Teach Maestro

This is your project onboarding interview for AI workflows. It walks you through five sections (models, architecture, evaluation, constraints, priorities) and generates a `.maestro.md` context file that other Maestro commands depend on. Think of it as the setup wizard that asks about your stack, budget, latency needs, and what you actually care about optimizing for. Run it once per project before anything else. The structured approach is solid, though you'll need to be specific in your answers or the downstream commands won't have much to work with. It won't let you skip sections or overwrite existing context without confirmation, which is the right call.