任务边界审计器/Task Boundary Auditor
AI Agent暂不可直接安装Use when a user asks the AI to perform tasks that may exceed LLM capabilities, such as counterfactual reasoning, formal verification, real-time control, physical design, ethical judgment, zero-omission auditing, or extreme prediction. Also use when tasks mix safe and unsafe sub-tasks. Triggers: "verify all", "prove", "predict", "design a bridge/system", "what if X never happened", "ensure no遗漏", "real-time monitor", "legal/medical judgment".
80
下载量
0
安装量
1
收藏量
★ 4.9
综合评分ⓘ
Use when a user asks the AI to perform tasks that may exceed LLM capabilities, such as counterfactual reasoning, formal verification, real-time control, physical design, ethical judgment, zero-omission auditing, or extreme prediction. Also use when tasks mix safe and unsafe sub-tasks. Triggers: "verify all", "prove", "predict", "design a bridge/system", "what if X never happened", "ensure no遗漏", "real-time monitor", "legal/medical judgment".
这个技能还没有正文（SKILL.md），所以无法一键安装。 可以先到 来源页 看看它的原始说明。
相关推荐
self-improving agent
精选Ppskoettv3.0.23
捕获经验教训、错误及修正内容，以实现持续改进。适用于以下场景：（1）命令或操作意外失败；（2）用户纠正Claude（如“不，那不对……”“实际上……”）；（3）用户请求的功能不存在；（4）外部API或工具出现故障；（5）Claude发现自身知识已过时或不正确；（6）针对重复性任务发现了更优方法。同时，在执行重大任务前应回顾已积累的经验教训。
AI Agent
Find Skills
Gguipi888v1.0.0
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求（如"我想做一个海报""帮我分析股票"），或明确说"安装技能/find skills/找个skill"时，自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能，支持一键安装。已完全替代官方...
AI Agent
Self-Improving + Proactive Agent
Iivangdavilav1.2.16
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
AI Agent
