Stop guessing about Next.js patterns and write code that scales. This skill provides authoritative guidance from Vercel on file conventions, React Server Components, data fetching, error handling, and deployment best practices.

Struggling with Svelte 5 runes and modern patterns? Access official documentation and automated code fixes directly in your workflow.

Codebases accumulate technical debt over time. This skill simplifies recently modified code to improve readability and consistency without changing functionality.

Teams struggle with inconsistent style and unclear intent in code. This skill applies Clean Code principles to guide clearer naming, structure, and reviews.

Building complex AI systems with multiple agents requires sophisticated coordination. This skill provides patterns and commands for mesh, hierarchical, and adaptive swarm topologies with automatic load balancing and fault tolerance.

AI agents waste time repeating the same suboptimal approaches. ReasoningBank enables agents to learn from experience, recognize patterns, and continuously improve their strategies over time.

Traditional solo coding lacks real-time feedback and collaboration benefits. This skill transforms Claude into an intelligent pair programming partner with multiple modes including driver, navigator, and automatic role switching for enhanced code quality and learning.

Managing multiple AI agents working on the same codebase creates conflicts and coordination overhead. Agentic Jujutsu provides lock-free version control with self-learning capabilities that improve over time and resolve conflicts automatically.

Creating programmatic videos requires deep knowledge of Remotion best practices and patterns. This skill provides expert guidance on animations, compositions, audio, 3D content, and media handling to help you build production-quality videos with React.

PyTorch operators may lack support for unsigned integer types like uint16, uint32, and uint64. This skill provides step-by-step guidance for updating AT_DISPATCH macros to enable unsigned type support in operator kernels.

Creating backend APIs and admin panels with Payload CMS requires understanding collections, fields, hooks, and access control patterns. This skill provides comprehensive documentation and code examples for building TypeScript-first CMS applications with Next.js integration.

AI assistants often skip tests and write code directly. This skill enforces test-first development by requiring failing tests before any implementation. It prevents bugs, documents behavior, and enables safe refactoring for production code.

Random fixes waste hours and create new bugs. This skill teaches a four-phase process that finds root causes before attempting fixes. It prevents rework by ensuring you understand the problem before proposing solutions.

Code issues found late in development are expensive to fix. This skill dispatches a code-reviewer subagent to catch problems early, before they cascade into larger issues.

Code reviews often contain unclear or technically questionable feedback that gets implemented without verification. This skill ensures AI evaluates feedback technically before implementation, preventing bugs and maintaining code quality.

AI assistants often complete implementation tasks but lack structured guidance for integrating work back into the repository. This skill provides a step-by-step workflow for verifying tests, presenting merge and PR options, executing user choices, and safely cleaning up worktrees.

Multiple independent failures waste time when investigated sequentially. This pattern dispatches one AI agent per independent problem domain, letting them work concurrently to solve separate issues in parallel.

Generating code in monorepos requires navigating complex project structures and selecting the right generator. This skill prioritizes workspace-plugin generators for custom solutions and guides you through running generators with proper verification steps.

Managing feature implementation across scattered todo lists and design documents wastes time and causes missed tasks. Task execution engine reads structured task lists directly from markdown design files and executes them one by one with automatic checkbox updates.

Feature development often stalls due to unclear requirements and missing context. The Feature Design Assistant guides you through structured information gathering to capture all necessary details before implementation, resulting in complete designs and actionable implementation tasks.