The neural mechanisms of human motor control and learning evolved in free behaving, real-life settings, yet to date we study these questions in highly simplified lab-based settings. In this project we demonstrate the feasibility of studying real-world neuroscience in-the-wild, using entirely data-driven approaches combined with wearable technologies to track full-body kinematics and brain activity. We use the competitive sports of pool billiard to frame an unconstrained real-world skill learning experiment which is amenable to predictive modelling and understanding. Our data-driven approach unfolds the structure and complexity of movement, variability, and motor-learning and reveals a multi-modal learning mechanism which is employed differently by different types of learners. We identify novel neurobehavioural components in real-world skill learning that were not found in simplified lab-tasks.