Yeah, the BE architecture parallel is intentional - single responsibility, bounded contexts, loose coupling. These are solved problems, they just apply to a new domain now. Totally agree on structure vs prompting, a well-written prompt gets you pretty far, but the real difference comes from how you organize everything around it. Cheers!

Spot on with the context window budget per skill - that's sth I should've called out explicitly. It forces you to be disciplined abt what goes into each skill. If it doesn't fit in ~1k tkns, it's probably trying to cover too mych. The I/O contracts points is interesting too. I've found that the clearer tjhe trigger conditions and expected outputs are, tjhe less the orchestrator has to think. I'm interested in your fallback behavior, it goes to a more general skill or retries with a different context?