一键导入
grill-with-docs
Stress-test a plan against repo docs and update decisions inline. Use when challenging a design against documented language, ADRs, or CONTEXT.md.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Stress-test a plan against repo docs and update decisions inline. Use when challenging a design against documented language, ADRs, or CONTEXT.md.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Bootstrap AI-ready repo governance, traceability, cascade, catalog audits, validation. Deprecated compatibility aliases: init-ai-repo, ai-sdlc-init. Use when setting up AI SDLC.
Deprecated compatibility alias for ai-catapult-init. Use only when legacy prompts invoke "ai-sdlc-init"; otherwise use "ai-catapult-init".
Ship a northstar handoff's goals in an ai-catapult-init repo — ultragoal one-PR-per-goal, deterministic engine-pick, peer review, CI gate, fail-closed merge, cascade closure.
Scaffold a structurally valid eval triplet for a target skill under .ai/evals/. CI checks structure only; the LM-judge runs out-of-band, never in CI.
Deprecated compatibility alias for ai-catapult-init. Use only when legacy prompts invoke "init-ai-repo"; otherwise use "ai-catapult-init".
Intake intent into a tracked, sliced plan in an ai-catapult-init repo — deep-interview + skippable grill-me, always raise an issue, ralplan, write the A→B handoff.
| name | grill-with-docs |
| description | Stress-test a plan against repo docs and update decisions inline. Use when challenging a design against documented language, ADRs, or CONTEXT.md. |
Challenge the plan against the existing domain model, sharpening terminology and updating documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Prefer codebase exploration over asking the user — only surface a question when exploration cannot resolve it. When you must ask, provide your recommended answer and move forward unless the user objects.
If a question can be answered by exploring the codebase, explore the codebase instead.
During codebase exploration, also look for existing documentation:
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.
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?"
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."
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.
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?"
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.
Only offer to create an ADR when all three are true:
If any of the three is missing, skip the ADR. Use the format in ADR-FORMAT.md.