Agent skill
drift-detect
Detect architectural drift and pattern violations
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/drift-detect
SKILL.md
Architecture Drift Detection
Detect when code deviates from established patterns and conventions.
What To Do
- Check layer violations: Controllers calling repositories directly
- Check naming conventions: Missing I prefix on interfaces, wrong suffixes
- Check dependency direction: Domain depending on infrastructure
- Check pattern consistency: Some entities use DTOs, others do not
- Generate drift report with specific file:line references
Rules Checked
- Controller -> Service -> Repository (no shortcuts)
- DTOs have static ToDomain()/FromDomain()
- All public service methods are async
- Repository returns domain models (not DTOs)
- No business logic in controllers
Arguments
--strict: Fail on any violation (default: warn only)
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?