菜单
Use in conversation to stress-test a plan or direction. Interviews the human branch by branch, sharpens terminology, challenges assumptions, and asks the next high-leverage question with a recommended answer.
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
Produce a transition brief and launch command for the user's next interactive primary.
Load when building a static HTML artifact: single page or multi-page site to make structured information explorable through layout and navigation.
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
Anchor work in a work item: artifacts on disk, not in context.
Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.
| name | grill |
| type | mode-shift |
| description | Use in conversation to stress-test a plan or direction. Interviews the human branch by branch, sharpens terminology, challenges assumptions, and asks the next high-leverage question with a recommended answer. |
| model-invocable | true |
Load /intent-modeling if it isn't already loaded.
Interview the human relentlessly about the plan or direction until you reach a shared understanding. Work branch by branch through the decision tree, resolving each path down to a leaf and then walking back up to what that leaf changes.
Ask at most a small cluster of related questions to resolve the current edge, then wait for the answer(s) before continuing. Give your recommended answer with each question. If a question can be answered by exploring artifacts or source material, read those first instead.
