Clean architecture requires clear separation between operations that change state and those that return data. This skill provides patterns and code examples for implementing Command Query Separation and CQRS in .NET applications.

Writing maintainable TypeScript code is challenging without clear guidance. This skill provides practical examples of DRY, KISS, and YAGNI principles to help you write cleaner, more readable code that your team can understand.

Writing modern frontend code with Next.js, React 19, and shadcn/ui requires understanding Server Components, data fetching patterns, and performance optimization. This skill provides comprehensive guidelines and proven patterns for building type-safe, performant web applications.

Writing backend code for Supabase can be complex with many moving parts. This skill provides ready-to-use patterns for Edge Functions, database design, Row-Level Security, and integrations so you can ship faster with fewer bugs.

Ensures your code actually works by creating isolated test environments and executing code with realistic inputs. This skill moves beyond static analysis to verify genuine functionality through systematic testing, debugging, and validation workflows.

Manual code reviews are slow and inconsistent across reviewers. This skill orchestrates 15 specialized AI agents to validate PRs systematically across security, performance, architecture, and documentation dimensions in a repeatable 4-hour workflow.

Manual code reviews are time-consuming and inconsistent across teams. This skill orchestrates five specialized AI agents to perform comprehensive security, performance, quality, testing, and documentation analysis on pull requests in parallel, delivering standardized review reports with actionable feedback.

Finding bugs in complex codebases wastes valuable development time. This skill provides a structured 5-phase debugging workflow that identifies root causes and validates fixes automatically.

Building APIs requires systematic planning, implementation, testing, and deployment. This skill orchestrates 12 specialist agents across 5 phases to deliver production-ready REST APIs using Test-Driven Development methodology.

Building complex AI systems with multiple agents requires sophisticated coordination. This skill provides proven patterns and commands for orchestrating agent swarms with automatic load balancing, fault tolerance, and intelligent task distribution.

Code that works is not enough. Poor style creates confusion, accumulates technical debt, and slows team collaboration. This skill transforms functionally correct code into maintainable, production-grade code by applying systematic style audits and refactoring.

Manual code reviews are time-consuming and inconsistent. This workflow coordinates multiple specialized AI agents to perform thorough reviews across quality, security, performance, architecture, and documentation in parallel.

Building REST APIs from scratch requires coordinating multiple specialists across backend, database, testing, and DevOps. This skill provides a complete 2-week workflow that coordinates AI agents to design, implement, test, document, and deploy production-ready APIs using test-driven development.

Debugging complex bugs wastes hours of developer time. This skill uses systematic root cause analysis, multi-model reasoning, and automated testing to identify and fix bugs faster with validated solutions.

Stop building on assumptions. This skill uses 6-agent research teams and 5-iteration pre-mortem analysis to create evidence-based project plans with less than 3 percent failure confidence.

AI agents waste time repeating the same mistakes and using suboptimal strategies. ReasoningBank Intelligence enables your agents to learn from every experience, recognize patterns, and continuously improve their performance over time.

Code quality checks take too long and slow down development. Run theater detection, linting, security scans, and tests in parallel for instant feedback.

Writing code alone slows you down and limits your learning. This skill enables AI-assisted pair programming with flexible driver-navigator roles, automatic testing, and continuous code review. You get real-time quality feedback while accelerating development and learning best practices.

Manual code reviews are slow and inconsistent. The Code Review Assistant uses a multi-agent swarm to analyze pull requests across security, performance, style, tests, and documentation in parallel, then posts detailed feedback with fix suggestions directly to GitHub.

Building complex AI workflows requires coordinating multiple models and tools. This skill provides a declarative framework to define cascades with sequential, parallel, and conditional stages that automatically route tasks to the optimal AI model.