architect-review

Critique architecture artifacts with rubric-based severity-tagged findings and a verdict.

15|5|Updated May 4, 2026
One-click install
npx skills add https://github.com/eugenelim/agent-ready-repo --skill architect-review-eugenelim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: architect-review
Source: https://github.com/eugenelim/agent-ready-repo/tree/main/packs/architect/.apm/skills/architect-review
Command: npx skills add https://github.com/eugenelim/agent-ready-repo --skill architect-review-eugenelim

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It helps you evaluate architecture artifacts before you commit to building them, so you can catch misleading claims, missing risks, and the wrong artifact shape early.

Core Features & Use Cases

  • Rubric-based critique: Reviews design docs, RFCs, ADRs, and diagrams against the right architecture rubric instead of giving vague opinions.
  • Severity-tagged findings: Returns blockers, majors, minors, and nits in a prioritized order, with concrete fixes the author can apply.
  • Grounding checks: Flags load-bearing claims that are not backed by a cited surface or an explicit unverified marker.
  • Well-architected lens mode: Assesses designs through pillar and workload-class lenses, including serverless and GenAI or agentic systems.
  • Use case: Use it when a teammate shares an architecture proposal and you need a crisp verdict, specific issues, and the strengths worth keeping.

Quick Start

Ask the skill to review the pasted architecture artifact and return a verdict with severity-tagged findings.

Frequently Asked Questions about architect-review

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

FAQPage Schema
How do I review an architecture design doc before committing to it?▼

To review an architecture design doc, apply a rubric-based critique that evaluates pasted RFCs, ADRs, and diagrams. This process returns prioritized, severity-tagged findings with concrete fixes and a clear verdict, helping catch missing risks early.

What is a grounding check in an architecture review?▼

A grounding check in an architecture review flags load-bearing claims that are not backed by a cited surface or an explicit unverified marker. This ensures critical assertions in your design docs and RFCs are properly substantiated before approval.

Can I use a well-architected review for serverless or GenAI systems?▼

Yes, you can assess serverless and GenAI or agentic systems through a well-architected lens mode. This evaluates designs through pillar and workload-class lenses to produce severity-tagged findings and a closing strengths section.

How do I prioritize architecture findings from a design critique?▼

To prioritize architecture findings from a design critique, order them by severity levels: blockers, majors, minors, and nits. This prioritized list includes concrete fixes the author can apply to resolve specific issues.

What is the best way to evaluate an architecture diagram for risks?▼

The best way to evaluate an architecture diagram is to run a rubric-based critique that checks for misleading claims and missing risks. This yields a crisp verdict, ordered severity findings, and highlights the strengths worth keeping.