agentleFS
LeonardoEnnesLeonardoEnnes/ai-engineering-toolkit/.agents/skills/grill-me/SKILL.md

grill-me

Skill0 starsChanged 12 days agoApache-2.0View on GitHub

Adversarial interrogation. When a plan, idea or decision must be stress-tested before committing, grill the user with hard questions that expose unstated assumptions. Triggers: "/grill", "grill me", "me grelha".

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

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

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read it adversarially: hunt for unstated assumptions, undefined success criteria, hidden dependencies, irreversible costs and every "we …

    line 14
  2. Distinctive:

    Ask ONE question at a time.

    line 16
  3. Distinctive:

    Follow the thread. Do not rescue the proposal and do not answer your own questions.

    line 20

“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 — put the plan in the hot seat

The user asks to be grilled when they want their own proposal attacked, not approved. Your job is to find the holes, not to be pleasant.

When triggered, execute:

  1. Restate the proposal in ONE sentence. If you cannot, the proposal is not clear yet — that is the first finding, and you stop and ask for the missing definition.
  2. Read it adversarially: hunt for unstated assumptions, undefined success criteria, hidden dependencies, irreversible costs and every "we will figure it out later" clause.
  3. Ask ONE question at a time. Never dump a list. Start from the weakest assumption and wait for the answer before the next question.
  4. Reject vague answers. For every "scalable", "simple", "soon", "it will be fast", "users will like it", demand the number, the date, the owner, the fallback or the evidence. Do not move on until it is concrete or the user admits the gap.
  5. Follow the thread. Do not rescue the proposal and do not answer your own questions.
  6. Minimum bar: at least 5 questions, or until two concrete holes are exposed.

Close with the fixed verdict:

GRILLED: <the proposal in one sentence>
HOLES: <the assumptions that did not survive>
HARDEST QUESTION: <the one that was still dodged>
NEXT STEP: <a single testable action, or "kill it">

Verification checklist

  • Exactly one question asked at a time.
  • Every vague term challenged with a concrete demand.
  • At least the weakest assumption surfaced.
  • Closed in the fixed verdict format.

Antipatterns (do NOT do)

  • Dumping 20 bulleted questions at once.
  • Accepting the first answer.
  • Softening the question to stay polite.
  • Answering your own question or defending the proposal for the user.
  • Ending without a verdict.

Boundary

This skill only interrogates. It does not implement, does not make the decision for the user, and does not replace the verdict of council, security-audit or performance-audit.

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.