home/categories/code-quality/hamelsmu-evals-skills-skills-write-judge-prompt-skill-md
code-qualitytesting-security

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.

hamelsmu
maintainer
hamelsmu
Atualizado 3/3/2026
Estrelas
1105
Forks
117
quick start

Installation and usage

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.

Instalação
$ install --globalskills.sh
Uso

Depois de instalar, você pode usar esta skill executando o seguinte comando no terminal:

skills use write-judge-prompt