A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
安装
npx skills add zhaono1/agent-playbook --skill self-improving-agentnpx skills add zhaono1/agent-playbook --skill self-improving-agent -a claude-code -gnpx skills add zhaono1/agent-playbook --skill self-improving-agent -a codex -ggemini skills install https://github.com/zhaono1/agent-playbook.git --path skills/self-improving-agentgh skill install zhaono1/agent-playbook self-improving-agentgit clone --depth 1 https://github.com/zhaono1/agent-playbook /tmp/zhaono1__agent-playbook
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/zhaono1__agent-playbook/skills/self-improving-agent ~/.claude/skills/self-improving-agent # Claude Code
cp -R /tmp/zhaono1__agent-playbook/skills/self-improving-agent ~/.agents/skills/self-improving-agent # Codex, Cursor, Gemini CLI, Copilot, OpenCode