Advanced Evaluation

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.

Optimized workflow

This edition turns the source methodology into a repeatable agent workflow with explicit inputs, checkpoints and deliverables.

Quality standard

• Confirm scope and missing inputs before execution
• Ground decisions in available evidence and preserve source constraints
• Return an actionable result with assumptions, risks and next steps

Agent compatibility

The same core method is packaged for Claude, Codex, GPT, Gemini, Cursor and OpenCode.