task-boundary-auditor

关于这个 Skill

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 omissions", "real-time monitor", "legal/medical judgment".