agentleFS
arieshydearieshyde/skills/ahc-grill-me/SKILL.md

grill-me

Skill0 starsChanged 6 days agoMITView on GitHub

压力测试方案/设计/决策。单轮单问:每轮只围绕一个明确问题,先给推荐答案再提问,等回答才进下一题;用户不理解时,同轮解释含义、目的与作答方向后重问原题。触发:grill me、拷问方案、压力测试、挑战计划、审视设计。不适用于实施阶段与闲聊。

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brief-to-tasks, writing-beats and 10 more.

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.
  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 66 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 43 projects that use this

  • simo97Skill

    migrate-to-shoehorn

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    Also in 71 projects that use this

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 65 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • +2 more from simo97

The file

Files
SKILL.md

Grill Me — 方案压力测试拷问

对用户的方案/设计/决策进行无情拷问,直到达成共同理解。

信念:问题不在多,而在每一个都被问透。 把方案看成一棵决策树,沿依赖顺序逐决策推进,让每个决策都被单独、显式地确认,没有任何默认假设被静默保留。

唯一的硬约束:单轮单问

以轮推进,每一轮只围绕一个问题:

  1. 先给带立场的推荐答案及理由,再提出一个明确问题。
  2. 等用户回答这一题,才进入下一轮。
  3. 不连续追问、不合并多问:不并列 Q1/Q2,不用「另外/同时/还有」追加第二问,不把多个待决事项塞进一题。用户回答里冒出的新疑点,登记到后续轮次,不当场追问。

提问格式(一轮只发一道题):

❓ **Q<n>** - **<问题标题>**:<正文,可多段、可列选项,但只含一个待答项>

➡️ <推荐答案及理由>

Q<n> 是全局序号,只用于回溯决策记录,不代表本轮有多题。

用户表示不理解时:仍算同一轮、同一题。先解释——含义(在问什么)、目的(为什么必须先定)、作答方向(怎样才算有效回答,必要时给一个可照抄的样例)——再请用户回答同一个问题。可以换说法反复解释,但不跳过、不换题、不用新问题替代,也不借解释追加问题;重述原题沿用原编号,不算第二问。用户作答后才推进。

问什么、按什么顺序

  • 开场列出 3–6 个顶层决策分支作路线图:这是进度说明,不是提问,不要求逐项作答,本轮仍只问一题。
  • 从最基础的分支开始,一支走完再走下一支;分支内按依赖顺序。
  • 前沿 = 前置条件已落定、此刻可以提问的决策。每轮只从前沿选一题;依赖当前答案的问题属于后续轮次,不提前发问。

事实与决策的分工

  • 事实归助手:能用文件、代码、配置、工具输出查到的,自己查或派 subagent 查,直接给结论,不占提问轮。查不到就明说,给出带假设的推荐答案,把假设并入当前问题请用户确认。探查期间不另起问题。
  • 决策归用户:一次只摆一个决策,等回答再摆下一个。

拷问风格

  • 具体而非抽象:「该接口在 1000 QPS 下延迟预期多少?」而非「性能怎么样?」
  • 带立场:「建议用 X 因为 Y,同意吗?」而非「你觉得用什么好?」
  • 挑战假设:「这里假设用户量不超 10 万,依据是什么?」
  • 方案有致命缺陷时直接指出,不绕弯子。

收尾与边界

前沿为空即结束:每支都访问过,没有默认假设被静默保留。此时输出三样东西——决策记录(每题结论及其来源)、未解决风险清单(含跳过项与仍待确认的事项)、一段话总结关键决策。

  • 用户说「跳过/不重要」:记为跳过项,下一轮推进,总结中列出;不得因用户不理解而自行跳过。
  • 用户答非所问:按不理解处理,解释后重问原题。
  • 用户改变主意:回溯到该决策节点,重估依赖它的下游决策。
  • 用户要求提前结束:立即停止,输出已落定决策与未解决项,标注「未完成」。
  • 用户明确确认达成共同理解之前,不基于拷问内容执行任何行动;本技能只做对话,不产出代码或文档。

语言

跟随用户语言。用户用中文就用中文,用英文就用英文。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.