doc-grounded-grilling
Skill16 starsChanged 5 months agoMITView on GitHub
Stress-test a plan, feature, or design against the repo's existing docs, domain language, ADRs, and context files. Use when a task is ambiguous, terminology is fuzzy, architecture trade-offs matter, or the user wants alignment before implementation. Ask one question at a time, inspect the codebase when answers are already present, and sharpen the project's language as decisions crystallize.
In this repository94 other files it gives its agents.
- agent-friction-ledgerSkill
- agent-learning-layer-triageSkill
- agent-operations-contractSkill
- agents-best-practicesSkill
- agent-tool-contract-reviewSkill
- anti-slop-reviewSkill
- architecture-deepening-reviewSkill
- assumption-excavationSkill
- authorized-security-routerSkill
- book-to-skillSkill
- bounded-evaluationSkill
- bounded-growth-loopSkill
- bounded-orchestration-contractSkill
- brief-first-executionSkill
- browser-verificationSkill
- bug-evidence-protocolSkill
- codex-review-loopSkill
- compaction-survivalSkill
- complexity-optimizerSkill
- confidence-fragility-reviewSkill
- context-degradation-reviewSkill
- corporate-surfaceSkill
- delivery-baseline-auditSkill
- delivery-preflight-gateSkill
- design-critique-polishSkill
- designmd-brand-kitSkill
- design-register-bootstrapSkill
- diagnoseSkill
- doc-to-lora-evaluatorSkill
- durable-context-maintenanceSkill
- dynamic-workflow-packetsSkill
- editorial-surfaceSkill
- evidence-ledger-researchSkill
- filesystem-context-disciplineSkill
- fluid-interaction-reviewSkill
- frontend-product-builderSkill
- frontend-taste-layerSkill
- git-native-context-contractSkill
- goal-loop-designerSkill
- graph-guided-code-readingSkill
- handoffSkill
- happy-handoffSkill
- html-brief-artifactSkill
- html-diagram-artifactSkill
- hypothesis-diversificationSkill
- idea-to-ship-gatesSkill
- knowledge-base-enrichmentSkill
- lean-context-layoutSkill
- local-inference-tuningSkill
- loop-hardening-contractSkill
- loopops-protocolSkill
- loop-readiness-reviewSkill
- lottie-motion-builderSkill
- minimal-diff-builderSkill
- motion-review-gateSkill
- overengineering-reviewSkill
- personal-workspace-routerSkill
- phase-spec-executionSkill
- pipeline-readiness-gateSkill
- plan-to-issuesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
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 12
Use structured questioning to align a plan with the repo's actual language, constraints, and existing decisions.
- Distinctive: line 16
Read the nearest relevant context first:
- Distinctive: line 22
Ask one question at a time.
- Distinctive: line 23
If the answer is already in the code or docs, verify there before asking.
- Distinctive: line 27
wait for user feedback before continuing.
- Distinctive: line 33
When a term or decision settles, classify the durable artifact:
- Distinctive: line 37
no artifact when the answer is temporary or already documented.
- Distinctive: line 59
Do not interrogate for its own sake.
- Distinctive: line 60
Do not invent domain language when the repo already has one.
- Distinctive: line 61
Do not batch ten questions at once.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Doc Grounded Grilling
Use structured questioning to align a plan with the repo's actual language, constraints, and existing decisions.
Workflow
- Read the nearest relevant context first:
AGENTS.mddocs/ai/*- ADRs
- repo docs
designmd-brand-kitartifacts when frontend or brand work is involved
- Ask one question at a time.
- If the answer is already in the code or docs, verify there before asking.
- For each question:
- identify the ambiguity;
- give a recommended answer or framing;
- wait for user feedback before continuing.
- Walk down the branches of the design tree until:
- terms are precise;
- boundaries are understood;
- key trade-offs are named;
- critical scenarios are covered.
- When a term or decision settles, classify the durable artifact:
- glossary/context update for canonical domain language;
- ADR candidate for hard-to-reverse or surprising trade-offs;
- PRD/spec note for scope and acceptance criteria;
- no artifact when the answer is temporary or already documented.
What To Challenge
- terminology that conflicts with existing domain language;
- assumptions contradicted by code or ADRs;
- vague nouns like "account", "session", "client", "job", "draft", "campaign";
- plans that skip the test seam, integration seam, or rollout seam;
- frontend ideas that ignore the current design system or brand shape.
Output
The session should leave behind:
- sharper language;
- clarified decisions;
- explicit open questions;
- identified docs that should be updated through
durable-context-maintenancewhen the decision settles; - proposed glossary/context or ADR updates when the task changed the repo's shared language or a consequential decision.
Guardrails
- Do not interrogate for its own sake; stop when the plan is clear enough to execute.
- Do not invent domain language when the repo already has one.
- Do not batch ten questions at once.
Final Report
Summarize resolved terms, decisive trade-offs, remaining open questions, and which docs should be refreshed next.
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.

