agentleFS
Sign inStart free
Luis85Luis85/agentic-workflow/.claude/skills/grill/SKILL.md

grill

Skill0 starsChanged 6 months agoMITView on GitHub

Interrogate user one question at a time until every branch of a plan/design/requirement is resolved. Recommends answers, explores codebase. Triggers "grill me", "stress-test", "tighten this up", "interrogate".

87 other projects use a version of this.

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

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 69 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After Pocock's grill-me. This is the interview primitive every clarification gate (/spec:clarify, the analyst's open-question pass, design …

    line 11
  2. Distinctive:

    If the answer is in the codebase or upstream artifacts, answer it yourself and confirm with the user instead of asking blind.

    line 20
  3. Distinctive:

    Always state your recommended answer.

    line 28
  4. Very specific:

    Read upstream artifacts (docs/CONTEXT.md, docs/glossary/*.md — per ADR-0010.

    line 29
  5. Very specific:

    Use AskUserQuestion only when free-text or multi-option is needed.

    line 30
  6. Distinctive:

    Don't ask "what do you want?" — propose a default and ask the user to confirm or redirect.

    line 31
  7. Distinctive:

    Don't grill past the artifact's purpose.

    line 32

“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 one question at a time. Do not stop until every branch of the decision tree is resolved.

After Pocock's grill-me. This is the interview primitive every clarification gate (/spec:clarify, the analyst's open-question pass, design alternative selection, requirement disambiguation) reaches for.

Procedure

  1. Restate the artifact under examination in one sentence. Confirm with the user this is what they want grilled.
  2. Identify the first ambiguity — the highest-leverage decision that is currently under-specified.
  3. Ask one question to resolve it. Always:
    • Phrase it as a binary or small enum (≤4 options) where you can.
    • Provide your recommended answer with one-sentence reasoning.
    • If the answer is in the codebase or upstream artifacts, answer it yourself and confirm with the user instead of asking blind.
  4. Wait for the answer. On answer, write the resolution into the artifact (or hold a running list to write at the end).
  5. Walk down the resulting branch — each answer creates new sub-questions. Recurse until that branch is fully resolved before moving to the next ambiguity.
  6. When all branches are resolved, summarize the resolved decisions in a bulleted list and confirm with the user before persisting.

Rules

  • One question per turn. Never batch.
  • Always state your recommended answer. The user should be able to say "yes do that" and move on.
  • Read upstream artifacts (docs/CONTEXT.md, docs/glossary/*.md — per ADR-0010; legacy docs/UBIQUITOUS_LANGUAGE.md if present, the relevant specs/<slug>/*.md) before each question — many ambiguities are already settled there.
  • Use AskUserQuestion only when free-text or multi-option is needed. Otherwise plain conversational questions are fine.
  • Don't ask "what do you want?" — propose a default and ask the user to confirm or redirect.
  • Don't grill past the artifact's purpose. A PRD is grilled on requirements, not on implementation.

When to invoke this skill

  • During /spec:clarify (it is the body of that command).
  • Inside the analyst when idea.md has open questions.
  • Inside the pm when a requirement candidate is under-specified.
  • Inside the architect when a design decision could go multiple ways.
  • Anywhere the user says "grill me" or "tighten this up".

When not to invoke

  • The artifact is already specified. Don't manufacture ambiguity.
  • The decision is the user's intent (e.g. priorities). Don't grill on values; ask once.
  • You're already inside another skill's flow that owns the conversation (don't double-grill).

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