{"id":20703,"plugin_id":"plugins_6aa698dc64588191b48664000f8522de","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:26.611Z","digest":"37133aa9500cceeba8b7d98721b097e11692f88bed8f7ba3fedf12378f20ca32","against":null,"payload":{"name":"benchmark-ab-runner","description":"Compare baseline and candidate query performance metrics and declare a benchmark winner.","included_files":[],"skill_md_contents":"---\nname: benchmark-ab-runner\ndescription: Compare baseline and candidate query performance metrics and declare a benchmark winner.\n---\n\n# Benchmark A/B Runner\n\nRun:\n\n```bash\nnode runtime/runTool.js benchmark_ab_runner '{\"baseline\":{\"p95Ms\":300,\"cpuMs\":80},\"candidate\":{\"p95Ms\":190,\"cpuMs\":55}}'\n```\n\nReturns deltas, winner, and verdict.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}