grilling
Skill2 starsChanged 53 days agoMITView on GitHub
The shared design-tree interview protocol — the status markers, the example tree, the reprint rules, and the node status-lifecycle. Use when running or structuring a relentless one-question-at-a-time interview that walks a decision tree to resolve every branch of a plan or design. Composed by grill-me and grill-with-docs.
193 other projects use a version of this, 37 of them edited.
Adopted by
Most recently taken up by
- xiaoxiaosrm/dsh-mattpocock-skillstheir own version, first seen Nov 8, 2026
- wowyuarm/dsh-agent-teamtheir own version, first seen Nov 8, 2026
- Contexera/dsh-agent-teamtheir own version, first seen Nov 8, 2026
- awslabs/agentic-developer-platformtheir own version, first seen Nov 8, 2026
- microsoft/frontier-agentic-modernization-rvastheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 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
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
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 58 projects that use this
- +3 more from The-Vibe-Company
Other versions193 projects use a version of this.
Word for word · 0
None found.
Edited · 37
- GreyDGL/PentestGPT★ 16k46% same
- PX4/PX4-Autopilot★ 13k28% same
- stevesolun/ctx★ 58323% same
- Tiberriver256/mcp-server-azure-devops★ 39946% same
- ninehills/skills★ 28046% same
- loulanyue/skills★ 23123% same
- heyongjun666/AICU-Graph★ 20046% same
- opencrvs/opencrvs-core★ 12227% same
- HarryMtv/create-frontstack★ 10323% same
- GulajavaMinistudio/awesome-copilot-id★ 9211% same
27 more not listed
Wrote their own version · 156
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- windmill-labs/windmill★ 18ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- pollinations/pollinations★ 5.3ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
146 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 repository32 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ask-zslSkill
- codebase-designSkill
- code-reviewSkill
- commit-push-prSkill
- commitSkill
- decision-mappingSkill
- diagnoseSkill
- domain-modelingSkill
- git-branchSkill
- grill-with-docsSkill
- human-itlSkill
- improve-codebase-architectureSkill
- prototypeSkill
- setup-zsl-superpowersSkill
- tdd-parallelSkill
- tddSkill
- teach-me-the-codebaseSkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- verify-coverageSkill
- edit-articleSkill
- setup-pre-commitSkill
- steampipeSkill
- grill-meSkill
- handoffSkill
- timesheetSkill
- writing-great-skillsSkill
- afk-fanoutSkill
- afk-workerSkill
- morning-reviewSkill
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 71 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 25
Before the first question, print the design tree you intend to traverse — the decisions and sub-decisions you've identified, with a status …
“Common” is measured: kept by at least 6 in 10 of the 71 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
The shared engine for a relentless, one-question-at-a-time interview that walks a
design tree until every branch is resolved. One home for the protocol so the
markers, the example, the reprint rules, and the status lifecycle mean the same
thing in every skill that grills — grill-me, grill-with-docs, and anything
else that needs the interview loop composes this instead of carrying its own copy.
The loop
Interview the user relentlessly about every aspect of the plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer. Ask the questions one at a time, waiting for feedback on each before continuing. If a question can be answered by exploring the codebase, explore the codebase instead of asking.
Design tree
Before the first question, print the design tree you intend to traverse — the decisions and sub-decisions you've identified, with a status marker on each:
[ ]unresolved[→]currently being grilled[✓]resolved
Example:
Design tree
├── [→] Auth strategy
│ ├── [ ] Session storage (cookie vs JWT)
│ └── [ ] Refresh-token rotation
├── [ ] Persistence layer
│ ├── [ ] Primary store
│ └── [ ] Migration path from current schema
└── [ ] Rollout
├── [ ] Feature-flag gate
└── [ ] Backfill planReprint the tree whenever it changes: a node is resolved, a new branch is discovered, the focus moves to a new node, or scope shifts. Don't reprint between every question — only when the shape or status actually changes. Always reprint the full tree, not a diff, so progress is visible at a glance.
Status lifecycle for a single node:
stateDiagram-v2
direction LR
[*] --> unresolved: node added
unresolved: [ ] unresolved
grilling: [→] currently grilling
resolved: [✓] resolved
unresolved --> grilling: focus moves here
grilling --> resolved: decision made
grilling --> unresolved: focus moves elsewhere<br/>before deciding
resolved --> grilling: reopened (new info)
resolved --> [*]: tree completeDoes 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.

