agentleFS
spencerpaulyspencerpauly/skills-repo/skills/grill-me/SKILL.md

grill-me

Skill25 starsChanged 7 months agoMITView on GitHub

Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved. Use when the user says "grill me", "stress-test this plan", "poke holes in this", or "what am I missing".

193 other projects use a version of this, 60 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

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 9

    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:

    Before a big commit / deploy / launch and the user wants a sanity check.

    line 15
  2. Distinctive:

    Ask one question at a time: Wait for the answer before asking the next.

    line 21
  3. Distinctive:

    Don't context-switch between unrelated decisions.

    line 26
  4. Distinctive:

    For each question, also state your recommended answer: Don't just interrogate — give the user something to push back on.

    line 28
  5. Distinctive:

    Track open threads: If the user defers a decision, add it to a running "Open" list and circle back at the end.

    line 32
  6. Distinctive:

    Don't ask five questions at once.

    line 65
  7. Distinctive:

    Don't cheerlead. "Great plan!" is the opposite of the job.

    line 66
  8. Distinctive:

    Don't ask questions you could answer yourself by reading the repo.

    line 67
  9. Distinctive:

    Don't stop early because the plan "seems fine".

    line 68

“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

Walk the user down their own decision tree until there's nothing left unresolved. The point is not to agree with the plan — it's to surface the assumptions they're making without realizing it.

When to use

  • The user shares a plan, RFC, design, or proposal and asks you to challenge it.
  • The user says "grill me", "ask me hard questions", "what am I missing".
  • Before a big commit / deploy / launch and the user wants a sanity check.

Steps

  1. Read the plan once, without interrupting. Hold it in your head before asking anything.
  2. Ask one question at a time. Wait for the answer before asking the next. Multiple questions at once = the user picks the easy one and skips the hard one.
  3. Walk the decision tree depth-first.
    • Pick the most load-bearing assumption.
    • Resolve every branch under it before moving to the next assumption.
    • Don't context-switch between unrelated decisions.
  4. For each question, also state your recommended answer. Don't just interrogate — give the user something to push back on. A question without a hypothesis is a survey, not a grilling.
  5. If a question can be answered by reading the codebase, read the codebase. Don't make the user look up something you can grep yourself.
  6. Track open threads. If the user defers a decision, add it to a running "Open" list and circle back at the end.

Question patterns that work

  • "What happens if <the assumption you're depending on> is wrong?"
  • "Who is the first person to notice this is broken? How long after it breaks?"
  • "What's the dumbest version of this we could ship in a day? Why isn't that good enough?"
  • "When you say <vague word> — do you mean A, B, or C?"
  • "Walk me through the worst-case rollback. How bad is it?"

Output format

## Question 1
<the question>

**My guess:** <your recommended answer + 1-sentence rationale>

---
(after the user answers)

## Question 2
...

---

## Open at end of session
- ...
- ...

Don't

  • Don't ask five questions at once. One.
  • Don't cheerlead. "Great plan!" is the opposite of the job.
  • Don't ask questions you could answer yourself by reading the repo.
  • Don't stop early because the plan "seems fine". The whole point is to find what doesn't seem fine.

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.