Multi-agent swarm coordination for complex tasks. Use when: 3+ files need changes, new features, refactoring. Skip when: single file edits, simple fixes, documentation.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add ruvnet/ruflo --skill swarm-orchestration --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Swarm Orchestration?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ruvnet-swarm-orchestration-35310ae8)More formats (shields.io, HTML) on the badges page.
---
name: swarm-orchestration
description: >
Multi-agent swarm coordination for complex tasks.
Use when: 3+ files need changes, new features, refactoring.
Skip when: single file edits, simple fixes, documentation.
---
# Swarm Orchestration Skill
## Purpose
Multi-agent swarm coordination for complex tasks.
## When to Trigger
- 3+ files need changes
- new features
- refactoring
## When to Skip
- single file edits
- simple fixes
- documentation
## Commands
### Initialize Swarm
Start a new swarm with hierarchical topology
```bash
npx @claude-flow/cli swarm init --topology hierarchical --max-agents 8
```
### Route Task
Route a task to the appropriate agents
```bash
npx @claude-flow/cli hooks route --task "[task description]"
```
### Monitor Status
Check the current swarm status
```bash
npx @claude-flow/cli swarm status
```
## Best Practices
1. Check memory for existing patterns before starting
2. Use hierarchical topology for coordination
3. Store successful patterns after completion
4. Document any new learnings
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...