MiniHack is a sandbox framework for easily designing rich and diverse environments for Reinforcement Learning (RL). MiniHack includes a collection of example environments that can be used to test various capabilities of RL agents, as well as serve as building blocks for researchers wishing to develop their own environments. MiniHack's navigation tasks challenge the agent to reach the goal position by overcoming various difficulties on their way, such as fighting monsters in corridors, crossing a river by pushing boulders into it, navigating through complex, procedurally generated mazes, etc. MiniHack's skill acquisition tasks enable utilising the rich diversity of NetHack objects, monsters and dungeon features, and the interactions between them. The skill acquisition tasks feature a large action space (75 actions), where the actions are instantiated differently depending on which object they are acting on.