Self-improvement helps an AI agent learn from its mistakes. It captures errors, corrections, and new ideas in simple markdown files. Over time the agent gets better at helping you because it remembers what went wrong and what works.
Whenever a command fails or you correct the agent, it logs that lesson. It also tracks missing features and outdated knowledge. This makes every interaction smarter than the last. The agent can even promote important lessons into its long-term memory for future projects.
Global
mkdir -p ~/.claude/skills/self-improvementProject
mkdir -p .claude/skills/self-improvementSource Repository
Setup Matt Pocock Skillsmattpocock/skills
Set up your repo for engineering skills with just a few guided steps
Lark Skill Makerlarksuite/cli
Create reusable skills to automate Feishu tasks with lark-cli commands
Teachmattpocock/skills
Teach yourself any skill with guided lessons and mission-driven practice
Write A Skillmattpocock/skills
Build new agent skills with clear structure and bundled resources
Writing Great Skillsmattpocock/skills
A guide for writing predictable AI agent skills with clear principles and reliable behavior
Ask Mattmattpocock/skills
Pick the perfect skill or flow for your project every time
Writing Skillsobra/superpowers
Test your agent skills like code to make them truly effective
Animejsheygen-com/hyperframes
Safely add Anime.js animations to your HyperFrames compositions with seek control