メニュー
Create a structured handoff summary when the user asks for a checkpoint. OMP transcript sync is automatic; this skill adds a concise continuation record.
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
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.
| name | save-thread |
| description | Create a structured handoff summary when the user asks for a checkpoint. OMP transcript sync is automatic; this skill adds a concise continuation record. |
The Nowledge Mem OMP plugin automatically syncs completed OMP conversations as searchable threads. This skill creates a structured handoff summary when the user wants a concise checkpoint for a future session.
Do not use this as routine transcript sync. Use it only when a curated handoff would help a future session resume quickly.
nmem --json t create \
-t "Session Handoff - <topic>" \
-c "Goal: ... Decisions: ... Files: ... Risks: ... Next: ..." \
-s generic-agent
Structure the content as a clear handoff. Include only what a future session needs to continue:
Goal: What the session set out to accomplish
Decisions: Key choices made and their rationale
Files: Important files created or modified
Outcome: What was achieved
Risks: Known risks, open questions, or things that could break
Next: Concrete steps for the next session
nmem --json t create \
-t "Session Handoff - Auth Migration to OAuth2" \
-c "Goal: Migrate session auth from JWT to OAuth2 with PKCE.
Decisions: Chose Authorization Code flow with PKCE over Implicit for security. Using passport-oauth2 library.
Files: src/auth/oauth2.ts (new), src/auth/middleware.ts (updated), tests/auth.test.ts (updated).
Outcome: Core flow working, token refresh implemented, tests passing.
Risks: Token refresh not tested under clock skew; CSRF state parameter still missing.
Next: Add CSRF state parameter, update API docs, deploy to staging." \
-s generic-agent
A thread preserves session structure: goals, sequence, context. A memory distills a single insight or decision. They serve different purposes. Use both when appropriate: save the thread for continuity, distill key decisions as standalone memories.