Build and maintain a self-evolving skill system that silently captures feedback, graduates repeated feedback into formal rules, improves low-performing skills, and proposes new skills when repeated patterns are not covered. Use when users mention auto evolution, feedback capture, rule graduation, skill optimization, evolution proposals, "that's not right", "you forgot again", "not like this", 自动进化, 反馈沉淀, 规则毕业, Skill 优化, or 新 Skill 提议.
Build and maintain a self-evolving skill system that silently captures feedback, graduates repeated feedback into formal rules, improves low-performing skills, and proposes new skills when repeated patterns are not covered. Use when users mention auto evolution, feedback capture, rule graduation, skill optimization, evolution proposals, "that's not right", "you forgot again", "not like this", 自动进化, 反馈沉淀, 规则毕业, Skill 优化, or 新 Skill 提议.
justinzm
未分类communityv0.1.01 版本99173.6Key: 无需
★ 1
Stars
📥 100
下载
💾 2
安装
1
版本
#latest
概述
[技能说明]
这个 Skill 用来为 Agent 系统建立“先记录、再归纳、后建议、最终扩展”的演化闭环。
It is designed for multilingual teams and should work for both Chinese and English feedback signals.
它的目标不是让 AI 擅自修改规则,而是让系统像自动备份一样无感捕捉问题,再在合适的时机向用户提出可确认、可拒绝的进化建议。
当用户出现“不是这样”“你又忘了”“不对”“我不是让你这么干”等中文表达,或 “that's not right”, “you forgot again”, “this is wrong”, “that's not what I asked”, “don't do it this way”等英文表达时,运行 python scripts/detect_feedback_signal.py --text ""