Skill 审计报告

detect-hallucinations 审计报告.

Use this to detect when an LLM is making things up, so you can flag or block confident-but-wrong answers before users see them. Trigger on "detect hallucinations", "is the model making this up", "flag unreliable answers", "hallucination check", "confidence scoring for LLM output", or hardening a RAG/QA system. Pick a method that matches whether you have reference context or not.