Self Improving Agent

This is a meta-programming experiment that lets an AI agent analyze and modify its own skill definitions based on task performance. It watches how well it completes tasks, then edits the SKILL.md files in its workspace to adjust system prompts, tool configurations, and behavior patterns. You'd use this if you're exploring autonomous improvement loops or want an agent that adapts its own instructions over time. The concept is interesting for research, but in practice you're introducing unpredictability into your agent's behavior, which most production use cases probably don't want. Worth trying if you're curious about self-modifying systems, but expect to babysit it.

skills.sh installs: 1.1K
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill self-improving-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

Self-Improving Agent

Auto-memory captures. This plugin curates.

Claude Code's auto-memory (v2.1.32+) automatically records project patterns, debugging insights, and your preferences in MEMORY.md. This plugin adds the intelligence layer: it analyzes what Claude has learned, promotes proven patterns into project rules, and extracts recurring solutions into reusable skills.

Quick Reference

Command	What it does
`/si:memory-review`	Analyze MEMORY.md — find promotion candidates, stale entries, consolidation opportunities
`/si:promote`	Graduate a pattern from MEMORY.md → CLAUDE.md or `.claude/rules/`
`/si:extract`	Turn a proven pattern into a standalone skill
`/si:memory-status`	Memory health dashboard — line counts, topic files, recommendations
`/si:remember`	Explicitly save important knowledge to auto-memory