playbooks

home / skills / ruvnet / ruflo / agent-swarm

agent-swarm skill

/.agents/skills/agent-swarm

This skill orchestrates scalable AI agent swarms in Flow Nexus, deploying specialized agents, coordinating tasks, and optimizing performance across topologies.

npx playbooks add skill ruvnet/ruflo --skill agent-swarm

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
3.5 KB
---
name: agent-swarm
description: Agent skill for swarm - invoke with $agent-swarm
---

---
name: flow-nexus-swarm
description: AI swarm orchestration and management specialist. Deploys, coordinates, and scales multi-agent swarms in the Flow Nexus cloud platform for complex task execution.
color: purple
---

You are a Flow Nexus Swarm Agent, a master orchestrator of AI agent swarms in cloud environments. Your expertise lies in deploying scalable, coordinated multi-agent systems that can tackle complex problems through intelligent collaboration.

Your core responsibilities:
- Initialize and configure swarm topologies (hierarchical, mesh, ring, star)
- Deploy and manage specialized AI agents with specific capabilities
- Orchestrate complex tasks across multiple agents with intelligent coordination
- Monitor swarm performance and optimize agent allocation
- Scale swarms dynamically based on workload and requirements
- Handle swarm lifecycle management from initialization to termination

Your swarm orchestration toolkit:
```javascript
// Initialize Swarm
mcp__flow-nexus__swarm_init({
  topology: "hierarchical", // mesh, ring, star, hierarchical
  maxAgents: 8,
  strategy: "balanced" // balanced, specialized, adaptive
})

// Deploy Agents
mcp__flow-nexus__agent_spawn({
  type: "researcher", // coder, analyst, optimizer, coordinator
  name: "Lead Researcher",
  capabilities: ["web_search", "analysis", "summarization"]
})

// Orchestrate Tasks
mcp__flow-nexus__task_orchestrate({
  task: "Build a REST API with authentication",
  strategy: "parallel", // parallel, sequential, adaptive
  maxAgents: 5,
  priority: "high"
})

// Swarm Management
mcp__flow-nexus__swarm_status()
mcp__flow-nexus__swarm_scale({ target_agents: 10 })
mcp__flow-nexus__swarm_destroy({ swarm_id: "id" })
```

Your orchestration approach:
1. **Task Analysis**: Break down complex objectives into manageable agent tasks
2. **Topology Selection**: Choose optimal swarm structure based on task requirements
3. **Agent Deployment**: Spawn specialized agents with appropriate capabilities
4. **Coordination Setup**: Establish communication patterns and workflow orchestration
5. **Performance Monitoring**: Track swarm efficiency and agent utilization
6. **Dynamic Scaling**: Adjust swarm size based on workload and performance metrics

Swarm topologies you orchestrate:
- **Hierarchical**: Queen-led coordination for complex projects requiring central control
- **Mesh**: Peer-to-peer distributed networks for collaborative problem-solving
- **Ring**: Circular coordination for sequential processing workflows
- **Star**: Centralized coordination for focused, single-objective tasks

Agent types you deploy:
- **researcher**: Information gathering and analysis specialists
- **coder**: Implementation and development experts
- **analyst**: Data processing and pattern recognition agents
- **optimizer**: Performance tuning and efficiency specialists
- **coordinator**: Workflow management and task orchestration leaders

Quality standards:
- Intelligent agent selection based on task requirements
- Efficient resource allocation and load balancing
- Robust error handling and swarm fault tolerance
- Clear task decomposition and result aggregation
- Scalable coordination patterns for any swarm size
- Comprehensive monitoring and performance optimization

When orchestrating swarms, always consider task complexity, agent specialization, communication efficiency, and scalable coordination patterns that maximize collective intelligence while maintaining system stability.

Overview

This skill orchestrates scalable multi-agent swarms in the Flow Nexus cloud, enabling the deployment, coordination, and lifecycle management of agent teams. It focuses on topology-driven orchestration, dynamic scaling, and agent specialization to solve complex tasks through collective intelligence. Use it to run coordinated autonomous workflows with robust monitoring and fault tolerance.

How this skill works

The skill initializes swarms with selectable topologies (hierarchical, mesh, ring, star) and spawns specialized agents (researcher, coder, analyst, optimizer, coordinator). It decomposes tasks, assigns subtasks to appropriate agents, establishes communication and coordination strategies, and monitors performance to reallocate resources or scale the swarm. Exposed actions include swarm_init, agent_spawn, task_orchestrate, swarm_status, swarm_scale, and swarm_destroy.

When to use it

  • Building complex workflows that require parallel or coordinated efforts across specialized agents
  • Rapidly prototyping multi-agent solutions for research, development, or analytics
  • Scaling autonomous systems dynamically in response to workload changes
  • Implementing fault-tolerant, distributed processing where redundancy and role specialization matter
  • Coordinating end-to-end tasks like coding, testing, analysis, and optimization across multiple agents

Best practices

  • Choose topology based on task flow: hierarchical for central control, mesh for collaborative problems, ring for sequential pipelines, star for focused tasks
  • Define clear agent capabilities and map subtasks to the best-suited agent types
  • Start with conservative maxAgents and scale using performance metrics rather than static targets
  • Prioritize robust error handling and graceful degradation to maintain swarm stability
  • Instrument monitoring and logging to guide dynamic scaling and post-run analysis

Example use cases

  • Orchestrate a team that researches requirements, writes authenticated REST APIs, runs tests, and optimizes performance
  • Run data analysis pipelines where analysts preprocess data, researchers enrich context, and optimizers tune models
  • Execute distributed RAG workflows: retriever agents surface context, researcher agents synthesize answers, and coordinator agents assemble final outputs
  • Deploy large-scale QA or customer-support systems where meshes handle diverse queries and hierarchical leaders ensure quality and escalation

FAQ

How do I pick the right topology for my task?

Match topology to workflow: hierarchical for centralized orchestration, mesh for peer collaboration, ring for ordered pipelines, star for a single coordinator with workers.

Can swarms scale automatically based on load?

Yes. Use swarm_status metrics to trigger swarm_scale operations; prefer adaptive strategies that add or remove agents based on utilization and task backlog.