home/categories/lab-tools/growthxai-output-coding-assistants-claude-plugins-outputai-skills-output-eval-validate-judge-skill-md
lab-toolsresearch
output-eval-validate-judge
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.
maintainer
growthxai
Обновлено 4/8/2026
Звёзды
72
Форки
1
quick start
Installation and usage
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.
Установка
$ install --globalskills.sh
Использование
После установки вы можете использовать этот skill, выполнив следующую команду в терминале:
skills use output-eval-validate-judge