Ranking users in social networks is a well-studied problem, typically solved by algorithms that leverage network structure to identify influential users and recommend people to follow. In the last decade, however, curation - users sharing and promoting content in a network - has become a central social activity, as platforms like Facebook, Twitter, Pinterest, and GitHub drive growth and engagement by connecting users through content and content to users. While existing algorithms reward users that are highly active with higher rankings, they fail to account for users' curatorial taste. This paper introduces CuRank, an algorithm for ranking users and content in social networks by explicitly modeling three characteristics of a good curator: discerning taste, high activity, and timeliness. We evaluate CuRank on datasets from two popular social networks - GitHub and Vine - and demonstrate its efficacy at ranking content and identifying good curators.