multi-agent-builder

Design multi-agent workflows with sequential steps and model selection.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/SimyV/agent-system --skill multi-agent-builder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-agent-builder
Source: https://github.com/SimyV/agent-system/tree/main/config/skills/multi-agent-builder
Command: npx skills add https://github.com/SimyV/agent-system --skill multi-agent-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Enables building structured, repeatable multi-agent pipelines by composing sequential steps, selecting appropriate models, and coordinating teams of agents.

Core Features & Use Cases

  • Design sequential pipeline workflows with clear step boundaries and output chaining.
  • Support for coordinated agent teams (lead/parallel mode); for true team coordination, use the team-delegation skill and delegate tool.
  • Works across Claude CLI (with full tool access) and OpenRouter models, enabling flexible tool usage, file access, web access, and script execution as needed.
  • Provides guidance on tool usage, model selection, and best practices for robust workflow design in complex automation scenarios.

Quick Start

Design a simple two-step workflow that processes an input document through sequential steps and stores intermediate results.

Frequently Asked Questions about multi-agent-builder

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

FAQPage Schema
How do I design multi-agent workflows for sequential data processing pipelines?

Multi-agent workflows orchestrate sequential steps with model selection and inter-agent communication, enabling repeatable pipelines for complex automation tasks across Claude CLI and OpenRouter models.

Can I use OpenRouter models and Claude CLI together for agent orchestration?

Yes, agent orchestration works across Claude CLI with full tool access and OpenRouter models, enabling flexible tool usage, file access, web access, and script execution within automated pipelines.

What's the best way to structure agent roles and inter-agent communication in an automation pipeline?

Structure agent roles by defining frontmatter options, allowed-tools, context, and optional resources like scripts and references, ensuring clear step boundaries and output chaining for repeatable workflows.

How do I set up a simple two-step workflow that processes an input document through sequential agents?

Set up a two-step workflow by designing sequential steps that process an input document through agents and store intermediate results, utilizing defined frontmatter and allowed-tools for each stage.

When should I use team delegation instead of building a standard sequential agent workflow?

Use team delegation for true team coordination instead of standard sequential workflows, utilizing the team-delegation skill and delegate tool to manage coordinated agent teams in lead or parallel modes.

What limitations should I consider when defining allowed-tools and context for multi-agent pipelines?

When defining allowed-tools and context, consider that limitations depend on the selected model's capabilities, as tool access, file handling, and script execution vary between Claude CLI and OpenRouter models.