agentleFS
Sign inStart free
yokeloopyokeloop/yoke/skills/grill/SKILL.md

grill

Skill1 starsChanged 4 months agoMITView on GitHub

Interviews the user one interactive question at a time about a plan or design, walking each branch of the decision tree to a shared understanding; every question offers a recommended answer. A read-only interview that writes no files — for the variant that also captures terminology and decisions into .yoke/context.md and ADRs, use grill-docs. Activates when the user writes "grill", "grill me", "poke holes in this", "interrogate my design", "challenge my plan", "stress-test my plan", "interview me about this".

87 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use write-skill, root-cause 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.
  • NoaiRoxSkill

    write-skill

    Use when creating a new skill, editing an existing skill, or verifying a skill works before deployment.

    Also in 5 projects that use this

  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 4 projects that use this

  • Neko-Catpital-LabsSkill

    prove-it

    Shared evidence rule for investigating, diagnosing, debugging, proving, or explaining what happened or why for any problem or situation: do not assert something is fixed, working, passing, merged, or running unless you personally observed it this turn and can show what you saw; do not assert it was caused by X until a repro and controlled isolation prove that cause.

    Also in 4 projects that use this

  • sahinSkill

    execute

    Also in 5 projects that use this

  • assisjpSkill

    file-pr

    Prepare and open or update an authorized pull request with a concise problem-first description and verifiable evidence. Use when the user asks to create, file, open, or update a PR. Do not use merely to review a diff or when publication is not authorized.

    Also in 3 projects that use this

  • Arman-KudaibergenovSkill

    write-plan

    Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md. SHOULD также вызывать как промежуточный шаг между brainstorm и subagent-dev. Do NOT использовать для обсуждения идеи — используй brainstorm; для выполнения задач — используй subagent-dev.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 69 edited versions we read keep these.

  • 6

    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:

    Ask one question at a time through the AskUserQuestion tool, and wait for the answer before moving to the next.

    line 17
  2. Distinctive:

    If a question can be answered by exploring the codebase, explore the codebase instead of asking.

    line 19
  3. Distinctive:

    After each answer, fold it into the running understanding and ask the next question down that branch.

    line 39
  4. Distinctive:

    Stop when a full pass down the tree surfaces no new open decisions, or when the user signals they're satisfied.

    line 41
  5. Distinctive:

    Always include the recommended answer, listed first.

    line 48
  6. Distinctive:

    Prefer exploring the codebase over asking when the codebase holds the answer.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 69 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

Interview the user relentlessly about every aspect of this plan until reaching a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.

Ask one question at a time through the AskUserQuestion tool, and wait for the answer before moving to the next. A later question usually depends on an earlier answer, so resolve the branch in order — don't batch unrelated questions.

If a question can be answered by exploring the codebase, explore the codebase instead of asking.

This is a read-only interview — it writes no files. The output is the shared understanding and a closing summary.

Input

$ARGUMENTS — the plan, design, or topic to grill. If empty, ask via AskUserQuestion what they want to be grilled on.

Each question

Pose every question with AskUserQuestion:

  • A short header (≤12 chars) naming the decision.
  • 2–4 options. Put the recommended answer first, labelled (Recommended), with a one-line rationale in its description. Make the remaining options the strongest realistic alternatives.
  • The user can always pick "Other" to type a free-form answer — options are starting points, not a cage; don't force a fit.

After each answer, fold it into the running understanding and ask the next question down that branch. Surface contradictions immediately ("you just chose X, but earlier you said Y — which holds?").

Stop when a full pass down the tree surfaces no new open decisions, or when the user signals they're satisfied. After about 15 questions, check in: ask whether to keep going or wrap up. Summarise the resolved decisions at the end.

Rules

  • One AskUserQuestion per question. Wait for the answer before moving on.
  • Always include the recommended answer, listed first.
  • Resolve dependencies in order — don't jump branches.
  • Prefer exploring the codebase over asking when the codebase holds the answer.
  • Exploring the codebase includes its git memory: read the affected files' commit history per ${CLAUDE_PLUGIN_ROOT}/skills/gca/reference/history-reading.md — a past Rejected: or Constraint: trailer is grill material, cite it when challenging the plan.
  • For deeper grilling that also captures terminology and decisions into .yoke/context.md and ADRs, use /yoke:grill-docs.
  • Language: match the user's language, or follow the project-level definition in CLAUDE.md / AGENTS.md.

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