grilling：mattpocock/skills 方法论: productivity/grilling，适用于工程实践、代码质量与开发流程优化。
grilling：mattpocock/skills 方法论: productivity/grilling，适用于工程实践、代码质量与开发流程优化。
> 来源: mattpocock/skills (141k stars) — Total TypeScript 创始人 Matt Pocock
> 类目: 生产力
> 原文件: skills/productivity/grilling/SKILL.md
> 模型推荐: gpt-4.1 (代码工程)
Matt Pocock (Total TypeScript, 141k stars) 沉淀下来的"日常代码工程动作"skill 模板。
每一个对应一个具体动作(代码评审 / TDD / 重构 / 文档对齐 / 任务交接),不是工具,是"该怎么干这件事"的工作流模板。
michael 强调"skill 要有相应的指导功能,指导用户使用",所以这里加了下面两节让 Agent 和用户对接。
---
1. 接到任务后先按这个 skill 的检查清单走一遍
2. 清单里如果出现"先做 X 才能做 Y"的红线 → 必须先完成 X
3. 跑完清单后开始动手(改代码 / 写文档 / 评审)
4. 完工前用 `verification-before-completion`(superpowers) 或 `verification` 类 step 自检
5. 任务量大时考虑用 `dispatching-parallel-agents`(superpowers) 或 `wayfinder`(mattpocock) 拆解
1. 告诉 Agent 你要做什么(一句话即可)
2. Agent 跑 skill 清单时不要打断 — 它可能在收集上下文
3. 如果 Agent 主动问你"代码评审要不要安排一个 reviewer"等决策点 → 直接回答
4. 完工后让 Agent 跑一遍自检再交回
5. 整个过程 Agent 自动化,不需要手工介入
---
---
name: grilling
description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
---
Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled: the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
Each question should be formatted like so:
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one.
Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The _decisions_ are the user's: put each to them and wait.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
本 skill 专注于grilling，mattpocock/skills 方法论: productivity/grilling。它将相关流程标准化，帮助用户更快拿到可靠结果，减少重复手工操作。
当你需要在grilling相关工作中获得稳定、可复用的产出时最适合——无论是单次任务还是纳入日常工作流，都能直接调用。
需要一个具体的项目或任务上下文，最好带有代码仓库或需求文档。
1. 告诉 Agent 你要做什么(一句话即可)
2. Agent 跑 skill 清单时不要打断 — 它可能在收集上下文
3. 如果 Agent 主动问你"代码评审要不要安排一个 reviewer"等决策点 → 直接回答
4. 完工后让 Agent 跑一遍自检再交回
5. 整个过程 Agent 自动化,不需要手工介入
---
本 skill 专注于grilling，mattpocock/skills 方法论: productivity/grilling。它将相关流程标准化，帮助用户更快拿到可靠结果，减少重复手工操作。
当你需要在grilling相关工作中获得稳定、可复用的产出时最适合——无论是单次任务还是纳入日常工作流，都能直接调用。
需要一个具体的项目或任务上下文，最好带有代码仓库或需求文档。