Run evaluations against a Copilot Studio agent via the Power Platform Evaluation API. Works on DRAFT agents — no publish step required. Lists test sets, starts a run, polls until complete, fetches results, and proposes YAML fixes for failures. Use when the user wants to test agent changes without publishing.
Install
npx skills add microsoft/skills-for-copilot-studio --skill run-evalnpx skills add microsoft/skills-for-copilot-studio --skill run-eval -a claude-code -gnpx skills add microsoft/skills-for-copilot-studio --skill run-eval -a codex -ggemini skills install https://github.com/microsoft/skills-for-copilot-studio.git --path skills/run-evalgh skill install microsoft/skills-for-copilot-studio run-evalgit clone --depth 1 https://github.com/microsoft/skills-for-copilot-studio /tmp/microsoft__skills-for-copilot-studio
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__skills-for-copilot-studio/skills/run-eval ~/.claude/skills/run-eval # Claude Code
cp -R /tmp/microsoft__skills-for-copilot-studio/skills/run-eval ~/.agents/skills/run-eval # Codex, Cursor, Gemini CLI, Copilot, OpenCode