agentleFS
VladButacuVladButacu/agentkit/skills/grill-me/SKILL.md

grill-me

Skill0 starsChanged 5 days agoMITView on GitHub

Use when a plan or design has consequential unresolved assumptions, requirements or trade-offs, or the user asks to be grilled. Skip settled designs and trivial changes.

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

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 5

    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:

    Use superpowers:brainstorming for from-scratch discovery of what to build.

    line 12
  2. Distinctive:

    Read the supplied context and relevant existing code, glossary and architectural decisions before asking questions.

    line 18
  3. Distinctive:

    Wait for answers before advancing dependent decisions.

    line 22
  4. Distinctive:

    Look up facts yourself using the available tools.

    line 24
  5. Distinctive:

    After each round, carry forward the resolved choices and focus the next round on what they unlock.

    line 26
  6. Very specific:

    Follow the existing documentation layout.

    line 32
  7. Distinctive:

    Create files lazily. Do not produce an ADR for every answer, rewrite global rules, publish tickets, or start implementation as a side …

    line 35

“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

Use superpowers:brainstorming for from-scratch discovery of what to build; this skill pressure-tests a plan or design that already exists.

Reach a shared, evidence-backed understanding of the decisions that matter. Challenge assumptions and ambiguous language, expose consequential trade-offs, and preserve useful conclusions without turning every discussion into a documentation project.

Interview

Read the supplied context and relevant existing code, glossary and architectural decisions before asking questions. Carry forward answers already given. Separate established facts, user preferences and your proposals.

Map the unresolved decisions and their dependencies. Ask a short round of independent questions whose prerequisites are settled. Defer questions that depend on an unanswered choice. Number each question and give your recommendation, its reason and the main trade-off. Make disagreement easy; do not phrase questions to steer the user toward agreement.

Wait for answers before advancing dependent decisions. Use concrete scenarios and counterexamples to expose hidden constraints, failure modes and unclear terms. When terminology or stated behavior conflicts with the project's glossary or code, show the discrepancy and resolve it with the user.

Look up facts yourself using the available tools. Delegate bounded research only when it helps and is permitted. If evidence is unavailable, state the uncertainty instead of asking the user to ratify a guess.

After each round, carry forward the resolved choices and focus the next round on what they unlock. Stop when consequential uncertainties are resolved or explicitly deferred. Do not prolong the interview with speculative choices that would not affect the outcome.

Preserve useful decisions

For project design work, capture resolved terminology and significant decisions when documentation is in scope. Respect requests for discussion only and repository approval rules. With no relevant project or durable conclusion, keep the result in the conversation.

  • Follow the existing documentation layout. If GLOSSARY-MAP.md exists, use it to find the relevant context. Challenge inconsistent vocabulary before recording it.
  • Add or refine a glossary entry only after its meaning is agreed. Keep definitions about the domain, without implementation details. Follow the existing format; for a new glossary, use a context heading and bold terms with one- or two-sentence definitions and any misleading synonyms to avoid.
  • Record an ADR only for a consequential decision that is costly to reverse, surprising without context, and the result of a real trade-off. Follow the existing format; otherwise use the next sequential docs/adr/NNNN-slug.md, a descriptive title and a short paragraph explaining context, decision and reason. Distinguish proposals from accepted decisions.
  • Create files lazily. Do not produce an ADR for every answer, rewrite global rules, publish tickets, or start implementation as a side effect of the interview.

Finish

Give the settled decisions, unresolved or deliberately deferred points, and any documentation changed. Ask the user to confirm that the shared understanding is accurate before proceeding to implementation. Confirmation of the design does not grant unrelated external actions or permissions.

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.