to-questionnaire
Skill27 starsChanged 3 months agoMITView on GitHub
把一个你无法完全回答的决策变成一份问卷,交给别人填写。
Files
把用户无法独自回答的东西,变成一份问卷——一份 Markdown 文档,交给某个人异步填写,或者双方在会议上一起填。收件人掌握着用户所缺的知识;问卷把它从他们身上引出来。
拷问“这次发送”,而不是主题。 只就发送一事拷问用户,这是他们始终能回答的:发给谁,以及需要拿回什么。文档里的问题随后瞄准收件人所知与用户所需之间的缺口。
- 它发给谁? 在一次交流中,问清收件人的角色、专长以及与用户的关系。这确定了问卷的语气,以及它必须携带多少上下文。当你知道收件人是谁、以及他们掌握而用户不掌握的是什么时,即完成。
- 你需要拿回什么? 在一次交流中,问清用户无法独自解决、需要从这个人那里获得的具体决策或事实。当你有了一份具体清单——列出用户最终必须能做或能决定的事——即完成。
- 写问卷。 依据第 1–2 步找到的缺口起草问题,遵循下面的“文档结构”。把它写入当前目录下的
to-questionnaire-<slug>.md(slug 取自主题)并回报路径。当文件存在、且用户在第 2 步指明的每一项都有一个问题覆盖时,即完成。
文档结构
把文档定位为一份探索性问卷:用户缺上下文,收件人握有它。问题按最重要在前排序——异步意味着你可能只有一轮机会——并在问题超过寥寥几个时,用 ## 标题按主题分组。使用下面的模板来写。
<questionnaire-template><问卷标题>
目的: 这份问卷为何存在,以及依赖它的决策是什么。
发件人: <用户> — 收件人: <收件人> — 你的回答将如何被使用: <它们的去向>
背景
一段话,为不了解用户脑中所想的收件人提供方位。够回答好即可,别写成一整页。
如何作答
截止时间与大致工作量。部分回答和“我不知道”都是有用的——对任何不确定的地方做出标记,而不要跳过它。
<主题标题>
每个主题一个 ## 小节。每个小节下放其问题,最重要在前。每个问题只包含一个想法——绝不复合——正下方紧跟一个答案存根,并且只有在问题可能被误读或会招来敷衍答案时,才加一行 为什么这很重要。
<question-example>
### 系统在上线时预期要承受多大负载?为什么这很重要:它决定我们现在就为突发流量做资源预留,还是先推迟。
</question-example>还有别的吗?
一个收尾的兜底问题:有没有什么我们没问到、但我们应当知道的?
</questionnaire-template>Other versions117 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 117
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- ArcReel/ArcReel★ 6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
- moeru-ai/xsai★ 665same name
- devcxl/mattpocock-skills-zh★ 522same name
- aws/graph-explorer★ 489same name
- itsmylife44/cliproxyapi-dashboard★ 281same name
107 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.
Used alongsideProjects with it also use setup-skills and chief-of-staff.
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.
GitHubSkillsetup-skills
Configures shared sources and drafts context with independent writers. Plain/fresh setup offers installation of user-named packages and reuses built-in browser capabilities, adding browser tooling only for an evidenced required-check gap. Use for setup, source repair, writing context or refreshing drafts. Configure-only skips tooling and authoring; installations and activation require separate approval.
Also in 6 projects that use this
getnaoSkillchief-of-staff
Also in 10 projects that use this
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ask-mattSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- setup-matt-pocock-skillsSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- wizardSkill
- claude-handoffSkill
- loop-meSkill
- setup-ts-deep-modulesSkill
- writing-beatsSkill
- writing-fragmentsSkill
- writing-shapeSkill
- git-guardrails-claude-codeSkill
- migrate-to-shoehornSkill
- scaffold-exercisesSkill
- setup-pre-commitSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- teachSkill
- wait-whatSkill
- writing-for-agentsSkill
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.

