Use this skill whenever the user wants to evaluate, test, or validate an AI agent, decide whether an agent is ready to ship or go live, choose how to grade an agent's answers (exact match, similarity, meaning, keywords, quality, or custom), design a test set of questions and expected answers, or interpret evaluation results into a go/no-go decision.
Install
npx skills add microsoft/cat-agent-skills --skill agent-evaluation-designernpx skills add microsoft/cat-agent-skills --skill agent-evaluation-designer -a claude-code -gnpx skills add microsoft/cat-agent-skills --skill agent-evaluation-designer -a codex -ggemini skills install https://github.com/microsoft/cat-agent-skills.git --path submissions/agent-evaluation-designergh skill install microsoft/cat-agent-skills agent-evaluation-designergit clone --depth 1 https://github.com/microsoft/cat-agent-skills /tmp/microsoft__cat-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__cat-agent-skills/submissions/agent-evaluation-designer ~/.claude/skills/agent-evaluation-designer # Claude Code
cp -R /tmp/microsoft__cat-agent-skills/submissions/agent-evaluation-designer ~/.agents/skills/agent-evaluation-designer # Codex, Cursor, Gemini CLI, Copilot, OpenCode