Imagine a team of AI agents working together to handle complex tasks. This skill helps you build a graph of connected agents. Each agent has its own job, and they pass information along edges. You can create a root agent that routes work to specialists. This is useful for customer support, data pipelines, or any workflow with multiple steps.
The skill uses the LaunchDarkly platform. You will design the graph first, then create it with tools. You need the remote MCP server set up. The process involves making sure each agent config exists, then adding edges between them. Each edge can carry handoff data to guide the next agent.
Managers and developers can use this to make AI workflows more organized. The graph is like a map that shows how agents talk to each other. You can test the routing to make sure everything works end to end.
Global
mkdir -p ~/.claude/skills/agent-graphsProject
mkdir -p .claude/skills/agent-graphsSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly