Menu
生成 session work log，检查是否需要更新 AGENTS.md，并清理临时文件。用于替代 session-summary 和 stop-summary hooks。
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Use when the user asks to generate or refresh an architecture map, structure diagram, core call flow, local viewer assets, or runs ~map. Produces hello-scholar native architecture-map.json plus compact Markdown and Mermaid companion artifacts.
Use when the user asks to open the architecture viewer, view diagrams, inspect node evidence, export the local architecture map, or troubleshoot hello-scholar map view/export behavior.
实验分析命令，基于 experiment package、runs、metrics 和 evidence 形成结果解释与下一轮实验计划。
实现命令，把 plan package、change record 或 experiment package 落成代码、配置、文档或实验变更。
Use only when the user explicitly types ~map. Generates or refreshes the hello-scholar native architecture map by invoking the architecture-map workflow, then validates and points to the local viewer.
用于涉及编写或修改源码的日常编码任务。
| name | session-wrap-up |
| description | 生成 session work log，检查是否需要更新 AGENTS.md，并清理临时文件。用于替代 session-summary 和 stop-summary hooks。 |
| tags | ["Workflow","Session","Productivity"] |
生成完整的 session summary，并执行收尾清理任务。
在以下场景触发该 skill：
如果当前仓库中可用，先运行：
python3 ".hello-scholar/skills/codex-hook-emulation/scripts/codex_hook_emulation.py" session-end --cwd "$PWD"
如果当前模式是 global，则将 helper path 替换为：
python3 "$HOME/.codex/plugins/cache/local-plugins/hello-scholar/local/skills/codex-hook-emulation/scripts/codex_hook_emulation.py" session-end --cwd "$PWD"
把该输出当作 Codex 对 SessionEnd / Stop hook 的确定性替代，再撰写最终的人类可读总结。
Only present a final complete, waiting, or blocked status at the actual end of the turn. Progress updates and intermediate summaries must not be phrased as final completion. When the project provides structured turn-state helpers, write machine-readable status before the final closeout and include reason category plus reason for waiting or blocked states.
总结本次 session：
📋 本次操作回顾
1. [List main operations performed]
2. [List files modified/created]
📊 当前状态
• Git: [branch, uncommitted changes count]
• Tests: [pass/fail status if applicable]
• Build: [status if applicable]
💡 下一步建议
1. [Actionable next steps]
扫描是否存在需要更新 AGENTS.md 的变化：
如果需要更新，提出具体修改建议。
检查哪些临时文件应被清理：
/temp/ 目录内容/plan/ 目录中的已完成计划报告发现，并在删除前征求确认。
展示：
始终使用以上结构化格式。保持总结简洁，但信息完整。