self-skill-evolver

Analyze and improve OpenClaw agent skills by tracking usage, checking skill health, scanning code quality, and generating actionable improvement suggestions. Use when evaluating skill reliability, performance, maintainability, or release readiness.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "self-skill-evolver" with this command: npx skills add harrylabsj/self-skill-evolver

Self Skill Evolver

A Python CLI tool for analyzing and improving OpenClaw agent skills.

Features

usage monitoring
skill health scoring
SKILL.md and code analysis
automated improvement suggestions
JSON / Markdown / HTML reporting

Installation

clawhub install self-skill-evolver

Typical Commands

self-skill-evolver init
self-skill-evolver analyze <skill-name>
self-skill-evolver analyze --all
self-skill-evolver report <skill-name>
self-skill-evolver report --all
self-skill-evolver health <skill-name>
self-skill-evolver health --all
self-skill-evolver log <skill-name> <action> --status success --duration 100
self-skill-evolver feedback <skill-name> 5 --comment "Very helpful"
self-skill-evolver clear --days 90
self-skill-evolver log --list

Dependencies

Python 3.8+
SQLite3
PyYAML
GitPython (optional)

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open Registry Record Open in ClawHub

Related Skills

Related by shared tags or category signals.

Coding

Web Research Assistant

AI-powered web research assistant that leverages BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.

Registry SourceRecently Updated

2.5K3phheng

Coding

Pandoc Convert

Convert documents between 40+ formats using pandoc CLI. Handles Markdown ↔ Word ↔ PDF ↔ HTML ↔ LaTeX ↔ EPUB with smart defaults, professional templates, and comprehensive tooling.

Registry SourceRecently Updated

1.9K1thejorgeschmidt

Coding

Monitored Ralph Loop

Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a "Ralph loop", "Ralph Wiggum loop", or an AI loop to plan/build code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENTATION_PLAN.md, including PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions.

Registry SourceRecently Updated

1.3K0endogen

Coding

Forge

Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology with BDD/Gherkin specifications, 7 quality gates, defect prediction, chaos testing, and cross-context dependency awareness. Architecture-agnostic — works with monoliths, microservices, modular monoliths, and any bounded-context topology.

Registry SourceRecently Updated

1.5K0ikennaokpala