The true potential of the Internet of Things (IoT) will be realized only when devices are able to harness the collective capabilities of a wide range of peer-devices. In this paper, we propose a novel model where friends in a social network can share device capabilities with their peers in an access controlled manner. We develop a theoretical model of such a peer-to-peer network in which devices can search for remote capabilities, and elaborate on the trade-offs of different algorithms in terms of capability searching and execution. We study various types of social network models to understand the degree of sharing in such networks. Our results show that Barabási-Albert graphs that approximate most real world social networks have a high degree of sharing, validating the utility of our social network based model. We also propose an algorithm that takes any given network and augments it to increase the level of sharing by intelligently suggesting friendship recommendations among vertices. Finally, we describe the prototype implementation of an android mobile application that uses facebook APIs to allow smartphones share GPS and camera capabilities with other devices owned by friends.