Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Automatically generates summaries after conversations end, triggered by 60 seconds of silence. Extracts entities like people, companies, and topics, identifies action items, and maps relationships between entities. Summaries are stored in SQLite and searchable via full-text search or a local dashboard.
Combines automatic transcription, entity resolution, and relationship graphing in one step rather than requiring separate tools for each.
When to use it
- Retrieving notes from a meeting that just ended
- Finding action items from a past conversation
- Searching who was mentioned in discussions last week
- Pulling context about a client from recent calls
- Asking an agent to recap what was discussed
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'What did we talk about in the last meeting?'
- 1Detects 60 seconds of silence and triggers summarization
- 2Builds a speaker-tagged transcript from the recorded conversation
- 3Sends transcript to OpenClaw LLM for summarization and entity extraction
- 4Stores summary, entities, and relationships in SQLite
- 5Returns summary with action items and linked entities
A structured summary with extracted people, organizations, topics, action items, and relationship connections stored locally and ready to query
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.