Create a test set CSV file for import into Copilot Studio's in-product Evaluate tab. Reads the agent's topics, instructions, and knowledge sources to generate meaningful test cases with appropriate graders (General quality, Compare meaning, Exact match, etc.). Use when the user asks to create, prepare, or generate evaluation test cases for their agent.
Install
npx skills add microsoft/skills-for-copilot-studio --skill create-eval-setnpx skills add microsoft/skills-for-copilot-studio --skill create-eval-set -a claude-code -gnpx skills add microsoft/skills-for-copilot-studio --skill create-eval-set -a codex -ggemini skills install https://github.com/microsoft/skills-for-copilot-studio.git --path skills/create-eval-setgh skill install microsoft/skills-for-copilot-studio create-eval-setgit 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/create-eval-set ~/.claude/skills/create-eval-set # Claude Code
cp -R /tmp/microsoft__skills-for-copilot-studio/skills/create-eval-set ~/.agents/skills/create-eval-set # Codex, Cursor, Gemini CLI, Copilot, OpenCode