This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
Install
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill evaluationnpx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill evaluation -a claude-code -gnpx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill evaluation -a codex -ggemini skills install https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering.git --path skills/evaluationgh skill install muratcankoylan/Agent-Skills-for-Context-Engineering evaluationgit clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering/skills/evaluation ~/.claude/skills/evaluation # Claude Code
cp -R /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering/skills/evaluation ~/.agents/skills/evaluation # Codex, Cursor, Gemini CLI, Copilot, OpenCode