agentleFS
joeloverbeckjoeloverbeck/skill-evidence/.claude/skills/grilling/SKILL.md

grilling

Skill0 starsChanged 3 months agoMITView on GitHub

Interview the user about a plan or design, adjudicate a third-party document against the environment, or drive a user-directed documented process, then honor the ratified outcome. Use to stress-test a plan, rule on someone else's proposal, execute an already-authorized process, or on any "grill" trigger phrase.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture-learning-tools, design-frontend-dev and 9 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.
  • The-Vibe-CompanySkill

    capture-learning-tools

    Turn technical conversations, bugs, CI failures, review comments,

    Also in 5 projects that use this

  • The-Vibe-CompanySkill

    design-frontend-dev

    Clean Impeccable frontend design skill. Use when the user wants to

    Also in 5 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 58 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

  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

  • AWSSkill

    wizard

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Also in 136 projects that use this

  • +3 more from The-Vibe-Company

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 72 edited versions we read keep these.

  • 11

    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:

    Verify premises against the authoritative environment.

    line 10
  2. Distinctive:

    Ask unresolved forks one at a time, recommendation first.

    line 12
  3. Distinctive:

    Always read Verification before drawing the branch list.

    line 32
  4. Distinctive:

    Read Adjudication for adjudication, divergent/corroborating sources, or when its evidence classifications are needed.

    line 33
  5. Distinctive:

    Read Questions And Ledger before asking or re-asking a question, accepting answers ahead, or starting execution that may resolve decisions.

    line 35
  6. Distinctive:

    Read Recap before a closing recap, blanket-approval closeout, hard-to-reverse approval, or execution handoff.

    line 37
  7. Distinctive:

    Read Execution Contract before edits, process execution, challenge/retraction handling, or the final summary.

    line 39
  8. Distinctive:

    Read Verifier Packets only when an external or cold-context verifier receives a self-contained packet.

    line 41
  9. Distinctive:

    Put findings the user needs for a decision in a visible turn before the question.

    line 56
  10. Distinctive:

    If the project declares a completion or landing contract, read it while planning and run it again before delivery.

    line 61
  11. Distinctive:

    Run the applicable completion contract, or state why none applies.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 72 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

Grilling

Resolve every decision that changes the outcome and none that evidence already resolves:

  1. Verify premises against the authoritative environment.
  2. Name the foreseeable decision branches.
  3. Ask unresolved forks one at a time, recommendation first.
  4. Record decisions in a running ledger.
  5. Recap the ratified scope.
  6. Execute when authorized, capturing new forks as they arise.

Choose The Mode

Choose by the request's object and authority, not by how many artifacts it mentions:

ModeUse whenBehavior
InterviewThe user wants to sharpen their plan or design.Explore first, then ask each outcome-changing fork.
AdjudicationThe object is a third-party report, spec, finding set, handoff, or a repository/environment sweep.Verify claims, disposition each item, and collapse only scope-changing forks. If the user asked only for a verdict, stop after the ruling.
Documented processThe user asks to follow a process or a companion workflow routes an explicit, already-authorized reversible request here.Verify the stated scope, name foreseeable branches, and execute it. Do not manufacture a design interview or a second approval; re-question only a mismatch that changes what ships.

A sweep that is only an execution step stays in the governing execution mode. Multiple authoritative inputs do not by themselves turn a direct execution into adjudication.

Load Only What The Branch Needs

  • Always read Verification before drawing the branch list.
  • Read Adjudication for adjudication, divergent/corroborating sources, or when its evidence classifications are needed.
  • Read Questions And Ledger before asking or re-asking a question, accepting answers ahead, or starting execution that may resolve decisions.
  • Read Recap before a closing recap, blanket-approval closeout, hard-to-reverse approval, or execution handoff.
  • Read Execution Contract before edits, process execution, challenge/retraction handling, or the final summary.
  • Read Verifier Packets only when an external or cold-context verifier receives a self-contained packet.

Complete every required reference read. If output is truncated, fetch the missing portion before acting.

Invariants

  • Explore instead of asking when authoritative evidence can resolve the question.
  • A failed premise becomes a rejected/downgraded proposal or a blocking fork; never silently assume it away.
  • In adjudication, classify evidence before assigning warrant. Verifiers return evidence and coverage; the main thread owns dispositions.
  • Briefly name the expected branches before the first question. In a many-item adjudication, the disposition list can serve as that branch map.
  • Put findings the user needs for a decision in a visible turn before the question; follow Questions And Ledger for client-specific rendering.
  • Capture every mid-execution fork before the next mutation, then reconcile those captures and the delivered artifact against the ratified scope.
  • If the project declares a completion or landing contract, read it while planning and run it again before delivery.

Final Delivery

Before responding:

  1. Sweep the decision ledger, including mid-execution forks.
  2. State the ratified in-scope and out-of-scope boundaries.
  3. Confirm the delivered artifact matches them; scope every completeness claim.
  4. Report unresolved, unavailable, or pending evidence.
  5. Run the applicable completion contract, or state why none applies. For non-product or companion-domain work, use the conditional fields in Execution Contract.

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.