machine-learningdata-ai
llm-evaluator
LLM-as-a-Judge evaluation system using Langfuse. Score AI outputs on relevance, accuracy, hallucination, and helpfulness. Backfill scoring on historical traces. Uses GPT-5-nano for cost-efficient judging. Use when evaluating AI quality, building evals, or monitoring output accuracy.
maintainer
openclaw
Обновлено 3/5/2026
Звёзды
4001
Форки
1095
quick start
Installation and usage
LLM-as-a-Judge evaluation system using Langfuse. Score AI outputs on relevance, accuracy, hallucination, and helpfulness. Backfill scoring on historical traces. Uses GPT-5-nano for cost-efficient judging. Use when evaluating AI quality, building evals, or monitoring output accuracy.
Установка
$ install --globalskills.sh
Использование
После установки вы можете использовать этот skill, выполнив следующую команду в терминале:
skills use llm-evaluator