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.
In this repository56 other files it gives its agents.
- C31-1stSkill
- C31-adopt-projectSkill
- C31-brainstormSkill
- C31-coding-disciplineSkill
- C31-compound-refreshSkill
- C31-compoundSkill
- C31-context-engineeringSkill
- C31-curatorSkill
- c31-daily-intelSkill
- C31-debugSkill
- c31-devSkill
- C31-grillSkill
- C31-lfgSkill
- C31-planSkill
- C31-researchSkill
- C31-specSkill
- C31-stormSkill
- C31-strategySkill
- C31-workflow-bug-reproductionSkill
- C31-workSkill
- rl-workflowSkill
- C31-cvideoSkill
- c31-loopSkill
- c31-sxsSkill
- teachSkill
- video-content-analysisSkill
- agent-reachSkill
- kimiimSkill
- skillhub-preferenceSkill
- c31-communitySkill
- c31-growSkill
- c31-gutcheckSkill
- c31-marketSkill
- c31-mvpSkill
- c31-priceSkill
- c31-processSkill
- c31-sellSkill
- c31-validateSkill
- c31-valuesSkill
- growth-hackerSkill
- c31-improve-codebase-architectureSkill
- C31-multi-reviewSkill
- C31-review-adversarialSkill
- C31-review-securitySkill
- C31-reviewSkill
- c31-wizardSkill
- external-privacy-guardSkill
- find-skillsSkill
- gsd-map-codebaseSkill
- gsd-new-projectSkill
- gsd-progressSkill
- gsd-quickSkill
- gsd-shipSkill
- humanize-aiSkill
- time-awarenessSkill
- worker-safetySkill
The file
Files
Multilingual Triggers
| Language | Trigger phrases |
| EN | C31-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
| Level | Meaning | Fix Timeline |
| P0 | Critical — new circular dependency, monolith leak into service boundary, scalability blocked | Block merge |
| P1 | High — wrong layer for logic (business in DB, infra in domain), tight coupling introduced | Fix in PR |
| P2 | Medium — abstraction not pulling weight, premature generalization, interface bloat | Fix this sprint |
| P3 | Low — naming inconsistency, package structure could be cleaner | Backlog |
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.
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
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.

