Deterministically score comparable imported review-run lanes with root-cause metrics and uncertainty. Use only when the user explicitly asks to benchmark normalized local review runs or use the bundled synthetic fixture.
安装
npx skills add openai/community-plugins --skill benchmark-review-configsnpx skills add openai/community-plugins --skill benchmark-review-configs -a claude-code -gnpx skills add openai/community-plugins --skill benchmark-review-configs -a codex -ggemini skills install https://github.com/openai/community-plugins.git --path plugins/reviewops-auditor-benchmark/skills/benchmark-review-configsgh skill install openai/community-plugins benchmark-review-configsgit clone --depth 1 https://github.com/openai/community-plugins /tmp/openai__community-plugins
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/openai__community-plugins/plugins/reviewops-auditor-benchmark/skills/benchmark-review-configs ~/.claude/skills/benchmark-review-configs # Claude Code
cp -R /tmp/openai__community-plugins/plugins/reviewops-auditor-benchmark/skills/benchmark-review-configs ~/.agents/skills/benchmark-review-configs # Codex, Cursor, Gemini CLI, Copilot, OpenCode