Safe Self Improving
v0.3.0A privacy-first, consent-based self-improvement skill for AI agents. Captures learnings, errors, best practices with auto-sanitization and duplicate detection. Includes smart skill synthesis — auto-generates new skill drafts from recurring patterns. No hooks, no cross-session, no silent modification. All operations require user confirmation.
0· 0·0 当前·0 累计
by 下载技能包
License
MIT-0
运行时依赖
无特殊依赖
安装命令
点击复制官方npx clawhub@latest install safe-self-improving
镜像加速npx clawhub@latest install safe-self-improving --registry https://cn.longxiaskill.com 镜像可用