Use this skill when forecasting time series data, modeling trend/seasonality, applying ARIMA/SARIMA/Prophet/LSTM/TFT, or performing temporal cross-validation. This skill enforces: decomposition analysis (trend/seasonality/residual), stationarity testing, model selection by data characteristics, temporal cross-validation, forecast evaluation with MASE/sMAPE. Do NOT use for: generic regression on non-temporal data, anomaly detection in time series (use ml-anomaly-detection), causal inference with time series, or real-time streaming (use data-streaming skill).
