architecture-review

Coordinate multi-member architecture reviews and generate a consolidated findings document.

74|11|Updated May 23, 2025
One-click install
npx skills add https://github.com/codenamev/ai-software-architect --skill architecture-review-codenamev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: architecture-review
Source: https://github.com/codenamev/ai-software-architect/tree/main/.claude/skills/architecture-review
Command: npx skills add https://github.com/codenamev/ai-software-architect --skill architecture-review-codenamev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Conducting thorough architecture reviews manually is time-consuming, often misses perspectives, and struggles with synthesizing diverse feedback. This Skill automates the entire process, ensuring all team members contribute to a comprehensive assessment.

Core Features & Use Cases

  • Multi-Perspective Analysis: Engages all architecture team members (e.g., Security, Performance, Domain Experts) to review from their unique viewpoints.
  • Automated Document Generation: Produces a detailed review document with executive summary, individual findings, collaborative discussion, and prioritized recommendations.
  • Pragmatic Mode Integration: Automatically includes a "Pragmatic Enforcer" to challenge over-engineering if enabled.
  • Use Case: Before a major release, you need a holistic view of your system's health. You initiate an "architecture review for version 2.0.0" to get a consolidated report on strengths, concerns, and actionable recommendations from your entire AI architect team.

Quick Start

Start architecture review for version 2.0.0

Frequently Asked Questions about architecture-review

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

FAQPage Schema
How do I conduct a comprehensive architecture review across multiple team members?

Architecture review automates multi-perspective assessment by engaging all team members (Security, Performance, Domain Experts) to review from their unique viewpoints, then synthesizes individual findings into a consolidated report with executive summary, collaborative discussion, and prioritized recommendations.

Can I review my system architecture for a specific version or feature?

Yes, architecture review applies to versioned targets, feature branches, or individual components. Trigger a review for a specific version (e.g., version 2.0.0) to get a holistic assessment of that release's health, strengths, and concerns.

What is pragmatic mode in architecture reviews and when should I enable it?

Pragmatic mode integrates a Pragmatic Enforcer to challenge over-engineering and flag unnecessary complexity. Enable it when you want realistic, implementation-focused recommendations balanced against ideal architecture.

Do I need to configure my architecture team before running a review?

Yes, architecture review loads team configuration from .architecture/members.yml. Define your review team members and their roles (e.g., Security Lead, Performance Expert) before initiating a review to ensure all perspectives are included.

How does architecture review analyze technical debt and system concerns?

Architecture review analyzes your codebase using Read, Glob, Grep, and Git history to identify technical debt, coordination gaps, and system concerns. It synthesizes findings from all team members into a final document with actionable recommendations.

What output do I get from a full architecture review?

A detailed review document containing an executive summary, individual member findings organized by perspective, collaborative discussion, and prioritized recommendations addressing strengths, concerns, and next steps for your system.