Proactive Self-Improving Agent skill for OpenClaw - combines context protection (WAL/Buffer) with structured learning and safe evolution
npx skills add https://github.com/yanhongxi-openclaw/proactive-self-improving-agent --skill proactive-self-improving-agentCLI를 사용하여 이 스킬을 설치하고 작업 공간에서 SKILL.md 워크플로 사용을 시작하세요.
自动捕获经验 · 安全进化 · 记录轨迹
专为 OpenClaw agent 设计的自改进技能,融合 proactive-agent 的行为准则与 self-improving-agent 的结构化学习系统。
# OpenClaw
openclaw add https://github.com/yanhongxi-openclaw/proactive-self-improving-agent
# 或手动
git clone https://github.com/yanhongxi-openclaw/proactive-self-improving-agent.git ~/.openclaw/skills/proactive-self-improving-agent
安装后 agent 自动加载 SKILL.md。确保 workspace 下有 .learnings/ 目录:
mkdir -p .learnings
详见 SKILL.md。
MIT