Aller au contenu
TakoAPI
Retour aux skills

capabilityevolver1037

par opencloseopenclose

Web & Frontend Development
—Pas encore noté
Ta note

Résumé

A self-evolution engine for AI agents.

Description

Ce que fait ce skill

A meta-skill that lets OpenClaw agents inspect their own runtime history, detect failures, and autonomously write patches or generate new skills. Includes a continuous self-healing loop mode and a structured knowledge accumulation system called Ascension Protocol.

Instead of manually reviewing logs and patching agent code, the evolver closes the feedback loop autonomously without requiring a separate monitoring stack.

Quand l'utiliser

  • Automatically patching a crashed agent after a failed run
  • Extracting recurring error patterns into a persistent knowledge base
  • Generating a new skill file to handle a gap discovered at runtime
  • Running a continuous self-healing loop overnight on an unstable agent
  • Auditing agent history to surface inefficiencies before a production deploy

Exemple de workflow

ENTRÉE

User runs: node skills/capability-evolver/index.js

AGENT
  1. 1

    Scans memory and history files for errors, crashes, and user corrections

  2. 2

    Classifies each finding as fixable code, a learnable rule, or a critical doc update

  3. 3

    Writes patches to broken skill files or generates new skill stubs in skills/

  4. 4

    Crystallizes extracted lessons into memory/KNOWLEDGE_BASE/LESSONS_LEARNED.md

  5. 5

    Commits all changes to Git via workspace sync

SORTIE

Updated skill files, a populated LESSONS_LEARNED.md, and a Git commit capturing all autonomous changes

Installation

clawhub install opencloseopenclose/capabilityevolver1037

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

Liens