architecture-review
Before committing to an implementation plan, run this skill to stress-test the proposed architecture. Catches over-engineering, circular dependencies, missing failure modes, security gaps, and scalability cliffs — before any code is written. Acts as a "second eye" on the plan.
npx skills add majiayu000/claude-skill-registry --skill architecture-review-omergocmen-vibe-coder-kit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
<!-- TÜRKÇE AÇIKLAMA ─────────────── Bu skill, bir implementasyon planı kod yazılmadan önce "ikinci göz" olarak stres testine tabi tutar. Aşırı mühendislik, döngüsel bağımlılıklar, eksik hata senaryoları, güvenlik açıkları ve ölçeklenebilirlik sorunlarını erken tespit eder. Yanlış temele inşa etmenin maliyeti çok yüksektir — bu skill o maliyeti sıfıra indirir. NE ZAMAN: Plan hazırlandıktan SONRA, kod yazmaya başlamadan ÖNCE. Zorunludur. ÇIKTI: 🔴 Blocker / 🟡 Warning / 🔵 Note listesi + Approved/Revisions Required kararı. --> # Architecture Review Skill ## When to Trigger - After `writing-plans` produces an implementation plan, *before* `executing-plans` - When a significant refactor is proposed - When adding a new external service or integration - When the team is debating between two approaches - When something "feels off" about a design but you can't articulate why ## Step-by-Step Process ### 1. Load the Plan Read the implementation plan (typically `implementation_plan.md` or the artifact from `writing-plans`). Extract: - Components being built - Data flow between components - External dependencies - Assumptions the plan makes ### 2. Run the Checklists Work through each checklis
- When to Trigger
- Step-by-Step Process
- 1. Load the Plan
- 2. Run the Checklists
- 3. Classify Findings
- 4. Produce the Review Report
- 5. Gate: Proceed or Revise?
- Rules
What does the architecture-review skill do?
Before committing to an implementation plan, run this skill to stress-test the proposed architecture. Catches over-engineering, circular dependencies, missing failure modes, security gaps, and scalability cliffs — before any code is written. Acts as a "second eye" on the plan.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill architecture-review-omergocmen-vibe-coder-kit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.