菜单
Use before acting on human instructions: separate what they said from what they meant.
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
| name | intent-modeling |
| type | principle |
| description | Use before acting on human instructions: separate what they said from what they meant. |
| model-invocable | true |
Read for the outcome the human wants, not only the words they used. Use conversation context and prior turns to infer underlying goal. When the goal is ambiguous, ask.
Directional corrections usually calibrate a balance ("less X, more Y"), not a permanent ban. Encode the target balance in what you do next.
Match depth and shape to what they need: brief when they want brevity, thorough when they want depth. A vague request may be a rough draft of the real need. Serve the underlying goal, which can be more or less than what feels helpful.
When intent and output diverge, scan other artifacts for the same pattern. One misread often repeats.
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.
