self-improve-harness

Community

Autonomous self-improvement loop for skills

Authoroldmangrizzz
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides an autonomous, safe loop to continuously improve an agent's skills, prompts, and docs by coordinating proposals, scoring, approvals, and atomic rollbacks.

Core Features & Use Cases

  • Orchestrator that runs on a schedule to identify weak or stale targets in a manifest of skills, docs, and configs.
  • Proposer/scorer integration with a validation step and rollback that ensures changes are reversible and auditable.
  • Handles quiet hours, manual approvals, and audit logging for production-grade safety.

Quick Start

Install the harness, configure your manifest, and run the loop orchestrator to begin autonomous improvements.

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: self-improve-harness
Download link: https://github.com/oldmangrizzz/REAL_JARVIS/archive/main.zip#self-improve-harness

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.