agentleFS
ChianWChianW/C31/skills/review/C31-review-architecture/SKILL.md

C31-review-architecture

Skill1 starsChanged 3 months agoMITView on GitHub

Output language: Respond automatically in the user's conversation language. # C31-review-architecture For each issue: P[0-3] | <concern> | <one-line summary> | <file:line> Last line: ARCHITECTURE_SCORE: [0-10] — 10 = clean boundaries, 0 = systemic coupling introduced.

The file

Files
SKILL.md

Multilingual Triggers

LanguageTrigger phrases
ENC31-review-architecture
ZH架构审查, 架构设计
JAアーキテクチャレビュー, 設計レビュー

Output language: Respond automatically in the user's conversation language.

C31-review-architecture

Purpose

Architecture reviewer — coupling, layering violations, abstraction leaks, scalability ceiling, tech debt trajectory.

Severity Calibration

LevelMeaningFix Timeline
P0Critical — new circular dependency, monolith leak into service boundary, scalability blockedBlock merge
P1High — wrong layer for logic (business in DB, infra in domain), tight coupling introducedFix in PR
P2Medium — abstraction not pulling weight, premature generalization, interface bloatFix this sprint
P3Low — naming inconsistency, package structure could be cleanerBacklog

Review Checklist

  • Coupling — Does this create new import cycles? Service A now depends on Service B internals?
  • Layering — Domain logic leaking into controllers? Infra concerns in business rules?
  • Abstraction Leaks — ORM details escaping repository? HTTP status codes in domain?
  • Scalability — Stateful where stateless works? Shared mutable state? Horizontal scaling blocked?
  • Boundaries — Module/package boundaries respected? Domain events vs direct calls?
  • Tech Debt — Copy-paste pattern that should be abstracted? Previous hack now entrenched?
  • Extensibility — New feature requires touching how many files? Open/closed principle?
  • Dependencies — New library justified? Version conflict risk? License compatible?

Output Format

For each issue: P[0-3] | <concern> | <one-line summary> | <file:line>

Last line: ARCHITECTURE_SCORE: [0-10] — 10 = clean boundaries, 0 = systemic coupling introduced.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.