skills.rest
liminal-ai
liminal-aiOFFICIAL
Explore all skills by this author →
GitHub

architecture-review

Analyze code changes against project architecture and boundaries.

Updated Mar 16, 2026
Search Tags:#architecture#codebase#design-review#dependency-graph#module-boundaries#architectural-review#boundary-check
One-click install
npx skills add https://github.com/liminal-ai/code-steward --skill architecture-review-liminal-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: architecture-review
Source: https://github.com/liminal-ai/code-steward/tree/main/.claude/plugins/code-steward-reviews/skills/architecture-review
Command: npx skills add https://github.com/liminal-ai/code-steward --skill architecture-review-liminal-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Perform an architecture and design review — the "tech lead" pass that evaluates whether a change fits the existing codebase architecture. Use this skill when the user asks to "review architecture", "architecture review", "design review", "check coupling", "review code structure", "does this fit the codebase", "abstraction review", "module boundary check", "dependency review", "is this well-designed", "review module design", "check for tight coupling", "review layering", "does this belong here", "check dependencies", "review the design of this", or any request focused on whether code is in the right place, at the right abstraction level, with the right boundaries. Also trigger when the user asks about circular dependencies, leaky abstractions, separation of concerns, module organization, or API surface design — even if they don't use the word "architecture" explicitly.

Core Features & Use Cases

  • Phase 1 Context Research: Understand the existing architecture by reading project conventions, module structures, import patterns, and dependency graphs.
  • Phase 2 Comparative Analysis: Assess alignment with established patterns, module placement, and dependency direction to avoid architectural drift.
  • Phase 3 Issue Assessment: Produce an Architecture Scorecard across pattern conformance, abstraction quality, coupling, API clarity, and maintainability.
  • Use Case: Triggered when a user asks to review architecture, module boundaries, or systemic design concerns in a PR or design proposal.

Quick Start

Analyze a code change to determine if it fits the existing architecture and boundaries.

Frequently Asked Questions about architecture-review

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

FAQPage Schema
How do I review code structure and check if a new change fits the existing architecture?▼

An architectural review evaluates whether a code change aligns with the existing codebase architecture by analyzing pattern conformance, module boundaries, and dependency graphs. It produces an Architecture Scorecard with numeric ratings and structural findings to prevent architectural drift.

What is the best way to check for tight coupling and leaky abstractions in a pull request?▼

Checking for tight coupling and leaky abstractions involves a design review that assesses dependency direction, API surface design, and separation of concerns. The review identifies structural issues across the change's scope, focusing on whether code is at the right abstraction level and in the right module.

How do I perform a module boundary check to prevent circular dependencies?▼

A module boundary check analyzes import patterns and dependency graphs to verify that new code respects established module organization and dependency direction. This prevents circular dependencies by evaluating coupling and layering before runtime behavior is assessed.

When do I need an architectural review versus a standard code review?▼

An architectural review is needed when evaluating systemic design concerns like layering, API contracts, and module placement, rather than runtime behavior or syntax. It acts as a tech lead pass to determine if code belongs in the right place with the correct boundaries.

Can I assess abstraction quality and API clarity without running the code?▼

Yes, abstraction quality and API clarity can be assessed by analyzing the code structure and boundaries directly. The review produces a scorecard rating these dimensions, alongside pattern conformance and maintainability, without requiring code execution.

Related Skills

Explore More Software Engineering Skills→
santosomarsantosomar
1

module-level-code-translator

Translate entire software modules between programming languages using dependency graphs.

Community
Advanced
CANTAGESTUDIOCANTAGESTUDIO
3

refactor-arch-hotspots

Detect architectural hotspots by analyzing churn, coupling, and layer violations.

Community
Advanced
DayoptDayopt

cleanup

Detect and remove unused code, dead imports, and console statements in TypeScript/JavaScript projects.

Official
Advanced
benediktmsbenediktms

neocortex

Evaluate code changes for module boundaries, coupling, and abstraction fit.

Community
Advanced