grill-me-with-docs
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.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- grill-me-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.
- disable-model-invocation
- true
02 资源文件 1
- 参考文档CONTEXT-FORMAT.md3.1 KB
03 SKILL.md 正文
User-invoked only. The docs-aware grilling variant: the interview loop plus glossary and ADR maintenance. The plain loop that other skills delegate to lives in
grilling.
<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 one question at a time via AskUserQuestion. Never batch — each answer may change what you ask next. For each question:
- Give exactly 3 concrete options grounded in your analysis of the codebase and the plan, plus a fourth: "Chat about this", for when the user isn't ready to decide. Every question carries all four, no exceptions.
- Put your recommended option first, with
(Recommended)appended to its label. Always have a recommendation — never ask a question you have no opinion on. AskUserQuestionadds a free-form "Other" option automatically. Don't add one yourself, and never drop "Chat about this" because "Other" is already there. Both appear on every question.- If "Chat about this" is picked, ask "What would you like to chat about?" and nothing else. Never guess at what might need clarifying or list candidate topics. Discuss whatever they raise, then re-ask the question, revised if the discussion changed it.
- If a question can be answered by exploring the codebase, explore the codebase instead of asking.
</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.
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 look at the code and wonder "why on earth 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. Use the format in adr-format.md.
</supporting-info>
04 同仓库更多 Skills
to-tickets
Breaks a source into independently-grabbable GitHub tickets. For a code feature the source is the plan (`docs/plans/<feature>.md`, from /to-plan) and every new or changed symbol lands in exactly one ticket, its signatures copied into the ticket body; a non-code feature is cut from the PRD's slices. Cuts tickets for one feature per run. If a code feature has no approved plan, offers /to-plan instead of cutting from prose. In a repo that runs command-centre, also emits `[[task]]` blocks into its config; in a plain treepad repo, emits a Batch Manifest instead so the tickets materialise as stacked worktrees.
to-seams
Records an agreed-but-unlanded cross-repo interface as a seam: the file a consumer's agent gets pasted into its prompt as ground truth, plus the `[[seam]]` block command-centre reads for the retirement pointer. Use when two repos need to build against an interface neither has landed yet — "record a seam for X", "we agreed on this schema, seam it", "add a seam so Y can build against Z's new field". Halts for approval before writing either file.
to-roadmap
Prioritises settled features into a Now / Next / Later kanban board, rendered as a self-contained ./ideas/roadmap.html. Each card is a feature, not a ticket — one card later becomes several tickets via /to-prd -> /to-plan -> /to-tickets. Boards the features in ./docs/approach.md, or the "## Accepted ideas" in ./ideas/CONTEXT.md when there is no approach doc. The approach doc is settled truth: this assigns tiers and reasons about ordering, it never re-litigates what was decided.
to-prd
Turns one feature idea into a PRD built on journeys: a one-line problem, journeys (each ending in an observable state) and delivery slices that say what is usable after each. Interviews, explores the codebase, and saves to docs/prds/<feature>.md. Covers exactly one feature: given a multi-feature source, ask which one. Reads any approach doc or ideate report as priors so it doesn't re-ask what's settled, but needs none. Starts the per-feature spine (/to-prd -> /to-plan -> /to-tickets).
to-plan
Turns one feature's PRD into a skimmable plan in docs/plans/<feature>.md: a short overview, then per phase a glossary, the journeys it satisfies, and its new and modified definitions (types, enums, ports, schema), with the project:<slug> label. No code, branch or PR; the user's review of the file is the gate. Use for "plan this feature", "write the contract", "what are the types". One feature per run. Slash-only.
ticket-tracker
Use when the request is about the *current state* of GitHub issues rather than creating new ones: "where are my tickets", "show the board", "what's in progress", "what's ready to pick up", "move issue N to in-review", "mark N done", "update the ticket status". Live triage board over GitHub issues via the gh CLI, moving each between backlog -> ready -> in-progress -> in-review -> done using status labels. This is the ticket-level board; ./ideas/roadmap.html is the feature-level one. To file new tickets, use /to-tickets, file-issue for a single ad-hoc one, or /sweep for a batch of small fixes.