**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison.
Install
npx skills add microsoft/waza --skill wazanpx skills add microsoft/waza --skill waza -a claude-code -gnpx skills add microsoft/waza --skill waza -a codex -ggemini skills install https://github.com/microsoft/waza.git --path skills/wazagh skill install microsoft/waza wazagit clone --depth 1 https://github.com/microsoft/waza /tmp/microsoft__waza
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__waza/skills/waza ~/.claude/skills/waza # Claude Code
cp -R /tmp/microsoft__waza/skills/waza ~/.agents/skills/waza # Codex, Cursor, Gemini CLI, Copilot, OpenCode