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
- bmcszk/agent-skillstheir own version, first seen Nov 16, 2026
- devdeepjs/kobayashi-marutheir own version, first seen Nov 16, 2026
- gaoyuan98/dameng-skillstheir own version, first seen Nov 16, 2026
- lhotwll217/owner-operatortheir own version, first seen Nov 16, 2026
- Lixiuxiu559/AgentForgetheir own version, first seen Nov 16, 2026
- philoserf/claude-code-configtheir own version, first seen Nov 15, 2026
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-CompanySkillcapture-learning-tools
Turn technical conversations, bugs, CI failures, review comments,
Also in 5 projects that use this
The-Vibe-CompanySkilldesign-frontend-dev
Clean Impeccable frontend design skill. Use when the user wants to
Also in 5 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 58 projects that use this
liufeng1976Skillsetup-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
FabienDehopreSkilldecision-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
AWSSkillwizard
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
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 194
- mattpocock/skills★ 325ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- windmill-labs/windmill★ 19ksame name
- GreyDGL/PentestGPT★ 16ksame name
- formbricks/formbricks★ 13ksame name
- PX4/PX4-Autopilot★ 13ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- pollinations/pollinations★ 5.3ksame name
184 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.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- codebase-designSkill
- code-reviewSkill
- commission-method-gap-researchSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- method-gap-research-statusSkill
- prototypeSkill
- refactor-skillSkill
- research-briefSkill
- researchSkill
- setup-matt-pocock-skillsSkill
- skill-evidence-captureSkill
- skill-evolutionSkill
- skill-evolution-statusSkill
- tddSkill
- teachSkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- writing-great-skillsSkill
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
- Distinctive: line 10
Verify premises against the authoritative environment.
- Distinctive: line 12
Ask unresolved forks one at a time, recommendation first.
- Distinctive: line 32
Always read Verification before drawing the branch list.
- Distinctive: line 33
Read Adjudication for adjudication, divergent/corroborating sources, or when its evidence classifications are needed.
- Distinctive: line 35
Read Questions And Ledger before asking or re-asking a question, accepting answers ahead, or starting execution that may resolve decisions.
- Distinctive: line 37
Read Recap before a closing recap, blanket-approval closeout, hard-to-reverse approval, or execution handoff.
- Distinctive: line 39
Read Execution Contract before edits, process execution, challenge/retraction handling, or the final summary.
- Distinctive: line 41
Read Verifier Packets only when an external or cold-context verifier receives a self-contained packet.
- Distinctive: line 56
Put findings the user needs for a decision in a visible turn before the question.
- Distinctive: line 61
If the project declares a completion or landing contract, read it while planning and run it again before delivery.
- Distinctive: line 72
Run the applicable completion contract, or state why none applies.
“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.
Files
Grilling
Resolve every decision that changes the outcome and none that evidence already resolves:
- Verify premises against the authoritative environment.
- Name the foreseeable decision branches.
- Ask unresolved forks one at a time, recommendation first.
- Record decisions in a running ledger.
- Recap the ratified scope.
- 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:
| Mode | Use when | Behavior |
| Interview | The user wants to sharpen their plan or design. | Explore first, then ask each outcome-changing fork. |
| Adjudication | The 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 process | The 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:
- Sweep the decision ledger, including mid-execution forks.
- State the ratified in-scope and out-of-scope boundaries.
- Confirm the delivered artifact matches them; scope every completeness claim.
- Report unresolved, unavailable, or pending evidence.
- Run the applicable completion contract, or state why none applies. For non-product or companion-domain work, use the conditional fields in Execution Contract.
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
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.

