verified-capability-evolver

Community

Safely evolve AI capabilities with verification.

Authorwjlmrzd
Version1.0.0
Installs0

System Documentation

What problem does it solve?

AI agents frequently evolve in uncontrolled ways, risking drift, degraded reliability, and unsafe behaviors. This skill provides structured, verifiable self-improvement with rollback and promotion controls to ensure changes are deliberate and auditable.

Core Features & Use Cases

  • Structured learning logs with clearly tracked entries and statuses
  • Gate promotion with verification steps to prevent unsafe upgrades
  • Rollback safety and auditable rollback paths for failed improvements
  • Optional external verification to validate changes before adoption
  • Applicable to long-running autonomous agents and complex workflows

Quick Start

Log a learning event, define evaluation criteria, and request verification before promoting the change.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: verified-capability-evolver
Download link: https://github.com/wjlmrzd/OpenClaw-Wren/archive/main.zip#verified-capability-evolver

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.