review-multi-agent-orchestration
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.
Review Multi-Agent Orchestration
Overview
Review an orchestration as a distributed state machine, not as a list of agent roles. The goal is to prove that every task has one owner, every state transition has one authority, and every terminal outcome is reachable without duplicate effects, lost work, or unbounded loops.
This skill reviews a design or implementation. Do not launch workers, mutate queues, cancel runs, change production configuration, or deploy fixes unless the user separately requests implementation.
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.
Do not use it for a single independent tool call or a simple pipeline with no concurrency, shared state, retry, or delegation boundary.
Capture the Orchestration Contract
Request or derive:
- business goal, success criteria, and non-goals;
- task graph with stable task IDs and dependency edges;
- agent roles, capabilities, permissions, tools, and sandbox boundaries;
- state schema, source of truth, o
Subscribers only
The full skill, its 1 bundled files and every download is included with every paid Complete AI plan.
Details
| Source | self |
|---|---|
| License | — |
| Risk label | safe ("critical" means the skill may run commands or touch files — read before use) |
| Files | SKILL.md |
| Added | 2026-08-19 |
Related skills
accesslint-diff
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
accint-frames
Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").
accint-solve
Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.
ad-creative
Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization.