agentleFS
Sign inStart free
emiliosheinzemiliosheinz/agent-skills/grill-me/SKILL.md

grill-me

Skill20 starsChanged 28 days agoMITView on GitHub

Grills the user about a plan, decision, or idea through structured AskUserQuestion rounds, until every branch of it is settled. TRIGGER when: the user says "grill me" or "grill", asks to stress-test or poke holes in their thinking, asks to be challenged on a plan or decision, or asks what they have not thought of. SKIP for: questions the codebase or the web can answer, capturing requirements for a change (use `/forge specify`), and a decision already made (use `/create-adr`).

193 other projects use a version of this, 7 of them edited.

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

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Ask every question with the AskUserQuestion tool.

    line 19
  2. Very specific:

    Use preview when the user must compare concrete artifacts: code snippets, config, ASCII layouts, diagrams.

    line 26
  3. Distinctive:

    Read each answer carefully.

    line 29
  4. Distinctive:

    No emojis anywhere: not in questions, options, headers, previews, or summaries.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 177 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

Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.

Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round, then wait for the user's answers before the next round.

Asking a round

Ask every question with the AskUserQuestion tool. Never ask frontier questions as plain chat text.

  • One tool call holds at most 4 questions. When the frontier is larger, ask it in consecutive calls of up to 4, most load-bearing questions first, before recomputing the frontier.
  • question: the full question, ending with a question mark. Include the context the user needs to decide; keep it self-contained.
  • header: a short chip label, 12 characters max.
  • options: 2 to 4 concrete, mutually exclusive choices, each with a description stating its trade-off. Put your recommended answer first and append (Recommended) to its label. Do not add an "Other" option; the tool provides one.
  • Set multiSelect: true only when the choices genuinely combine.
  • Use preview when the user must compare concrete artifacts: code snippets, config, ASCII layouts, diagrams.
  • Open-ended questions still get options: offer the most plausible answers you can infer, and let "Other" catch the rest.

Read each answer carefully. A free-text "Other" answer may reject the premise, ask for clarification, or open a new branch; treat it as such rather than forcing it into the tree you expected.

Recomputing the frontier

Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.

Facts versus decisions

Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.

Finishing

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Summarize the settled decisions as a plain list, then confirm with one final AskUserQuestion call whether you have reached a shared understanding. Do not act on it until the user confirms.

Style

No emojis anywhere: not in questions, options, headers, previews, or summaries.

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.

Check your setup, free