{"id":20693,"plugin_id":"plugins_6aa698dc64588191b48664000f8522de","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:26.391Z","digest":"c1dc1f7b5b1cf1a752c4bcca69bc71a9b91b0d696199d4920d2bde28697b2d13","against":null,"payload":{"name":"autonomous-learning-backlog","description":"Prioritize missing evidence and follow-up experiments from database advisor feedback.","included_files":[],"skill_md_contents":"---\nname: autonomous-learning-backlog\ndescription: Prioritize missing evidence and follow-up experiments from database advisor feedback.\n---\n\n# autonomous_learning_backlog\n\nUse this skill to convert advisor feedback, incidents, and outcomes into prioritized AI learning tasks.\n\nGovernance:\n- Analysis-only backlog generation.\n- Do not mutate models, policies, or production systems.\n- Prioritize rollback evidence, confidence calibration, incident patterns, and prompt safety.\n\nOutput contract:\n- `usp: \"autonomous_learning_backlog\"`\n- `executionMode: \"analysis_only\"`\n- `learningBacklog`\n- `evidence`, `confidence`, `source: \"analysis\"`\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}