domains / families / agent-tooling / review-multi-agent-orchestration
review-multi-agent-orchestration
authentic
Use when a supervisor, swarm, graph, planner-worker system, or parallel agent workflow needs review for task boundaries, shared state, branch joins, retries, cancellation, context handoffs, budgets, deadlocks, or human escalation before implementation or production rollout.
When to use
- Reviewing supervisor/worker, planner/executor, debate, swarm, graph, or hierarchical Agent designs.
- Introducing parallel branches, subagents, MCP tools, durable execution, memory, checkpoints, or human-in-the-loop gates.
- Diagnosing duplicate work, stale context, deadlocks, livelocks, branch races, runaway retries, or ambiguous ownership.
- Deciding whether a complex task should be parallel, sequential, delegated, or kept in one agent.
When not to use
- A static review cannot prove runtime scheduling, provider isolation, or exactly-once external effects; validate those claims in a harness.
- Framework names do not establish durability or failure semantics. Inspect the configured runtime contract.
- Recommendations should match the system's actual risk and scale; do not add queues, consensus, or databases when a single writer and immutable artifacts are sufficient.
Skill page
Source