grilling
Skill2 starsChanged 4 months agoMITView on GitHub
Interview the user relentlessly about a plan, design, or idea until reaching shared understanding. Use when they want to stress-test a plan, get grilled on a design.
194 other projects use a version of this.
Adopted by
Most recently taken up by
- Lixiuxiu559/AgentForgetheir own version, first seen Nov 16, 2026
- philoserf/claude-code-configtheir own version, first seen Nov 15, 2026
- peterpme/skillstheir own version, first seen Nov 15, 2026
- otaq-io/otaqtheir own version, first seen Nov 15, 2026
- geoffbremner/skillstheir own version, first seen Nov 15, 2026
- ychampion/ystacktheir own version, first seen Nov 15, 2026
Used with
Projects with it also use capture-learning-tools, design-frontend-dev 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.
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 repository13 other files it gives its agents.
- claude-mdSkill
- commit-pushSkill
- create-cliSkill
- debug-agentSkill
- domain-modelingSkill
- grill-with-docsSkill
- handoffSkill
- helpSkill
- prototypeSkill
- review-structureSkill
- schedule-tasksSkill
- skill-masterSkill
- wayfinderSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 67 edited versions we read keep these.
1
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 38
Press for definitions: Don't accept "fast", "scalable", "simple", "clean", "good UX" — force a concrete version (numbers, examples, …
“Common” is measured: kept by at least 6 in 10 of the 67 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
Interview the user relentlessly about the thing they want to work on, walking the decision tree one branch at a time. The steps below are the mechanics; the goal is shared understanding — you and the user aligned on what to do and why. Keep the interview sharp and adaptive: pull moves as the conversation needs them, don't march the list.
How to grill
- Ground first. Spawn sub-agents in parallel to read the relevant codebase and anything the user attached or referenced — files, URLs, tickets, docs. Skip only if the subject is genuinely context-free.
- Start at the root. Open with the decision that gates the most others. Ask if the subject itself is unclear.
- One question at a time, always with a recommended answer. End on a single ask — don't bolt a second question on with "and" or a dash; that's the next turn's, not a tail on this one. An either/or that rephrases the same question is fine. Lay it out per Question shape.
- Facts you find; decisions are theirs. A fact — anything in the code, config, git history, or the attached resources — you look up/explore rather than ask. A decision is the user's: put it to them. Only ask for decisions, and for facts you genuinely can't derive.
- Follow dependencies. Resolve decisions in dependency order — each answer constrains the next, so settle the gating one before the choices that hang off it. Don't wander to siblings until the current branch is resolved.
- Don't stop early. Keep going until every decision has an answer, the user ends it, or what's left is pure implementation detail. Then summarize the decisions made — and stop. Don't act on the plan until the user confirms the summary reflects shared understanding.
Question shape
Make it answerable at a glance: lead with the question, then the options — each option's detail rides in the option, not a preamble before the list. Choice-shaped decisions get numbered options; open or reframing ones get just the recommendation and why.
Q1 — the question, one line.
- Short label — its description: what it means, the trade-off, whatever context it needs. As long as it needs to be, never padded.
- Short label — its description.
Recommend: N — why, sized to the decision.
State the question once, up top — don't restate it after the options. Any framing goes above the question, and only when it's a real Socratic move (a reframe, a surfaced assumption, a consequence) — never to narrate the method ("now we walk the tree in dependency order"). Keep framing to a sentence or two — surface what the user doesn't know that changes the answer; don't teach a framework or restate what the options already say.
Socratic moves
Layer these on to make sure the answer being accepted is actually load-bearing:
- Surface assumptions before walking the tree. Probe whether the root is framed correctly and the stated goal is the real goal — a tree rooted in the wrong place wastes the whole interview.
- Press for definitions. Don't accept "fast", "scalable", "simple", "clean", "good UX" — force a concrete version (numbers, examples, observable outcomes) and propose a sharp one.
- Test consequences. Trace each answer's downstream implications and confirm the user wants them: "If X, then Y and Z follow — OK with that?"
- Check for contradictions. Watch for answers that conflict with earlier ones; name both and ask which wins.
- Probe with counterexamples. Stress-test a tentative decision with one edge case before locking it in. If it breaks down, revisit before moving down the branch.
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.

