The growing proliferation of wind power into the power grid achieves a low-cost sustainable electricity supply while introducing technical challenges with associated intermittency. This paper proposes a fully adaptive distributionally robust multistage framework based on mixed decision rules (MDR) for generation scheduling under uncertainty to adapt wind power respecting non-anticipativity in quick-start unit status decision and dispatch process. Compared with existing multistage models, the proposed framework introduces improved MDR to handle all decision variables to expand the feasible region. Therefore, our model can find a feasible solution to some problems that are not feasible in the traditional models while finding a better solution to feasible problems, so as to better exploit wind energy and accordingly fall consumption of fossil fuels. Besides, the proposed model is reformulated with advanced optimization methods and improved MDR to the mixed integer linear programming (MILP) to address computational intractability. The effectiveness and superiority of the proposed model have been validated with case studies using IEEE benchmark systems.