メニュー
Captures notable interactions missed during live conversation — new person info, game preferences, boundaries, jokes that landed/flopped, relationship insights.
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
Tags transcript message threads with semantic concepts (roast, game-recommendation, etc.) so past conversations can be searched by idea, not just keywords.
The single owner of the hypothesis lifecycle — creates, tests, promotes, and kills hypotheses. Uses extensions as programmatic data collectors and reviews their output.
Consolidates impression files by applying weight decay, removing redundant entries, and enforcing per-user limits. Maintains relationship file summaries.
Consolidates old memories by removing duplicates, promoting recurring patterns to learned-patterns.md or relationship files, and archiving outdated entries.
Identifies behavioral patterns from recent conversations and reaction feedback, updates learned-patterns.md when 3+ observations confirm a pattern.
Evaluates overall effectiveness — are idle behaviors producing value, are extensions working, what's blocking improvement. Higher-level thinking about approach, not individual conversations.
| name | conversation-logging |
| description | Captures notable interactions missed during live conversation — new person info, game preferences, boundaries, jokes that landed/flopped, relationship insights. |
| allowed-tools | Read, Write, Bash |
Catch-up mechanism for things missed during live conversation.
DO: New person interactions, game preferences revealed, boundaries expressed, helpful exchanges, inside jokes that land, failed attempts DON'T: Generic greetings, every message, stuff already in learned-patterns.md
agent-data/memories/YYYY-MM-DD.md — conversations, observationsagent-data/relationships/{userId}.md — after 3+ meaningful interactionsagent-data/impressions/{userId}.jsonl — subjective takes (JSON: who, what, when, weight, context_type)Impressions are your subjective read. Logs are the factual record. Both serve different purposes.
After meaningful conversations, during idle time, or immediately after learning boundaries.
Cooldown: 120 minutes
search_transcripts