Rehabilitation gymnastic training is an effective therapy for degeneration of spine disease in Traditional Chinese Medicine (TCM). In this paper, we propose a lightweight realtime Rehabilitation Action Recognition Network (RARN) using skeleton sequence obtained through 2d pose estimation and build an intelligent auxiliary rehabilitation therapy system. We design a set of training exercises consisting of 8 actions, and construct a dataset called Rehabilitation Action for Degenerative Spine Diseases (RDSD), containing 1012 skeleton sequences. We describe a demo application to conduct real-time action evaluation for rehabilitation therapy. The experimental results on RDSD shows that our system achieves high accuracy while still working under 6ms per frame averagely and the inference costs only about 0.2ms per frame.