Loading...
Loading...
Found 46 Skills
Audit code architecture for over-engineering and unnecessary abstractions. Use when user asks to "review architecture", "simplify code structure", "reduce over-engineering", "evaluate abstractions", or mentions premature abstraction, interface proliferation, factory patterns, YAGNI, or enterprise-grade complexity.
Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with extended thinking support.
Analyzes code architecture and structure — layer violations, circular dependencies, god objects, anemic domain models, missing boundaries, directory structure issues, and configuration problems. Generates severity-scored findings with fix prompts. Trigger phrases: "architecture review", "structure check", "layer analysis", "god class".
Systematically find blind spots in code, architecture, APIs, and deployment — structured critique that catches what familiarity hides
Review code for architecture: module and layer boundaries, dependency direction, single responsibility, cyclic dependencies, interface stability, and coupling. Cognitive-only atomic skill; output is a findings list.
Use when designing module boundaries, planning refactors, or reviewing architecture in Python codebases. Also use when facing tangled dependencies, god classes, deep inheritance hierarchies, unclear ownership, or risky structural changes.
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.
Multi-perspective code review strategy covering architecture, security, performance, and quality. Follow when reviewing code or analyzing changes.
Use this skill when > Design review session that stress-tests plans against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallize. Use when validating architecture or plans against a project's language and documented decisions.
Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.