architect-first

Plan and validate architecture before writing implementation code.

Updated May 28, 2026
One-click install
npx skills add https://github.com/GustaPaes/aiox-sprint-canvas --skill architect-first-gustapaes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: architect-first
Source: https://github.com/GustaPaes/aiox-sprint-canvas/tree/main/.claude/skills/architect-first
Command: npx skills add https://github.com/GustaPaes/aiox-sprint-canvas --skill architect-first-gustapaes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

It prevents teams from starting implementation before the architecture is clear, reducing rework, capability loss, and tight coupling by forcing design, documentation, and validation up front.

Core Features & Use Cases

  • Architecture before code: Defines architecture and documentation as a non-negotiable prerequisite, especially for structural decisions and refactors.
  • Multi-agent validation: Requires validation from multiple perspectives (e.g., Product Owner, Architect, and final user/stakeholder) with explicit rationale.
  • Quality gates and safety checks: Enforces capability preservation, zero coupling, and a test-backed “escape hatch” for pragmatism when quality can be verified.

Quick Start

Use the architect-first skill when you need to make or refactor a structural system decision by first mapping the current state, presenting A/B/C options, validating them with stakeholders, documenting the chosen architecture, and only then implementing with tests.

Frequently Asked Questions about architect-first

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

FAQPage Schema
How do I enforce architecture documentation before writing implementation code?

To enforce architecture before code, you map the current state, present A/B/C options, validate them with stakeholders, document the chosen architecture, and only then implement with tests. This process ensures structural decisions are validated before development begins.

What is zero coupling module design and how does validation work?

Zero coupling module design ensures modules operate independently without hidden dependencies. Validation requires multiple perspectives, such as Product Owner, Architect, and stakeholders, to confirm the direction and preserve existing capabilities during structural refactors.

When do I need an architecture decision record for system refactoring?

You need an architecture decision record when making structural decisions or refactors that impact system design. It captures the chosen architecture, rationale from multi-agent validation, and ensures capability preservation before implementation begins.

Can I use YAML configuration externalization for test-backed execution?

Yes, YAML-based configuration externalization supports test-backed execution by externalizing settings. This allows quality gates and safety checks to verify capability preservation while providing a test-backed escape hatch for pragmatism when quality is confirmed.

What is the best way to prevent capability loss during structural system refactors?

The best way to prevent capability loss is enforcing quality gates and multi-agent validation before implementation. By mapping current state, presenting options, and requiring complete documentation with explicit stop rules, capabilities are preserved during refactoring.

What are the limitations of architecture-first development for new features?

Architecture-first development requires upfront time investment in documentation and multi-agent validation before coding begins. It may slow rapid prototyping, but includes a test-backed escape hatch for pragmatism when quality can be verified through tests.