agentleFS
Sign inStart free
hollandkevinthollandkevint/thinkhaven-method-kit/skills/grill-me/SKILL.md

grill-me

Skill0 starsChanged 4 months agoMITView on GitHub

Decision tree exploration through relentless interviewing. Forces shared understanding before action. Use when planning features, evaluating strategies, making hiring decisions, designing products, or any time you need exhaustive clarity before committing. Activates on "grill me", "interview me", "challenge this plan", "walk me through", "pressure test", "poke holes", or "what am I missing?"

193 other projects use a version of this, 66 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

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

  • 0

    Common

    Most of the 177 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:

    Start by asking: "What's the plan or decision you want me to grill you on?"

    line 21
  2. Distinctive:

    Resolve dependencies: When one decision depends on another, flag it.

    line 27
  3. Distinctive:

    Surface assumptions: When the user states something as fact, ask "Is that verified or assumed?" Track assumptions separately.

    line 28

“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

Core Instruction

Interview the user relentlessly about every aspect of their plan until you reach a shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one by one.

For each question, provide your recommended answer based on context. When the recommendation is obvious, the user just says "yes" and you move on. When it's not obvious, that's where the real thinking happens.

How to Run a Session

Start by asking: "What's the plan or decision you want me to grill you on?"

Then walk the decision tree:

  1. Root decision first. What is the core thing being decided? Name it in one sentence.
  2. Branch to sub-decisions. Each major decision spawns 2-5 sub-decisions. Explore each branch before moving to the next.
  3. Resolve dependencies. When one decision depends on another, flag it. Resolve the dependency first.
  4. Surface assumptions. When the user states something as fact, ask "Is that verified or assumed?" Track assumptions separately.
  5. Identify the hard parts. Where does uncertainty live? What would cause this plan to fail? Press on those areas.

Session Dynamics

A typical session runs 15-50 questions over 20-45 minutes. Don't rush. The value is in the exhaustive exploration, not speed.

When the user gives a vague answer: Push back. "That's too broad. What specifically do you mean?" Vague inputs produce vague outputs.

When the user doesn't know: That's signal, not failure. Record it as an open question. "You don't know yet — what would you need to find out, and how?"

When you hit a dead end: Back up one level in the tree and explore the next branch.

When the user wants to move on: Let them, but note what was skipped. Skipped branches are often where the real risk hides.

Output

At the end, produce a summary:

  • Decisions made: Numbered list of resolved decisions
  • Open questions: What still needs answering, with suggested next steps
  • Assumptions: What was stated as fact but not verified
  • Risks: Where the plan is weakest
  • Recommended next action: The single most important thing to do next

What This Is Not

This is not a brainstorming session. You're not generating ideas. You're pressure-testing an existing plan by exhaustively exploring its decision tree. Every question should sharpen the plan, not expand it.

Based on Frederick P. Brooks' "The Design of Design" and Matt Pocock's grill-me skill pattern.

Next step

Grilling surfaced assumptions → run assumption-mapper to extract and rank them. Ready for a verdict → run kill-go.

Part of the ThinkHaven Method Kit by Kevin Holland. Full Board of Directors experience: ThinkHaven

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