j5ik2o/ai-tools/j5ik2o-clean-architecture
Claude Code and agent skill by j5ik2o/ai-tools
- community
Checking that the SKILL.md file is still in the repository.
Use only when the user explicitly asks for Clean Architecture design, implementation, or review. Applies a domain, use case, interface adapter, and infrastructure layer model, with persistence and RPC adapters outside the domain and use-case rules. Do not trigger for generic architecture advice, hexagonal architecture, onion architecture, or ordinary design review unless Clean Architecture is named.
Install
npx vskill@latest install j5ik2o/ai-tools/j5ik2o-clean-architectureSKILL.md
Clean Architecture
Use this skill only for projects that intentionally follow Clean Architecture. Keep policy inward and mechanisms outward.
Layer Rule
- Domain: entities, value objects, aggregates, domain services, domain events, and invariants.
- Use cases: application-specific orchestration, transaction boundaries, ports, authorization decisions that are application policy, and repository interface usage.
- Interface adapters: controllers, presenters, gateways, repository implementations, RPC adapters, DTO mapping, and persistence mapping.
- Infrastructure: cross-cutting mechanisms such as logging, configuration, metrics, DI wiring, clocks, IDs, and concrete driver setup.
Workflow
- Confirm the project actually uses Clean Architecture.
- Map the touched code to the four layers.
- Check dependency direction: outer layers may depend inward; inward layers must not know outer mechanisms.
- Move persistence, RPC, UI, and framework details out of domain and use-case code.
- Report the minimal relocation or interface extraction needed.
Reference
Read references/layer-responsibilities.md when placement is ambiguous.
Detailed Reference
For non-trivial implementation, review, or refactoring work, read references/details.md before giving final guidance. It contains the detailed rules, examples, smells, and migration notes that do not belong in the short invocation body.
Output
Provide a layer-by-layer finding list, dependency violations, and concrete file-placement recommendations.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/software-design/skills/j5ik2o-clean-architecture/SKILL.md
Popularity
- Repository stars
- 28
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/j5ik2o/ai-tools/j5ik2o-clean-architecture)