We assess the forecasting skill of the system as it is a prototype real-time operational forecast system. This seasonal fire forecast system is based on operational dynamical climate forecast systems. In addition, all the forecasts are done by using cross-validation in order to evaluate the predictions as if they were done operationally, including the steps of the bias correction of the seasonal climate data and of the calibration of the fire-climate models. Moreover, to avoid artificial skill, the observed series are de-trended and standardized in each step of the cross-validation, avoiding using observation of the predicted year.