Compose

This is the brake pedal for multi-agent systems. It forces you to answer whether you actually need multiple agents before spinning up a complex topology, which is refreshing given how easy it is to over-engineer these systems. The skill walks you through pre-composition checks (has single agent failed? what specific limitation exists?), then guides topology design, handoff protocols, and supervisor patterns. It references a separate agent-workflow skill for principles and architecture patterns. The checklist at the end is practical: non-overlapping roles, defined handoffs, failure handling. Best used when you've already tried a single agent and hit a wall you can name, not as your first move.