agentleFS
Sign inStart free
tovrleaftovrleaf/openkata/skills/grill-me/SKILL.md

grill-me

Skill1 starsChanged 14 days agoMITView on GitHub

Challenge a plan, spec, ADR, or design by interviewing the user relentlessly until all corners are covered. Identifies edge cases, questions assumptions, probes failure modes, and surfaces missing requirements. Use when the user wants to stress-test a plan, get grilled on their design, says "grill me", "challenge this", or "poke holes in this."

193 other projects use a version of this, 62 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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After grilling a spec, the summary looks like:

    line 57
  2. Very specific:

    Every decision entry MUST follow this exact pattern: Topic — Decision.

    line 85
  3. Distinctive:

    Do not omit the reason or the rejected alternatives.

    line 87
  4. Distinctive:

    Does NOT modify files without asking first

    line 94
  5. Distinctive:

    Does NOT implement code changes — only updates plans

    line 95

“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

Grill Me

Challenge the user's plan until every decision is explicit and every corner case is addressed.

Workflow

  1. Read the artifact — Read the spec, ADR, design, or plan the user wants challenged. Understand the full scope before asking anything.
  2. Identify decision branches — Map out the areas where decisions were made or left implicit: trade-offs, edge cases, missing alternatives, unstated assumptions, dependencies.
  3. Interview one question at a time — Ask exactly ONE question per message. Never combine multiple questions. For each question, state YOUR recommended answer first, then ask the user to confirm, correct, or expand. Wait for a response before the next question. If a question can be answered by exploring the codebase, explore the codebase instead of asking.
  4. Continue until covered — Keep going until all branches are resolved. Do not stop early. The goal is shared understanding, not speed.
  5. Summarize — When complete, summarize using the format from Example Output. Each decision entry MUST include: (1) the decision made, (2) the reason it was chosen, and (3) what was rejected or considered. Do not list decisions without reasons.
  6. Offer to update (mandatory) — Always end with the literal line: "Want me to apply these changes to [artifact name]?" where [artifact name] is the specific file being grilled (e.g., "spec.md", "design.md", "0003-use-postgres.md"). This MUST be the final line of your output. Update the artifact only if the user confirms; otherwise leave it unchanged.

Example Output

After grilling a spec, the summary looks like:

## Decisions Made

1. **Auth strategy** — JWT with refresh tokens. Reason:
   stateless scaling requirement eliminates session affinity.
   Rejected: server-side sessions (scaling cost), API keys
   only (no refresh mechanism).
2. **Rate limiting** — Per-user at API gateway. Reason:
   prevents single-user abuse without penalizing shared IPs.
   Rejected: per-IP (punishes NAT users), no limiting
   (risk of runaway costs).
3. **Error format** — RFC 7807 Problem Details. Reason:
   standard format reduces client integration effort.
   Rejected: custom envelope (non-standard, more docs
   needed), plain text (no machine parsing).

## Changes to Apply

- Add "Rate Limiting" section to spec with per-user strategy
- Update Non-goals: remove "session management" (now in scope
  as JWT refresh)
- Add dependency: API gateway must support per-user rate limits

Want me to apply these changes to spec.md?

Every decision entry MUST follow this exact pattern: **Topic** — Decision. Reason: why. Rejected: alternatives. Do not omit the reason or the rejected alternatives.

Boundaries

  • DOES read specs, ADRs, designs, plans, and codebase
  • DOES challenge assumptions and identify gaps
  • DOES update the artifact only when user explicitly confirms
  • Does NOT modify files without asking first
  • Does NOT implement code changes — only updates plans

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