home / skills / microck / ordinary-claude-skills / swarm-orchestration

swarm-orchestration skill

/skills_all/swarm-orchestration

This skill orchestrates multi-agent swarms with adaptive topology, load balancing, and fault tolerance to scale complex workflows.

This is most likely a fork of the swarm-orchestration skill from chrislemke
npx playbooks add skill microck/ordinary-claude-skills --skill swarm-orchestration

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

Files (2)
SKILL.md
4.2 KB
---
name: "Swarm Orchestration"
description: "Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems."
---

# Swarm Orchestration

## What This Skill Does

Orchestrates multi-agent swarms using agentic-flow's advanced coordination system. Supports mesh, hierarchical, and adaptive topologies with automatic task distribution, load balancing, and fault tolerance.

## Prerequisites

- agentic-flow v1.5.11+
- Node.js 18+
- Understanding of distributed systems (helpful)

## Quick Start

```bash
# Initialize swarm
npx agentic-flow hooks swarm-init --topology mesh --max-agents 5

# Spawn agents
npx agentic-flow hooks agent-spawn --type coder
npx agentic-flow hooks agent-spawn --type tester
npx agentic-flow hooks agent-spawn --type reviewer

# Orchestrate task
npx agentic-flow hooks task-orchestrate \
  --task "Build REST API with tests" \
  --mode parallel
```

## Topology Patterns

### 1. Mesh (Peer-to-Peer)
```typescript
// Equal peers, distributed decision-making
await swarm.init({
  topology: 'mesh',
  agents: ['coder', 'tester', 'reviewer'],
  communication: 'broadcast'
});
```

### 2. Hierarchical (Queen-Worker)
```typescript
// Centralized coordination, specialized workers
await swarm.init({
  topology: 'hierarchical',
  queen: 'architect',
  workers: ['backend-dev', 'frontend-dev', 'db-designer']
});
```

### 3. Adaptive (Dynamic)
```typescript
// Automatically switches topology based on task
await swarm.init({
  topology: 'adaptive',
  optimization: 'task-complexity'
});
```

## Task Orchestration

### Parallel Execution
```typescript
// Execute tasks concurrently
const results = await swarm.execute({
  tasks: [
    { agent: 'coder', task: 'Implement API endpoints' },
    { agent: 'frontend', task: 'Build UI components' },
    { agent: 'tester', task: 'Write test suite' }
  ],
  mode: 'parallel',
  timeout: 300000 // 5 minutes
});
```

### Pipeline Execution
```typescript
// Sequential pipeline with dependencies
await swarm.pipeline([
  { stage: 'design', agent: 'architect' },
  { stage: 'implement', agent: 'coder', after: 'design' },
  { stage: 'test', agent: 'tester', after: 'implement' },
  { stage: 'review', agent: 'reviewer', after: 'test' }
]);
```

### Adaptive Execution
```typescript
// Let swarm decide execution strategy
await swarm.autoOrchestrate({
  goal: 'Build production-ready API',
  constraints: {
    maxTime: 3600,
    maxAgents: 8,
    quality: 'high'
  }
});
```

## Memory Coordination

```typescript
// Share state across swarm
await swarm.memory.store('api-schema', {
  endpoints: [...],
  models: [...]
});

// Agents read shared memory
const schema = await swarm.memory.retrieve('api-schema');
```

## Advanced Features

### Load Balancing
```typescript
// Automatic work distribution
await swarm.enableLoadBalancing({
  strategy: 'dynamic',
  metrics: ['cpu', 'memory', 'task-queue']
});
```

### Fault Tolerance
```typescript
// Handle agent failures
await swarm.setResiliency({
  retry: { maxAttempts: 3, backoff: 'exponential' },
  fallback: 'reassign-task'
});
```

### Performance Monitoring
```typescript
// Track swarm metrics
const metrics = await swarm.getMetrics();
// { throughput, latency, success_rate, agent_utilization }
```

## Integration with Hooks

```bash
# Pre-task coordination
npx agentic-flow hooks pre-task --description "Build API"

# Post-task synchronization
npx agentic-flow hooks post-task --task-id "task-123"

# Session restore
npx agentic-flow hooks session-restore --session-id "swarm-001"
```

## Best Practices

1. **Start small**: Begin with 2-3 agents, scale up
2. **Use memory**: Share context through swarm memory
3. **Monitor metrics**: Track performance and bottlenecks
4. **Enable hooks**: Automatic coordination and sync
5. **Set timeouts**: Prevent hung tasks

## Troubleshooting

### Issue: Agents not coordinating
**Solution**: Verify memory access and enable hooks

### Issue: Poor performance
**Solution**: Check topology (use adaptive) and enable load balancing

## Learn More

- Swarm Guide: docs/swarm/orchestration.md
- Topology Patterns: docs/swarm/topologies.md
- Hooks Integration: docs/hooks/coordination.md

Overview

This skill orchestrates multi-agent swarms using agentic-flow to run parallel and coordinated workflows across many agents. It supports mesh, hierarchical, and adaptive topologies with built-in task distribution, load balancing, and fault tolerance. Use it to scale beyond single-agent workflows and manage distributed AI systems reliably.

How this skill works

The skill initializes a swarm topology, spawns typed agents, and assigns tasks either in parallel, pipeline, or adaptive modes. It manages shared state through a swarm memory, monitors metrics, and automatically reassigns work on failures. Hooks allow pre/post-task coordination and session restore for continuity.

When to use it

  • Scaling a project beyond a single agent to parallelize work
  • Implementing complex workflows with dependencies and pipelines
  • Building distributed AI systems that require coordination and shared state
  • Needing automatic load balancing and fault-tolerant task delivery
  • Experimenting with dynamic topologies that adapt to task complexity

Best practices

  • Start small (2–3 agents) and scale incrementally
  • Use swarm memory to share context and avoid duplicated work
  • Enable monitoring and hooks for automatic coordination and recovery
  • Set timeouts and retry/backoff policies to prevent hung tasks
  • Choose topology based on task: mesh for peer-driven, hierarchical for centralized control, adaptive for mixed workloads

Example use cases

  • Parallel feature development: assign coder, frontend, and tester agents to concurrent tasks
  • End-to-end pipeline: design → implement → test → review as sequential stages
  • Adaptive orchestration: let the swarm auto-decide agent allocation for a tight deadline
  • Resilient batch processing: automatic reassign on agent failure with retry/backoff
  • Performance tuning: enable load balancing to optimize throughput and agent utilization

FAQ

What prerequisites are required?

agentic-flow v1.5.11+, Node.js 18+, and familiarity with distributed systems are recommended.

How does the swarm handle agent failures?

Configure resiliency with retry limits, exponential backoff, and fallback policies to reassign tasks automatically.