菜单
Use when choosing which repository instructions, architecture, domain knowledge, files, tests, or deep guidance to load for a task without reading everything.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ihabkhaled/AI-Psychiatry --skill context-router命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.
Use when the user explicitly requests the complete AI-Psychiatry framework through one all-in-one command that evaluates and orchestrates every available skill until the task is proven complete.
Use when the user explicitly requests the complete AI-Psychiatry framework through one all-in-one command that evaluates and orchestrates every available skill until the task is proven complete.
基于 SOC 职业分类
正在显示 SKILL.md
| name | context-router |
| description | Use when choosing which repository instructions, architecture, domain knowledge, files, tests, or deep guidance to load for a task without reading everything. |
Load minimal sufficient context in layers: boot, task index, domain, exact rules and files, then deep architecture only when required.
Task type, context layers loaded, canonical sources, and freshness.
Ordinary tasks should rarely use deep layer L4.
Do not read every AI or architecture document before locating the relevant source.
Stop when context is sufficient for reliable action and additional reading has no completion value.
