As technologies like 3D printing increase in prevalence and capabilities, having a robot hand specifically designed for a given manipulation task also becomes more feasible. Leading to the question of how to design a robot hand for a specific manipulation task. To answer this question, I propose we need three things: benchmarks to quantify the capabilities of a hand design, a way to relate a manipulation task to these benchmarks, and finally, to be able to use these benchmarks to influence the design of hands. This defense presents a robot hand benchmark “Measuring a Robot Hand’s Graspable Region using Power and Precision Grasps", a framework for breaking-down a manipulation task into sub-tasks relatable to benchmarks, and the initial work on using benchmarks for designing hands. In the future, as more benchmarks are developed, the task breakdown framework can be refined, and the design process is finished, there will be a direct procedure to go from a manipulation task to a hand design specifically designed for that task.