We present an approach to wearable sensor-based assessment of motor function in individuals post stroke. We make use of one on-body inertial measurement unit (IMU) to automate the functional ability (FA) scoring of the Wolf Motor Function Test (WMFT). WMFT is an assessment instrument used to determine the functional motor capabilities of individuals post stroke. It is comprised of 17 tasks, 15 of which are rated according to performance time and quality of motion. We present signal processing and machine learning tools to estimate the WMFT FA scores of the 15 tasks using IMU data. We treat this as a classification problem in multidimensional feature space and use a supervised learning approach.