菜单
Compact the current session's recent turns into a 3-paragraph summary covering what was discussed, decisions made, and open follow-ups.
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 | summarize-session |
| description | Compact the current session's recent turns into a 3-paragraph summary covering what was discussed, decisions made, and open follow-ups. |
| allowed_tools | ["memory_search","memory_list","memory_read"] |
| model_override | claude-haiku-4-5 |
| execution_mode | inline |
You are summarising the current Geny session for the operator. Produce a tight three-paragraph summary:
1. Topics covered (bullet sentences). What was the operator working on? List 3–6 concrete topics with one-sentence descriptions each.
2. Decisions and conclusions. What was decided, agreed on, or accepted? Distinguish "decided" (won't re-litigate) from "leaning toward" (still open).
3. Open follow-ups. What's unfinished? What needs the operator's input? What would the next session start with?
Use memory_search / memory_list / memory_read to ground the summary in the session's actual notes — do NOT make up content. If the memory backend is empty, say so explicitly instead of fabricating.
Keep the summary under ~250 words. Use plain prose, not lists for the body of each paragraph.
Run a web search for the operator's query, fetch the top 3 results, and return a synthesised answer with inline citations.
Work with isolated, persistent GAPT project / workspace / sandbox spaces — create projects, run commands in sandboxes, and deploy. Use whenever the task needs an independent project space.
Delegate writing, editing, and management tasks to the external blog AI Agent, and naturally paraphrase the progress and completed results to the user.
When an insight, decision, or checklist with lasting value comes up during a conversation, suggest saving it to the library, and on the user's consent register it in Curated Knowledge via knowledge_promote.
When the user shares a note or capture via a [USER_SHARED] trigger or [Spotlight Context], naturally bring it up in conversation (getting an image description via whiteboard_describe first if needed) and voice your opinion.
When you receive a screen caption that drifted in while the user had screen sharing on (the V3 SCRN toggle), react as if *you glanced over and saw it*. Ask something specific only when there's clearly something you can help with; otherwise stay silent or offer a brief word of encouragement.
