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.

Ghosteken Updated
DEFINE → PLAN → BUILD → VERIFY → REVIEW → SHIP pipeline

File contents

Ghosteken/agent-harness commit 6a12b4f264

Frequently asked questions

npx get-skill add ghosteken/advanced-evaluation