メニュー
Save a summary of the Copilot CLI session on explicit user request. Copilot lifecycle hooks already capture full transcripts automatically — this skill creates a concise summary thread.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | save-thread |
| description | Save a summary of the Copilot CLI session on explicit user request. Copilot lifecycle hooks already capture full transcripts automatically — this skill creates a concise summary thread. |
Only when user explicitly says: "Save this session" | "Checkpoint this" | "Record conversation"
Lifecycle hooks capture full session transcripts automatically after responses, before compaction, and at session end. This skill is for on-demand summary saves.
Create a summary thread via nmem t create:
nmem t create "A concise summary of this session: what was discussed, what was built, and key decisions made" \
--title "Copilot CLI: <short title from first user message>" \
-s copilot-cli
Important: Write the summary yourself from the current conversation context. Do NOT try to invoke the stop hook script directly — it requires hook payload from Copilot CLI internals.
Automatic lifecycle capture stores real session messages. This skill stores a concise summary thread. Memory stores distilled insights. They are different purposes, and a valuable session can use more than one.
✓ Thread saved
Summary: {summary}
Thread ID: {thread_id from nmem output}
If nmem is not in PATH: pip install nmem-cli, or on Arch Linux yay -S nmem-cli / paru -S nmem-cli
Run nmem status to check server connection.
Use Nowledge Mem from WorkBuddy or CodeBuddy for startup context, memory search, durable saves, thread search, and WorkBuddy/CodeBuddy transcript import.
Read your daily Working Memory briefing to understand current context. Contains active focus areas, priorities, unresolved flags, and recent knowledge changes. Load this automatically at the beginning of sessions for cross-tool continuity.
Search memory store when past insights would improve response. Recognize when user's stored breakthroughs, decisions, or solutions are relevant. Search proactively based on context, not just explicit requests.
Use Nowledge Mem from Kimi Code for startup context, memory search, durable saves, thread search, and Kimi Code transcript import.
Check Nowledge Mem setup, detect your agent, and guide native connector setup. Use when the user asks about setup, configuration, or when memory tools aren't working as expected.
Save decisions, insights, preferences, and procedures as durable memories. Fires when the conversation produces knowledge worth keeping across sessions.