Aller au contenu
TakoAPI
Retour aux skills

percept-summarize

par jarvis563

Transportation
306Téléchargements rapportés par clawskills.sh
1Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Automatic conversation summaries with entity extraction and relationship mapping.

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

User asks: 'What did we talk about in the last meeting?'

AGENT
  1. 1

    Detects 60 seconds of silence and triggers summarization

  2. 2

    Builds a speaker-tagged transcript from the recorded conversation

  3. 3

    Sends transcript to OpenClaw LLM for summarization and entity extraction

  4. 4

    Stores summary, entities, and relationships in SQLite

  5. 5

    Returns summary with action items and linked entities

SORTIE

A structured summary with extracted people, organizations, topics, action items, and relationship connections stored locally and ready to query

Prérequis

  • percept-listen skill installed and running

Installation

clawhub install jarvis563/percept-summarize

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens