Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).
Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).
检测代理输出中的捏造内容、虚假引用和无法验证的声明。使用来源核实和一致性检查。在收到“检测幻觉”、“事实核查”、“验证声明”、“检查准确性”、“查找捏造”等指令时激活。不用于验证（请使用 达格-输出验证器）或置信度评分（请使用 达格-置信度评分器）。
Category: other · Author: curiositech · Version: @main · License: MIT
Tags: dag, quality, hallucination, fact-checking, verification
该 Skill 暂无文档文件。
Category:other
Tags:dag, quality, hallucination, fact-checking, verification