home/categories/productivity-tools/treytucker05-pt-study-sop-projects-treys-agent-context-skills-evaluation-skill-md
productivity-toolstools
evaluation
Evaluate agent and LLM outputs. Use when asked to evaluate agent performance, build evaluation frameworks, implement LLM-as-judge, compare model outputs, create rubrics, mitigate evaluation bias, or design evaluation pipelines and quality gates.
maintainer
Treytucker05
更新日 1/20/2026
スター
1
フォーク
0
quick start
Installation and usage
Evaluate agent and LLM outputs. Use when asked to evaluate agent performance, build evaluation frameworks, implement LLM-as-judge, compare model outputs, create rubrics, mitigate evaluation bias, or design evaluation pipelines and quality gates.
インストール
$ install --globalskills.sh
使い方
インストール後、ターミナルで以下のコマンドを実行してこのスキルを使用できます：
skills use evaluation