Agent skill
review:architecture
Architecture-focused review covering boundaries, performance, scalability, and API contracts. Spawns the senior-review-specialist agent for architectural analysis.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/review-architecture
SKILL.md
Architecture Code Review
Run an architecture-focused review using 4 architecture checklists via the senior-review-specialist agent.
Instructions
Spawn the senior-review-specialist agent to perform this review.
Checklists to Apply
Load and apply these review checklists:
commands/review/architecture.md- Boundaries, dependencies, layeringcommands/review/performance.md- Algorithmic efficiency, N+1 queries, bottleneckscommands/review/scalability.md- Load handling, dataset growth, multi-tenancycommands/review/api-contracts.md- Stability, correctness, consumer usability
Agent Instructions
The agent should:
- Get working tree changes: Run
git diffto see all changes - Map the architecture:
- Identify architectural layers (presentation, service, domain, infra)
- Identify dependency direction
- Identify coupling points
- For each changed file:
- Read the full file content
- Go through each diff hunk
- Apply all 4 architecture checklists
- Look for layer violations and circular dependencies
- Cross-reference related files: Check import graphs, module boundaries
- Assess coupling impact: How many modules are affected?
Output Format
Generate an architecture review report with:
- Critical Issues (BLOCKER): Circular dependencies, boundary violations
- High Priority Issues: God objects, coupling problems
- Medium Priority Issues: Missing abstractions, low cohesion
- Architectural Map: Layers, boundaries, dependency direction
- Coupling Metrics: Fan-in, fan-out, affected modules
- File Summary: Architecture issues per file
- Overall Assessment: Architecture health recommendation
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?