arch-review

Analyzes project architecture across layers, couplings, execution models, and contract evolution risks.

6|1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/wesleyosantos91/multi-agents --skill arch-review-wesleyosantos91
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: arch-review
Source: https://github.com/wesleyosantos91/multi-agents/tree/main/devin/.devin/skills/arch-review
Command: npx skills add https://github.com/wesleyosantos91/multi-agents --skill arch-review-wesleyosantos91

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps you evaluate whether a proposed or existing architecture is well-structured, resilient, and evolution-friendly before you invest further in implementation.

Core Features & Use Cases

  • Boundary and layering review: checks separation between web/ (synchronous edge), message/ (asynchronous edge), domain/, infrastructure/, and core/ to prevent leaks and coupling.
  • Coupling and cohesion assessment: identifies architectural smells that increase maintenance cost and reduce modularity.
  • Execution-model decision support: analyzes suitability of Lambda vs container vs batch vs Step Functions for the described workload and failure profile.
  • Contract evolution compatibility: evaluates how changes can be introduced to interfaces and contracts without breaking consumers.

Quick Start

Run the arch-review skill with the module name or architectural decision you want assessed and get a focused architectural critique.

Frequently Asked Questions about arch-review

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

FAQPage Schema
How do I review architecture boundaries and failure trade-offs in my codebase?

Architecture review evaluates layer separation, coupling, and failure tolerance to improve system design quality. It analyzes synchronous and asynchronous boundaries to prevent leaks and identify architectural smells that increase maintenance cost.

What is the best way to choose an execution model for my workload?

Execution-model decision support analyzes workload suitability and failure profiles across Lambda, containers, batch, and Step Functions. It evaluates your specific requirements to map the workload to the most appropriate execution model.

How do I assess layer separation and coupling in a module architecture?

Layer separation assessment checks boundaries between web, message, domain, infrastructure, and core layers to prevent coupling. Evaluating coupling and cohesion identifies architectural smells that reduce modularity and increase maintenance cost.

Can I evaluate API contract evolution compatibility for synchronous and asynchronous boundaries?

Contract evolution compatibility evaluates how changes can be introduced to interfaces and API contracts without breaking consumers. It applies to both synchronous and asynchronous boundaries within your project structure.

Does this architecture review support branch and module-focused assessments?

Yes, architectural analysis applies to codebase reviews and focused branch or module-level assessments. It evaluates resiliency, execution decisions, and failure tolerance across the targeted scope.

When should I not use a Lambda execution model for my architecture?

Lambda may be unsuitable when your workload failure profile demands long-running processes or complex state management. Architecture review maps workload characteristics against Lambda, containers, batch, and Step Functions to identify trade-offs.