The Raleigh Agent Skill Cuts Through the City Website Maze

The Raleigh Agent Skill, a new AI tool from developer Magnus919, helps users navigate Raleigh's city website maze by providing direct answers to questions about public information, such as nearby bus stops. The skill maps scattered city data and includes a command-line tool for verification, eliminating the need for scavenger hunts through multiple web pages.

You’re standing near Fayetteville and Hargett streets downtown, and you need a bus. The useful answer isn’t a lesson about how transit information gets published. It’s this: the closest stops in this lookup were on East Hargett at Fayetteville, Wilmington at Morgan, and East Morgan at South Wilmington. You shouldn’t need a scavenger hunt through city websites to get an answer like that. The Raleigh Agent Skill https://github.com/magnus919/agent-skills/tree/main/raleigh gives an AI a map of Raleigh’s scattered public information: where to look, how to connect one lookup to the next, and when to admit that the record doesn’t say. A small command-line tool does the fetching underneath. You don’t have to care about that part, but the visible commands let you check the answer instead of taking the AI’s word for it.