orch-multi-agent
Domain: orch · Model class: strong
Description
Section titled “Description”Use this skill when the user wants to work on Designing the architecture and roles of multi-agent systems. Triggers include “design a multi-agent system”, “what roles should my agents have”, “set up specialist agents”. Do NOT use when implement the coordination logic (use core-agent-orchestrator).
Purpose
Section titled “Purpose”Designing the architecture and roles of multi-agent systems. This skill provides structured guidance, references, and worked examples to help produce high-quality, actionable outputs.
Trigger Phrases
Section titled “Trigger Phrases”- “design a multi-agent system”
- “what roles should my agents have”
- “set up specialist agents”
- “multi-agent architecture”
Anti-Triggers
Section titled “Anti-Triggers”- implement the coordination logic (use core-agent-orchestrator)
- synthesize agent outputs (use core-result-synthesis)
Intake Questions
Section titled “Intake Questions”- What is the user’s goal and current state?
- What constraints (time, team, compliance) apply?
- Are there existing artifacts (specs, code, benchmarks) to reference?
Output Contract
Section titled “Output Contract”- orchestration topology
- agent responsibility map
- control-loop or validation contract
- handoff guidance