Traditional reinforcement learning methods for interaction skills rely on labor-intensive, manually designed rewards that do not generalize well across different skills. Inspired by how humans learn from demonstrations, we propose ISMimic, the first data-driven approach that Mimics both human and ball motions to learn diverse Interaction Skills, e.g., a wide variety of challenging basketball skills. ISMimic employs a unified configuration to learn diverse interaction skills from human-ball motion datasets, with skill diversity and generalization improving as the dataset grows. This approach allows training a single policy to learn multiple interaction skills and allows smooth skill switching. The interaction skills acquired by ISMimic can be easily reused by a high-level controller to accomplish high-level tasks. To evaluate our approach, we introduce two basketball datasets that collectively contain about 35 minutes of diverse basketball skills. Experiments show that our method can effectively acquire various reusable basketball skills including diverse styles of dribbling, layup, and shooting. Video results and 3D visualization are available at https://ismimic.github.io