Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
根据多种因素（包括来源质量、一致性和推理深度）为代理输出分配置信度分数。生成经过校准的置信度估计。在“置信度分数”、“有多自信”、“确定性级别”、“输出置信度”、“可靠性分数”等触发词被激活时使用。不用于验证（请使用 dag-输出-验证器）或幻觉检测（请使用 dag-幻觉-检测器）。
Category: other · Author: curiositech · Version: @main · License: MIT
Tags: dag, quality, confidence, scoring, reliability
该 Skill 暂无文档文件。
Category:other
Tags:dag, quality, confidence, scoring, reliability