Validate and normalize declared local review-run exports into a bounded canonical summary. Use only when the user explicitly asks to normalize review runs or use the bundled synthetic fixture.
Install
npx skills add openai/community-plugins --skill normalize-review-runsnpx skills add openai/community-plugins --skill normalize-review-runs -a claude-code -gnpx skills add openai/community-plugins --skill normalize-review-runs -a codex -ggemini skills install https://github.com/openai/community-plugins.git --path plugins/reviewops-auditor-benchmark/skills/normalize-review-runsgh skill install openai/community-plugins normalize-review-runsgit 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/normalize-review-runs ~/.claude/skills/normalize-review-runs # Claude Code
cp -R /tmp/openai__community-plugins/plugins/reviewops-auditor-benchmark/skills/normalize-review-runs ~/.agents/skills/normalize-review-runs # Codex, Cursor, Gemini CLI, Copilot, OpenCode