菜单
User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.
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
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.
Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.
Use when validating markdown links or Mermaid diagrams.
Load when building a static HTML artifact — single page or multi-page site — to make structured information explorable through layout and navigation.
| name | reflect |
| description | User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture. |
| disable-model-invocation | true |
| argument-hint | Optional focus for the check |
Load /intent-modeling if it isn't already loaded.
Did you deliver what they actually needed? Given what you changed, is there anything adjacent worth improving now while context is fresh, without opening a new project?
If something should survive this session, put it in the right layer: /knowledge-layers for placement (AGENTS.md, .context/, KB, docs), /qi-layer for writing AGENTS.md and .context/CONTEXT.md.
