nw-design-patterns

Match agent types to design patterns using a decision-tree framework.

Updated Apr 15, 2026
One-click install
npx skills add https://github.com/StudentCristian/nWave-github --skill nw-design-patterns
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nw-design-patterns
Source: https://github.com/StudentCristian/nWave-github/tree/main/.github/skills/nw-design-patterns
Command: npx skills add https://github.com/StudentCristian/nWave-github --skill nw-design-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Maps each agent type to the most suitable agentic design pattern, reducing guesswork in architecting AI-driven workflows. It covers seven patterns: ReAct, Reflection, Router, Planning, Sequential Orchestration, Parallel Orchestration, and Hierarchical.

Core Features & Use Cases

  • Decision-tree based pattern selection for single-task vs multi-agent coordination.
  • Clear mappings to roles like specialists, reviewers, and orchestrators.
  • Real-world workflow examples and rationale to guide architecture decisions.

Quick Start

Provide your agent task scenario and desired outcome, and the system will suggest the best matching pattern.

Frequently Asked Questions about nw-design-patterns

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

FAQPage Schema
How do I choose the right multi-agent design pattern for my AI workflow?

To choose a multi-agent design pattern, match your agent types to a decision-tree framework that evaluates single-task coordination, routing, planning, and orchestration scenarios. This reduces guesswork by applying consistent selection criteria to determine the best architecture.

What is the difference between ReAct, Router, and Planning agent patterns?

ReAct, Router, and Planning are distinct agentic design patterns for different workflow needs. The decision-tree framework maps these patterns to specific roles like specialists and orchestrators, explaining the rationale and criteria for when to apply each architecture.

When do I need hierarchical orchestration instead of parallel orchestration?

You need hierarchical orchestration when multi-agent coordination requires structured top-down task delegation, whereas parallel orchestration handles independent concurrent execution. The decision-tree framework evaluates your workflow scenario to recommend the correct pattern.

Can I use this decision-tree framework for single-task agent scenarios?

Yes, the decision-tree framework supports single-task agent scenarios alongside multi-agent coordination. It maps your specific task scenario and desired outcome to the most suitable design pattern, providing clear mappings to roles like specialists and reviewers.

What is the best way to architect a multi-agent coordination workflow?

The best way to architect multi-agent coordination is applying a decision-tree framework that evaluates your workflow requirements against seven design patterns. This provides real-world examples and rationale to guide consistent architecture decisions across projects.