This work proposes a network perspective in order to empirically identify the relevant ICT skills related to AI, to what extent they are systemically related, and how their composition varies across regions. With the example of 5,227 job openings from Germany advertised as postings in Artificial Intelligence, relevant skills are identified and connected in a network fashion. Two skills are connected, if they are jointly required by the same job advertisement. Similarly, regional skill networks can be constructed: Job postings are screened by city location and skill networks are constructed for this set of regional postings exclusively. The resulting networks depict the regional city ecosystem of AI skills currently in demand.