agentleFS
FAHTHIZFAHTHIZ/oasis/skills/grill-me/SKILL.md

grill-me

Skill4 starsChanged 9 days agoApache-2.0View on GitHub

Interview the user one question at a time to pin down a vague idea, feature or plan before any code is written. Use when the user says "grill me", wants to think a design through, or the request is too fuzzy to plan.

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

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read just enough of the workspace (README, OASIS.md / AGENTS.md, the files the idea touches) to avoid asking things the code already …

    line 12
  2. Distinctive:

    Keep a private list of open decisions, ordered by how much each one changes the work: goal and users, scope and non-goals, data and …

    line 13
  3. Very specific:

    Ask one question per turn, using ask_user_question when it is available.

    line 14
  4. Distinctive:

    Stop asking when the remaining questions would not change the plan, or after about 12 questions, or when the user says stop.

    line 16
  5. Very specific:

    Write the brief: goal, users, in scope, out of scope, decisions made (with the reason), acceptance criteria, risks and open questions.

    line 17
  6. Distinctive:

    Read-only workspace inspection during the interview.

    line 21
  7. Distinctive:

    Every question was specific, answerable, and changed or confirmed a decision.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 178 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Grill-me skill

Purpose

Turn a fuzzy idea into a sharp, written brief by asking the user hard, specific questions, one at a time, until every decision that changes the implementation is made. Do not implement anything during the interview.

Workflow

  1. Read just enough of the workspace (README, OASIS.md / AGENTS.md, the files the idea touches) to avoid asking things the code already answers. Never ask what you can look up.
  2. Keep a private list of open decisions, ordered by how much each one changes the work: goal and users, scope and non-goals, data and interfaces, edge cases and failure behavior, security and privacy, performance limits, compatibility, testing and rollout.
  3. Ask one question per turn, using ask_user_question when it is available. Make each question concrete, offer 2-4 plausible answers with their trade-offs, and say which one you would pick and why. Accept "you decide" and record your choice.
  4. Push back on vague or contradictory answers: name the conflict and ask which wins. Challenge assumptions the user seems unsure about, and point out cheaper options when they exist.
  5. Stop asking when the remaining questions would not change the plan, or after about 12 questions, or when the user says stop. Do not drag the interview out.
  6. Write the brief: goal, users, in scope, out of scope, decisions made (with the reason), acceptance criteria, risks and open questions. Save it as docs/briefs/<topic>.md only if the user agrees; otherwise show it in chat.
  7. Offer the next step: /plan on the brief, or start implementing.

Permissions

  • Read-only workspace inspection during the interview. The only write is the optional brief file, with the user's agreement.

Success criteria

  • Every question was specific, answerable, and changed or confirmed a decision.
  • The brief has testable acceptance criteria and explicit non-goals.
  • Facts from the code are separated from the user's decisions and your assumptions.

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.