{"skill":{"slug":"outlier-detection-handler","displayName":"Outlier Detection & Handling","summary":"Use outlier detection handler for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.","tags":{"latest":"1.0.1"},"stats":{"comments":0,"downloads":125,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":2},"createdAt":1774849890568,"updatedAt":1774854709300},"latestVersion":{"version":"1.0.1","createdAt":1774854033283,"changelog":"Initial release of outlier-detection-handler.\n\n- Provides structured workflows for identifying and managing statistical outliers in data analysis.\n- Supports configurable detection methods (\"3-sigma\", \"IQR\", \"Grubbs\") and actions (\"flag\", \"remove\", \"winsorize\").\n- Emphasizes explicit assumptions, input validation, reproducible outputs, and clear documentation.\n- Includes risk and security checklists, audit-ready commands, and fallback/error-handling guidelines.\n- Targets use cases such as data quality control, pre-analysis screening, and regulatory compliance.","license":"MIT-0"},"metadata":null,"owner":{"handle":"aipoch-ai","userId":"s17fjw78yq6wtd4ep6zsaxwrn983hznr","displayName":"AIpoch","image":"https://avatars.githubusercontent.com/u/258999481?v=4"},"moderation":null}