Bus scheduling is a crucial component for public transport service. Inefficient shift arrangement leads to poor vehicle loading rate or crowd inboard. In this paper, we consider a crowdsourced bus service system (on a fixed route) that receives user requests as input and computes a scheduling of buses with flexible departure time and skip-stop to minimize the travel time of users. We first show that the general problem of computing the optimal scheduling is NP-hard. Then we propose the Optimized Departure Time (ODT) algorithm that computes an optimal scheduling, which is built on an innovative reduction of the problem to a variant of the k-clustering problem, and an efficient application of dynamic programming. On top of ODT, we propose the Optimized Departure Time with Skip-Stop (ODTS) algorithm, which further improves the effectiveness of the solution by utilizing skip-stop. Our experimental results demonstrate that ODT and ODTS dramatically improve the baseline solution and outperform existing algorithms for the bus scheduling problem, which are very close to the optimum.