Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/myagent:humanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
决定何时让用户确认、何时自动执行,以及如何从用户反馈中学习。
决定何时让用户确认、何时自动执行,以及如何从用户反馈中学习。
snippets/human/progressive-trust.ts — 渐进信任 + 规则建议 + 反馈闭环 + 竞赛解决器 + 异步分类器| 错误 | 后果 | 正确做法 |
|---|---|---|
| 只有 allow/deny | 太松或太紧 | 三态 + 规则建议 |
| 反馈文本丢弃 | 用户重复说 | 注入对话上下文 |
| 无拒绝跟踪 | 分类器反复被拒 | 自适应回退 |
| 无恩惠期 | 启动误触 | 200ms grace period |
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub dongliutony/myagent-skill --plugin myagent