subagent-coordination

Define agent roles, delegate tasks, and orchestrate multi-agent workflows.

2|Updated Oct 24, 2025
One-click install
npx skills add https://github.com/pwarnock/liaison-toolkit --skill subagent-coordination-pwarnock
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-coordination
Source: https://github.com/pwarnock/liaison-toolkit/tree/main/.skills/subagent-coordination
Command: npx skills add https://github.com/pwarnock/liaison-toolkit --skill subagent-coordination-pwarnock

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables organizations to coordinate multiple specialized AI agents, assign tasks, manage roles, and orchestrate workflows across agents, reducing handoff friction and boosting overall throughput.

Core Features & Use Cases

  • Agent role definitions and clear boundaries to prevent overlap.
  • Delegation patterns for sequential and parallel task execution.
  • Handoff templates and capability discovery to route work to the best-suited agent.
  • Workflow graph orchestration to manage dependencies and escalation.

Quick Start

To start coordinating agents, define agent roles, register agents in your system, and create a multi-agent workflow. Example steps:

  1. Define roles (cody-admin, cody-planner, qa-subagent, etc.).
  2. Register agents with their capabilities.
  3. Create a workflow that sequences tasks across agents and enables handoffs.
  • Then trigger the workflow using your CLI: liaison task create "Prepare release" --auto-trigger multi-agent-release.

Frequently Asked Questions about subagent-coordination

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multiple AI agents to orchestrate work?

Multi-agent coordination orchestrates work by defining specialized agent roles, routing tasks via a capability-driven graph, and managing handoffs to reduce friction and boost throughput across development, QA, and operations teams.

What is the best way to manage task handoffs and escalations across AI agents?

Managing task handoffs and escalations requires workflow graph orchestration and standardized handoff templates to route work to the best-suited agent and handle dependencies or escalations across sequential and parallel execution.

How do I set up parallel and sequential delegation for specialized AI agents?

To set up parallel and sequential delegation, define clear agent roles to prevent overlap, register agents with their capabilities, and create a workflow graph that sequences tasks and enables structured handoffs.

Do I need to define agent roles before starting multi-agent workflow orchestration?

Yes, you must define agent roles and register their capabilities before triggering workflows, because the capability-driven routing graph relies on these boundaries to route work to the best-suited agent and prevent overlap.

When should I use a multi-agent coordination framework instead of a single agent?

Use a multi-agent coordination framework when your scenarios involve complex task assignment, sequential or parallel delegation, and handoffs across specialized boundaries like development, QA, and operations that a single agent cannot manage.