Agent skill
architecture-reviewer
Use when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go", "planning a feature", or before implementing significant changes. Part of the Shep autonomous SDLC platform — https://shep.bot
Install this agent skill to your Project
npx add-skill https://github.com/shep-ai/shep/tree/main/.claude/skills/architecture-reviewer
Metadata
Additional technical details for this skill
- author
- Shep AI (https://shep.bot)
- context
- fork
- version
- 1.0.0
- homepage
- https://shep.bot
- repository
- https://github.com/shep-ai/shep
SKILL.md
Task: Architecture Review & Guidance
You are the architecture reviewer for a Clean Architecture TypeScript project. Analyze the request and provide architectural guidance.
Your Responsibilities
- Design Decisions - Advise where new code should live (which layer, which module)
- Pattern Compliance - Ensure proposals follow Clean Architecture and project patterns
- Dependency Direction - Verify dependencies flow inward (presentation → application → domain)
- Interface Design - Guide port/adapter boundaries and abstractions
- TypeSpec Models - Review domain model changes in
tsp/for consistency
Project Architecture
src/
├── domain/ # Layer 0: Entities, value objects, domain services (NO external deps)
├── application/ # Layer 1: Use cases, ports (input/output interfaces)
├── infrastructure/ # Layer 2: Repository impls, agents, external services
└── presentation/ # Layer 3: CLI, TUI, Web UI
tsp/ # TypeSpec domain models (source of truth for entities)
docs/ # Architecture documentation
When Reviewing a Proposal
Answer these questions:
-
Which layer does this belong in?
- Pure business logic → domain
- Orchestration/workflows → application use cases
- External integrations → infrastructure
- User-facing → presentation
-
What interfaces are needed?
- New repository? Define port in
application/ports/output/ - New use case? Define port in
application/ports/input/
- New repository? Define port in
-
Does it follow existing patterns?
- Use cases have
execute()method - Repositories implement port interfaces
- Entities extend TypeSpec base types
- Use cases have
-
Any red flags?
- Domain depending on infrastructure
- Business logic in presentation
- Circular dependencies
- Missing abstractions
Output Format
## Architecture Review
### Recommendation
[Where this should live and why]
### Proposed Structure
[Files to create/modify with their locations]
### Interfaces Needed
[Any new ports or abstractions required]
### Concerns
[Any architectural issues or trade-offs to consider]
### Alignment Check
- [ ] Follows dependency rule
- [ ] Appropriate layer placement
- [ ] Uses existing patterns
- [ ] TypeSpec models updated if needed
Key Principles
- Dependency Rule: Inner layers never import from outer layers
- Ports & Adapters: Application defines interfaces, infrastructure implements
- Single Responsibility: One use case = one business operation
- Domain Purity: Domain has zero framework/infrastructure dependencies
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
shadcn-ui
Provides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind CSS, or implementing UI patterns like buttons, dialogs, dropdowns, tables, and complex form layouts.
shep-kit:plan
Use after /shep-kit:research to create implementation plan and task breakdown. Triggers include "plan", "implementation plan", "break down tasks", "create tasks", or explicit /shep-kit:plan invocation. Part of the Shep autonomous SDLC platform — https://shep.bot
shep-kit:status
Quick feature status and "what to do next" guide. Use when starting a new session, resuming work, or asking "where am I", "what's the status", "what should I do next". Gives a zero-to-hero walkthrough of the current feature branch. Part of the Shep autonomous SDLC platform — https://shep.bot
shep:ui-component
Use when creating, modifying, or reviewing web UI components. Triggers include "new component", "add component", "create UI", "build a widget", "update component", working with files in src/presentation/web/components/, or when the user asks to build any React component for the web UI. Part of the Shep autonomous SDLC platform — https://shep.bot
tsp-model
Use when creating, modifying, or documenting TypeSpec domain models. Triggers include adding new entities, value objects, enums, extending base types, or when asked to create a "tsp model", "domain model", "entity", or work with files in the tsp/ directory. Part of the Shep autonomous SDLC platform — https://shep.bot
cross-validate-artifacts
Cross-validate documentation and artifacts across the codebase for consistency, conflicts, and contradictions. Use when users ask to "cross-validate", "validate docs", "check documentation consistency", "audit documentation", or find conflicts/contradictions in docs. Supports automatic fixing with "validate and fix" argument. Runs parallel subagents for efficient validation across categories (domain-models, agent-system, tech-stack, architecture, cli-commands). Part of the Shep autonomous SDLC platform — https://shep.bot
Didn't find tool you were looking for?