Pencak silat is one of a traditional martial art especially in Indonesia that emphasizes precision in kick motion technique. The errors in the motion can lead to injuries, particularly in the leg muscles. Trainers should pay attention to the motion of the trainees to understand proper posture and technique. But, the limitations of the trainer in paying attention to the movements or motion of each trainees allow difficulties to be supervised, therefore requiring assistive system. This study proposes a technology-based solution that provides real-time feedback to support trainer in practice in two kind of kick namely front kick and side kick. The developed system utilizes the YOLOv11 algorithm to detect objects and estimate body pose in motion real time. The dataset was derived from video frame extracting of front and side kick motions by trainees into image in a total of 3,619 images. The preprocessing stages included cropping, keypoint annotation using MediaPipe, bounding box generation, resizing, and data augmentation. Evaluation results showed an accuracy of 92.5%, precision of 92.3%, recall of 92.1%, and an F1-score of 92.2%. The best detection results were achieved in side-kicks. This system can serve as an effective tool for learning the fundamentals of the kick techniques.