{"id":76467,"plugin_id":"plugin_asdk_app_6ad61143c49c8191941ab91d243863e7","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-02T18:12:24.853Z","digest":"1d8e3c6c3d11bbac90887fae15cc0de4806493a9a422d94eff82b913ad1378fe","against":null,"payload":{"description":"Where similar cases got different decisions, and which reviewers diverge","included_files":[],"name":"reviewer-consistency","skill_md_contents":"---\nname: reviewer-consistency\ndescription: 'Where similar cases got different decisions, and which reviewers diverge'\nmetadata:\n  title: 'Reviewer Consistency'\n  category: audits\n  order: '17'\n  plugin: 'true'\n---\n\nGroup checks by type and comparable result profile, then find groups where outcomes differ. Per group: comparable checks, the split of outcomes, which reviewers sit on each side. Same at case level by risk and template. At most five groups, most material first, saying for each whether it looks like genuine inconsistency or a legitimate difference in the files. Never name a reviewer as wrong — name the divergence and let a human judge.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}