agent-swarm

Orchestrate parallel analysis agents with a central coordinator merging results.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/leonardofhy/openclaw-workspace --skill agent-swarm-leonardofhy
Or copy as Structured Prompt for Agentβ–Ό
Please help me install this Agent Skill.
Skill: agent-swarm
Source: https://github.com/leonardofhy/openclaw-workspace/tree/main/skills/agent-swarm
Command: npx skills add https://github.com/leonardofhy/openclaw-workspace --skill agent-swarm-leonardofhy

SYSTEM DOCUMENTATION & REQUIREMENTS

πŸ’‘ This Skill includes scripts (resource) components.

What problem does it solve?

Agent Swarm enables a Coordinator to orchestrate several parallel analysis agents, merging their results into a unified outcome for complex tasks that benefit from multiple perspectives.

Core Features & Use Cases

  • Centralized coordination of multiple workers (agents) with a single Coordinator
  • Deterministic prompts and configurable presets for common workflows
  • Supports parallel execution and result aggregation for complex analyses (e.g., code review, research surveys, debater-style analysis)

Quick Start

Run the swarm script to generate a config for your chosen preset, then spawn worker agents and await results.

Frequently Asked Questions about agent-swarm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple AI agents in parallel for complex analysis tasks?β–Ό

Parallel execution of multiple AI agents is orchestrated by a central Coordinator that spawns workers concurrently and merges their results. This approach accelerates complex tasks requiring diverse angles, such as code review or research surveys.

What is a multi-agent coordinator and when do I need one for workflow automation?β–Ό

A multi-agent coordinator is a mechanism that manages parallel workers and fuses their outputs. You need one for workflow automation when complex tasks require diverse angles, such as debater-style analysis or multi-criteria research surveys.

How do I configure deterministic prompt templates for parallel agent execution?β–Ό

Deterministic prompt templates are configured using built-in presets for common workflows. You run the swarm script to generate a configuration for your chosen preset before spawning worker agents and awaiting their fused results.

Does multi-agent orchestration support result persistence and logging?β–Ό

Yes, multi-agent orchestration supports result persistence via memory logs. The Coordinator fuses parallel analysis outcomes and saves them, ensuring merged results from the workflow are retained for future reference.

What are the limitations of using parallel agent swarms for code review?β–Ό

Parallel agent swarms are limited to tasks decomposable into independent sub-tasks. They are not suited for sequential or highly interdependent code review workflows where later analysis steps strictly depend on earlier ones.