Skip to content
Back to skills

Architecture Review

ASecurity

Reviews an existing codebase for structural friction, unclear ownership, leaky or shallow interfaces, excessive coupling, misplaced state, poor testability, and risky dependency direction, then prioritizes evidence-backed improvement candidates. Use for architecture audits, modularization, modernization, or recurring cross-cutting change pain. Not for designing one new interface, simplifying a local function, or fixing a reproduced bug.

  • 95 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 22, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 22, 2026

npx -y skills add thiientv/godmode --skill architecture-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Architecture Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Architecture Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thiientv-architecture-review/badge)](https://www.skillsdirectory.com/skills/thiientv-architecture-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: architecture-review
description: >-
  Reviews an existing codebase for structural friction, unclear ownership,
  leaky or shallow interfaces, excessive coupling, misplaced state, poor
  testability, and risky dependency direction, then prioritizes evidence-backed
  improvement candidates. Use for architecture audits, modularization,
  modernization, or recurring cross-cutting change pain. Not for designing one
  new interface, simplifying a local function, or fixing a reproduced bug.
---

# Architecture Review

Find structural changes that reduce the cost and risk of likely future work.
Do not produce a generic best-practices checklist.

## Scope the review

Use `codebase-orientation` first when ownership and execution paths are not
known. Focus on the user-named subsystem or on evidence-backed hotspots from
history, incidents, change coupling, and test failures. Read relevant ADRs and
domain vocabulary before proposing alternatives.

## Inspect structural pressure

Look for:

- behavior spread across many callers instead of owned behind one interface;
- interfaces that expose nearly as much complexity as they hide;
- dependency cycles, unstable direction, duplicated policy, and hidden global
  state;
- abstractions with one hypothetical implementation or pass-through layers;
- tests that require internal knowledge because the public seam is wrong;
- concepts named inconsistently across code, data, and product language.

Apply the deletion test: if removing a module only moves its complexity into
every caller, it may be earning its place; if complexity disappears, it may be
ceremony. Use [candidate-report.md](references/candidate-report.md) to compare
current and proposed ownership.

## Prioritize, do not redesign silently

Rank candidates by observed friction, expected locality/leverage, migration
risk, reversibility, and relevance to upcoming work. Include a smallest useful
change and explicit non-goals. Mark speculative ideas as speculative.

Hand an approved candidate to `solution-design` and
`implementation-planning`; use `code-simplification` when no architectural
boundary changes.

## Completion condition

The report ties each candidate to repository evidence, shows current and
proposed ownership, respects existing decisions or explicitly challenges them,
and recommends a bounded first move without implementing an unapproved
redesign.

Files in this skill

  • SKILL.md2.3 KB
  • agents/openai.yaml224 B
  • references/candidate-report.md589 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…