模式头部汇总 [B/C·代定] 计数;并在同一步刷新 00-状态.md v2,吸收明确不做、能力边界与非功能需求
Common Pitfalls
- 诱导性提问:"是不是觉得很麻烦?"把答案塞进了问题,收获的是客气话
- 问未来不问过去:"你会用吗"的信息量是零
- 跳过纪要确认直接写 Brief:先确认事实记录即 00 v1,再确认理解取舍即 Brief,两道门不是重复
- 修改已确认文档不更新版本:改 01/02 必须版本加 1 并加变更行,同一步刷新 00
- 模糊词过关:"功能丰富、体验流畅、类似 XX"留在 Brief 里,工程师还是不知道做什么
- 边界缺失:不写"明确不做",MVP 必然越做越大
- AI 轨道漏判或能力边界空泛:AI 产品不判轨道,后面 08-评测方案整条线断掉;能力边界写"支持各种文档"这种话,等于给用户递刀子
- 委托不留痕:代定取舍不标 [B/C·代定]、不给回执。委托不降低诚实度,只改变信任标记
- 替用户补答案:用户没说的就标"待补充",不要用"应该是想"填空
- 把功能清单提前评判或删减:访谈阶段原样记录,取舍是需求分层阶段的事
- 语言不跟用户:用户用英文仍用中文提问与写文档正文
输出物
00-状态.md,v1 起,用户确认01-问卷.md,标准与深度档,带版本头02-brief.md,用户确认后,带版本头
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.

