Author, validate, and run Vally evaluation suites for agent skills. TRIGGERS: create eval, write eval, add eval, run eval, validate eval, vally eval, eval.yaml, add stimulus, map test to eval, migrate test to eval, eval graders, eval scoring, add eval to CI.
安装
npx skills add microsoft/GitHub-Copilot-for-Azure --skill vally-evalnpx skills add microsoft/GitHub-Copilot-for-Azure --skill vally-eval -a claude-code -gnpx skills add microsoft/GitHub-Copilot-for-Azure --skill vally-eval -a codex -ggemini skills install https://github.com/microsoft/GitHub-Copilot-for-Azure.git --path .github/skills/vally-evalgh skill install microsoft/GitHub-Copilot-for-Azure vally-evalgit clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure /tmp/microsoft__GitHub-Copilot-for-Azure
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__GitHub-Copilot-for-Azure/.github/skills/vally-eval ~/.claude/skills/vally-eval # Claude Code
cp -R /tmp/microsoft__GitHub-Copilot-for-Azure/.github/skills/vally-eval ~/.agents/skills/vally-eval # Codex, Cursor, Gemini CLI, Copilot, OpenCode