Large inter-month variations of summer precipitation tend to cause alternations or transitions of extreme drought and flood in China, but seasonal averages may cover alternations on monthly scale, and affect the prediction skills on seasonal scale. Thus, it is necessary to improve the forecast of monthly climate which contribute to the enhancement of predictions on seasonal scale. This study focuses on the real-time predictions of monthly precipitation at 160 stations in China during the summer season (June, July, and August) with the year-to-year increment method and the field information coupled pattern method, and further calculate the seasonal precipitation with monthly predictions. The information from preceding observations and simultaneous predictions from the second version of Climate Forecast System (CFSv2) are considered. Consequently, the observed sea surface temperature (SST) over the mid-high latitude of the South Pacific in December, the observed sea ice concentration (SIC) in the critical region of the Arctic in January, and the simultaneous SST from CFSv2 released in February are selected as predictors to develop the downscaling model. Prediction models based on individual predictors are established firstly to evaluate the prediction skills of different predictors, and then the singular value decomposition (SVD) error correction method is applied to diminish the errors of downscaling models. The optimized ensemble scheme is also adopted to synthesize hybrid downscaling models for summer precipitation over China on monthly scale with higher stability, and further seasonal prediction is conducted with results on monthly scale. The re-forecast results during the period 1983?2022 showed that the hybrid downscaling models derived from the optimized ensemble scheme exhibit comprehensive prediction skills compared with single-predictor models. The percentages of stations, at which the time anomaly correlation coefficients of re-forecast results are larger than the 90% confidence level, count for 90%, 88%, and 82% respectively for June, July, and August. The mean values of the spatial anomaly correlation coefficients are respectively 0.39, 0.40, and 0.39, passing the 99% confidence level. For real-time prediction, the hybrid downscaling models perform well at both monthly and seasonal scales during 2020?2022, when summer precipitation situations are anomalous and different from each other under similar La Ni?a events. The averaged Ps scores of real-time predictions are respectively 75, 75, and 70 for precipitation in June, July, and August. The Ps scores for summer precipitation derived from monthly predictions are 72, 76, and 73 from 2020 to 2022, which are higher than the multi-year-averaged Ps score of real-time forecasts. Hence, seasonal predictions derived from effective monthly forecasts would improve the prediction skills of climate predictions on monthly–seasonal scale.