agentleFS
Sign inStart free
assisjpassisjp/specflow/skills/productivity/grill/SKILL.md

grill

Skill17 starsChanged 3 months agoMITView on GitHub

Stress-test a plan or decision by resolving consequential ambiguity, looking up facts and recommending choices against the user priorities. Use when asked to sharpen thinking, pressure-test an idea or grill a decision. Pass docs to capture meaningful glossary and architecture decisions.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 3

    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:

    Look up discoverable facts in the repository or tools instead of asking the user.

    line 14
  2. Distinctive:

    Ask the next consequential question with a recommended answer and concrete trade-off.

    line 15
  3. Distinctive:

    Keep a compact decision log: decision → choice → reason, plus deliberately deferred items.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 66 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

Stress-test a plan or decision before committing to it. Resolve the uncertainty that matters to the user's outcome; do not try to enumerate every imaginable branch.

The interview

  • Look up discoverable facts in the repository or tools instead of asking the user.
  • Ask the next consequential question with a recommended answer and concrete trade-off. Reuse priorities and decisions already given. Group closely related short questions when it reduces effort; avoid a long questionnaire.
  • Resolve upstream decisions before dependent ones. Challenge contradictions with the user's stated constraints, and ask only when evidence cannot resolve them.
  • Judge options against the user's priorities, not generic best practice. Offer sensible defaults for routine reversible choices.
  • Keep a compact decision log: decision → choice → reason, plus deliberately deferred items.

Grilling itself is discussion, not implicit permission to edit application code. Do not treat a vague conversational “yes” as new authority. If the user explicitly asks to implement the resolved work, recognize that changed scope and continue through the appropriate execution workflow using the existing authorization; do not demand another named skill command. A separate elaborate spec is unnecessary when the accepted request already defines an observable outcome.

docs mode

When requested, use domain-modeling for settled vocabulary and meaningful architectural decisions. Create files lazily. An ADR is warranted only when the choice is hard to reverse, surprising without context and a real trade-off. Temporary hypotheses and ordinary implementation reasoning stay in the decision log or task record; not every “why” needs an ADR.

Without docs, keep the log in the conversation unless the user requests a saved artifact. Do not duplicate a durable source just to satisfy a template.

Finish

Summarize the accepted outcome, important decisions and unresolved blockers. Stop when the relevant decisions are settled or deliberately deferred. Ask for a necessary decision if one remains; otherwise name or perform the next authorized action. Do not add a second approval solely to confirm that the previous approval was understood.

Download now (ZIP)

  • Other versions81 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 81

    1. kirodotdev/KiroCrew★ 4.7ksame name
    2. crbnos/carbon★ 2.8ksame name
    3. JuliusBrussee/cavekit★ 1.1ksame name
    4. SethGammon/Citadel★ 927same name
    5. nagi-studio/skills★ 387same name
    6. KerberosClaw/kc_ai_skills★ 79same name
    7. alamops/skills★ 53same name
    8. Kanevry/session-orchestrator★ 53same name
    9. oakreader/oakreader★ 46same name
    10. manusco/resonance★ 38same name

    71 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use write-skill, prove-it and 8 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

    • 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

    • 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 3 projects that use this

    • sahinSkill

      execute

      Also in 5 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

    • JkudjoSkill

      incident

      Production incident response — structured triage, hypothesis tree, safe remediation, incident record

      Also in 3 projects that use this

  • In this repository14 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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