agentleFS
EtanHeyEtanHey/golems/skills/golem-powers/grill-me/SKILL.md

grill-me

Skill0 starsChanged 16 days agoApache-2.0View on GitHub

Design-tree interview. Triggers: grill me, interview my plan, stress-test this design. NOT for implementation or one-question-at-a-time interviews.

193 other projects use a version of this, 7 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

6 rules. 0 are common, 5 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    design tree: every decision branches into the decisions that hang off it.

    line 22
  2. Distinctive:

    Ask the whole frontier in one round.

    line 29
  3. Distinctive:

    Do not block the whole round on that exploration.

    line 43
  4. Distinctive:

    Keep labels short enough to answer by voice in one breath:

    line 51
  5. Very specific:

    Read shorthand such as 1A 2C as the user's decisions.

    line 73
  6. Distinctive:

    Do not act on the plan until the user explicitly confirms shared understanding.

    line 83

“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

Ported and adapted from Matt Pocock's skills/productivity/grilling/SKILL.md and skills/productivity/grill-me/SKILL.md at upstream commit c55ee46073ed923f86ce59a5eb3b6d895095d1b7. Upstream is Copyright (c) 2026 Matt Pocock and MIT licensed; see LICENSE.upstream.

Local shape: the upstream grilling body is folded into this user-invoked skill so a one-line wrapper does not add a second always-on description to the skill roster.

Deliberate local divergence from upstream: retain Etan's voice-friendly lettered options, 1A 2C shorthand, exactly one Recommended label per question, and the final <=6 frozen bullets. A recommendation is never a default.

Interview the user relentlessly until you reach a shared understanding. Map the subject as a design tree: every decision branches into the decisions that hang off it.

Work the whole frontier

Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you have not heard yet.

Ask the whole frontier in one round. Do not impose a fixed question-count cap. Number every question, give it short lettered options, and mark exactly one option Recommended with a one-line reason. Then wait for the user's answers before the next round.

Each round reshapes the tree. Fold in the user's decisions, recompute the frontier, and ask the next round. A question whose answer depends on another open question belongs to a later round, not the current one.

Find facts without blocking the round

Finding facts is your job, never the user's. Read the plan and codebase first. When a frontier question needs a fact from the filesystem, tools, or another available source, dispatch a sub-agent to find it instead of asking the user.

Do not block the whole round on that exploration. Treat the running exploration as an unsettled prerequisite: hold only its downstream questions and ask the rest of the frontier now. Fold the fact into the tree when the sub-agent reports.

Facts belong to the agent. Decisions belong to the user: put every decision to them and wait.

Round format

Keep labels short enough to answer by voice in one breath:

## Round N

1. <question title>: <question body>
   A. <option>
   B. <option> (Recommended: <one-line reason>)
   C. <option>

---

2. <question title>: <question body>
   A. <option> (Recommended: <one-line reason>)
   B. <option>
   C. <option>

Answer like: 1B 2A, or 1B 2: <answer outside the options>

Separate every pair of questions in a round with a horizontal rule.

Read shorthand such as 1A 2C as the user's decisions. If an answer is outside the options, take it verbatim. Never answer for him. Recommended is advice, not a default. Never treat silence as a choice; unanswered questions remain open.

Stop only at shared understanding

The session is ready to close only when the frontier is empty: every branch of the design tree was visited and nothing remains silently assumed. Emit <=6 frozen bullets summarizing the settled decisions and the round that settled each one. Then wait.

Do not act on the plan until the user explicitly confirms shared understanding. If the user names something still open, put it back into the tree and continue.

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.