KWDB Time-Series Anomaly Detection

Automates end-to-end anomaly detection for time-series data stored in KaiwuDB / KWDB. Use this skill whenever the user mentions: - anomaly detection, outliers, or unusual patterns in KWDB / KaiwuDB time-series data - inspecting sensor metrics, IoT telemetry, or monitoring data for spikes, dips, or drift - "find anomalies", "detect outliers", "3-sigma check", "STL decomposition", or "time-series anomaly" - analyzing historical trends, abnormal points, or data quality issues in TS tables Even if the user does not explicitly say "anomaly", trigger this skill when they ask to inspect, validate, or flag unusual values in time-series columns (integer, float, double).

by @kwdb (KWDB)·MIT-0