bmad-create-architecture

Generate a complete architecture document from PRDs and project requirements.

1|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/mol4/BMAD-Board --skill bmad-create-architecture-mol4
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-create-architecture
Source: https://github.com/mol4/BMAD-Board/tree/main/BMAD%20board/.agents/skills/bmad-create-architecture
Command: npx skills add https://github.com/mol4/BMAD-Board --skill bmad-create-architecture-mol4

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns project requirements into a complete architecture document, reducing ambiguity and preventing inconsistent implementation across AI-assisted development.

Core Features & Use Cases

  • Context Analysis: Reviews PRDs, UX specs, epics, and project documents to understand scope, constraints, and cross-cutting concerns.
  • Architecture Decisions: Guides collaborative choices for data, security, APIs, frontend, infrastructure, and starter templates using current technology versions.
  • Consistency & Structure: Defines implementation patterns, naming rules, directory boundaries, and validation checks so multiple AI agents can work together reliably.
  • Use Case: Use this Skill when starting a new BMAD project or when you need a single source of truth for technical decisions before implementation begins.

Quick Start

Ask the assistant to create the architecture for your project using the available PRD and supporting documents.

Frequently Asked Questions about bmad-create-architecture

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

FAQPage Schema
How do I create an architecture document for AI-assisted development?

To create an architecture document for AI-assisted development, provide your project requirements and supporting context like PRDs and UX specs to generate a single source of truth for technical decisions.

What is the best way to structure a project for multiple AI agents?

The best way to structure a project for multiple AI agents is to define implementation patterns, naming rules, and directory boundaries that ensure consistent collaboration and reliable execution across the codebase.

How do I make technical decisions for a new software project before implementation?

Make technical decisions for a new software project by collaboratively evaluating starter templates and selecting current technology versions for data, security, APIs, frontend, and infrastructure based on analyzed requirements.

Can I use existing PRDs and epics to generate my project architecture?

Yes, you can use existing PRDs and epics to generate your project architecture by analyzing the scope, constraints, and cross-cutting concerns defined in those project documents.

When do I need to validate architecture readiness for implementation?

You need to validate architecture readiness for implementation when starting a new BMAD project to ensure boundary definitions and end-to-end handoff preparation are complete before coding begins.

Why does inconsistent implementation happen with AI agents and how to prevent it?

Inconsistent implementation happens with AI agents due to ambiguous requirements; prevent it by building a complete architecture document that establishes consistency patterns, naming rules, and validation checks.