| name | grill-with-docs |
| description | Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. |
Interview me relentlessly about every aspect of this plan until we 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 question before continuing.
If a question can be answered by exploring the codebase, explore the codebase instead.
Domain awareness
This skill is wired to {USER_NAME}'s vault, not to repo-local docs. The project's domain glossary and decisions live in the vault, in the project's claude-code/ folder — the same folder whose README.md is loaded at session start:
04 - Projects/<Projet>/claude-code/
├── README.md ← codebase context (loaded at session start)
├── CONTEXT.md ← domain glossary (this skill maintains it)
└── ADR/ ← decisions, created via /create-adr
└── INDEX.md
The dev repo (your cwd) stays clean — nothing is written into it. If you can't tell which vault project this repo maps to, ask before touching any doc.
During exploration, read CONTEXT.md and ADR/INDEX.md from that folder if they exist. Create CONTEXT.md lazily — only when the first term is resolved.
During the session
Challenge against the glossary
When the user uses a term that conflicts with the existing language in CONTEXT.md, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"
Sharpen fuzzy language
When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things."
Discuss concrete scenarios
When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.
Cross-reference with code
When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?"
Update CONTEXT.md inline
When a term is resolved, update the project's 04 - Projects/<Projet>/claude-code/CONTEXT.md right there. Don't batch these up — capture them as they happen. Create it lazily if it doesn't exist. Use the format in CONTEXT-FORMAT.md.
CONTEXT.md should be totally devoid of implementation details. Do not treat CONTEXT.md as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.
Offer ADRs sparingly
Only offer to create an ADR when all three are true:
- Hard to reverse — the cost of changing your mind later is meaningful
- Surprising without context — a future reader will wonder "why did they do it this way?"
- The result of a real trade-off — there were genuine alternatives and you picked one for specific reasons
If any of the three is missing, skip the ADR. When all three hold, create it by invoking the /create-adr skill — it resolves project vs transverse scope, vault placement, numbering and INDEX.md update. Never write ADR files by hand. See ADR-FORMAT.md for what qualifies.
