llm-aidata-ai
evaluation
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
maintainer
sickn33
Обновлено 3/20/2026
Звёзды
32093
Форки
5340
quick start
Installation and usage
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
Установка
$ install --globalskills.sh
Использование
После установки вы можете использовать этот skill, выполнив следующую команду в терминале:
skills use evaluation