Social networks are commonly used to enhance recommender systems. Most of such systems recommend a single resource or a person. However, complex problems or projects usually require a team of experts that must work together on a solution. Team recommendation is much more challenging, mostly because of the complex interpersonal relations between members. This chapter presents fundamental concepts on how to score a team based on members´ social context and their suitability for a particular project. We represent the social context of an individual as a three-dimensional social network (3DSN) composed of a knowledge dimension expressing skills, a trust dimension and an acquaintance dimension. Dimensions of a 3DSN are used to mathematically formalize the criteria for prediction of the team´s performance. We use these criteria to formulate the team recommendation problem as a multi-criteria optimization problem. We demonstrate our approach on empirical data crawled from two web2.0 sites: <a href=http://onephoto.net>onephoto.net</a> and a social networking site. We construct 3DSNs and analyze properties of team´s performance criteria.