advanced-evaluation

【开发与工程】ALWAYS use this when the request matches Advanced Evaluation: This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准