Multi agent
Skill pluginagentmarketplace/custom-plugin-ai-agents/skills/multi-agent
Build multi-agent systems - orchestration, coordination, workflows, and distributed architecturesFrom its SKILL.md
npx -y skills add pluginagentmarketplace/custom-plugin-ai-agents --skill multi-agentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.7 KB, as published. Nobody here has run it
Multi-Agent Systems
Build coordinated multi-agent systems for complex tasks.
When to Use This Skill
Invoke this skill when:
- Tasks require multiple specialized agents
- Building orchestrator-worker patterns
- Implementing agent workflows
- Coordinating parallel execution
Parameter Schema
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
task | string | Yes | Multi-agent goal | - |
architecture | enum | No | orchestrator-worker, hierarchical, peer-to-peer | orchestrator-worker |
framework | enum | No | langgraph, autogen, crewai | langgraph |
Quick Start
from langgraph.graph import StateGraph, MessagesState
from langgraph.prebuilt import create_react_agent
# Create specialized agents
researcher = create_react_agent(llm, [web_search])
coder = create_react_agent(llm, [execute_code])
# Build graph
graph = StateGraph(MessagesState)
graph.add_node("researcher", researcher)
graph.add_node("coder", coder)
graph.add_conditional_edges("coordinator", router)
Architecture Patterns
Orchestrator-Worker
Orchestrator (Opus)
├── Researcher (Sonnet)
├── Analyst (Sonnet)
└── Writer (Haiku)
Hierarchical
Manager (Opus)
├── Research Lead (Sonnet)
│ ├── Web Researcher (Haiku)
│ └── Doc Analyst (Haiku)
└── Engineering Lead (Sonnet)
├── Frontend Dev (Haiku)
└── Backend Dev (Haiku)
Model Allocation
| Agent Type | Model | Rationale |
|---|---|---|
| Orchestrator | Opus | Complex planning |
| Specialist | Sonnet | Reasoning |
| Worker | Haiku | Simple tasks |
Troubleshooting
| Issue | Solution |
|---|---|
| Agents not coordinating | Check message bus |
| Deadlock | Add timeout, detect cycles |
| Inconsistent results | Synchronize state |
| High costs | Use cheaper models for workers |
Best Practices
- One job per agent (single responsibility)
- Orchestrator handles planning only
- Use checkpointing for long workflows
- Implement circuit breakers per agent
Related Skills
ai-agent-basics- Single agentsagent-memory- Shared statetool-calling- Per-agent tools