Evaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.
Install
npx skills add openai/plugins --skill evaluate-pluginnpx skills add openai/plugins --skill evaluate-plugin -a claude-code -gnpx skills add openai/plugins --skill evaluate-plugin -a codex -ggemini skills install https://github.com/openai/plugins.git --path plugins/plugin-eval/skills/evaluate-plugingh skill install openai/plugins evaluate-plugingit clone --depth 1 https://github.com/openai/plugins /tmp/openai__plugins
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/openai__plugins/plugins/plugin-eval/skills/evaluate-plugin ~/.claude/skills/evaluate-plugin # Claude Code
cp -R /tmp/openai__plugins/plugins/plugin-eval/skills/evaluate-plugin ~/.agents/skills/evaluate-plugin # Codex, Cursor, Gemini CLI, Copilot, OpenCode