Write Judge Prompt

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.

eggboy Updated

File contents

eggboy/skills commit 0b399f4b35

Frequently asked questions

npx get-skill add eggboy/write-judge-prompt