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.

skills.sh installs: 343
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill compose --agent claude-code

Installs into .claude/skills of the current project.

Files

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the agent-architecture reference in the agent-workflow skill for topology patterns and when multi-agent is justified.

Design a multi-agent system. But first — are you sure you need one?

Step 1: Pre-Composition Check

Answer these before proceeding:

Has a single agent been tried and failed? (If no, try single agent first)
What specific limitation requires multiple agents? (If you can't name it, you don't need multi-agent)
Is the cost/latency increase justified? (Multi-agent = 2-10x cost and latency)

If you can't articulate a specific limitation, use /amplify on the single agent instead.