In this paper we address and discuss the approach of learning employee skills from data based on XML structured profiles and their representation as a Bayesian network. For extracting new information we use a dependency analysis approach. Many enterprise resource management systems (ERP) come along with integrated modules for Human Resource Management (HRM). One main task of HRM is to manage, improve and deploy the right skills at the right time. These processes are well known as skill management. Furthermore the problem of finding hidden or implicit dependencies between employee skills is considered. Using an information theoretical approach to construct a powerful skill representation as graphical model is recommendable. To demonstrate the achievement of the learned network structure, a test scenario is given, where historical reference project data is used.