Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.
Install
npx skills add github/awesome-copilot --skill arize-experimentnpx skills add github/awesome-copilot --skill arize-experiment -a claude-code -gnpx skills add github/awesome-copilot --skill arize-experiment -a codex -ggemini skills install https://github.com/github/awesome-copilot.git --path skills/arize-experimentgh skill install github/awesome-copilot arize-experimentgit clone --depth 1 https://github.com/github/awesome-copilot /tmp/github__awesome-copilot
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/github__awesome-copilot/skills/arize-experiment ~/.claude/skills/arize-experiment # Claude Code
cp -R /tmp/github__awesome-copilot/skills/arize-experiment ~/.agents/skills/arize-experiment # Codex, Cursor, Gemini CLI, Copilot, OpenCode