Grill with docs

Source: mattpocock/skills - engineering/grill-with-docs

<what-to-do>

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.

</what-to-do> <supporting-info>

Domain awareness

During codebase exploration, also look for existing documentation:

File structure

Most repos have a single context:

/
├── CONTEXT.md
├── docs/
│   └── adr/
│       ├── 0001-event-sourced-orders.md
│       └── 0002-postgres-for-write-model.md
└── src/

If a CONTEXT-MAP.md exists at the root, the repo has multiple contexts. The map points to where each one lives:

/
├── CONTEXT-MAP.md
├── docs/
│   └── adr/                          ← system-wide decisions
├── src/
│   ├── ordering/
│   │   ├── CONTEXT.md
│   │   └── docs/adr/                 ← context-specific decisions
│   └── billing/
│       ├── CONTEXT.md
│       └── docs/adr/

Create files lazily - only when you have something to write. If no CONTEXT.md exists, create one when the first term is resolved. If no docs/adr/ exists, create it when the first ADR is needed.

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 CONTEXT.md right there. Don't batch these up - capture them as they happen. Use the format in CONTEXT-FORMAT.md.

Don't couple CONTEXT.md to implementation details. Only include terms that are meaningful to domain experts.

Offer ADRs sparingly

why-not-mechanizable: skill workflow guidance; each step requires understanding the surrounding context (repo, task shape, prior state).

Only offer to create an ADR when all three are true:

1. Hard to reverse - the cost of changing your mind later is meaningful (review-time: see section note)
2. Surprising without context - a future reader will wonder "why did they do it this way?" (review-time: see section note)
3. The result of a real trade-off - there were genuine alternatives and you picked one for specific reasons (review-time: see section note)

If any of the three is missing, skip the ADR. Use the format in ADR-FORMAT.md.

Panel grilling (optional)

For a plan with genuine cross-domain tension or competing approaches, convene a panel (see rules/parallel-agents.md) instead of grilling solo:

• Spawn domain-expert teammates via the Agent tool (route per rules/agent-routing.md), each with a read-only brief and a distinct stance to argue (review-time: panel-vs-solo judgment)
• Have them debate the plan among themselves via SendMessage - the cross-talk between teammates surfaces contradictions and trade-offs you would miss solo (review-time: protocol guidance)
• Distill their disagreement into the next question and put it to the user - keep the user-facing cadence to one question at a time per rules/communication.md; the panel never messages the user directly (review-time: cadence discipline)
• Skip the panel for single-domain plans - solo grilling is cheaper and a panel adds nothing when there is nothing to contend (review-time: panel-vs-solo judgment)

</supporting-info>