菜单
A grilling session that also builds the project's domain model as it goes — challenging terminology against the glossary and recording decisions as ADRs the moment they crystallise. Use when you want to stress-test a plan against your project's documented language and decisions (brownfield).
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
Use before any creative/build work — adding features, building components, new functionality, or changing behavior. Turns a brief or vague idea into an approved design doc through one-question-at-a-time dialogue. Does NOT write code until the design is approved. Output is the design doc; the next step is owned by the caller.
Craft a clear /goal condition for Claude Code's autonomous mode from a rough task description.
Convene an independent cross-model judge — a model of a different family (e.g. Codex/GPT, Gemini, or a Cursor agent pinned to a non-Claude model), whichever CLI is installed — to cross-examine an artifact (a decision, a diff, a document, or a research answer) and adjudicate its findings disbelieve-it-back. This is the cross-model *mechanism*; the caller brings the artifact and its own in-family review. Use via `vet` (code), `research-council` (research), `plan` (a design decision), or directly when you want a second opinion from a model that doesn't share your blind spots. It reviews; it never edits.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
| name | grill-with-docs |
| description | A grilling session that also builds the project's domain model as it goes — challenging terminology against the glossary and recording decisions as ADRs the moment they crystallise. Use when you want to stress-test a plan against your project's documented language and decisions (brownfield). |
| license | MIT |
Run a grill-me session, but carry the domain-modeling discipline alongside it: as decisions crystallise, sharpen the project's terminology and write it down inline.
grill-me (in meta/) owns the relentless interview; domain-modeling (in software-development/design/) owns the glossary/ADR discipline — CONTEXT.md, docs/adr/, and the file formats. The codebase-agnostic version is grill-me on its own.
grill-me. Walk each branch of the decision tree, recommending an answer per question and resolving each branch before moving on.domain-modeling. Challenge terms that conflict with CONTEXT.md, sharpen fuzzy language to a canonical term, stress-test relationships with concrete edge-case scenarios, cross-reference claims against the code, and update CONTEXT.md the moment a term resolves. Offer an ADR only when the decision is hard to reverse, surprising without context, and a real trade-off.Create docs lazily — only when there's something to write. See domain-modeling for the file structure and the CONTEXT.md / ADR formats.
If domain-modeling isn't installed, apply its discipline inline from the description above rather than skipping the doc-keeping — the point of this workflow over a plain grill-me is that the glossary and decisions get captured as you go.