Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
vercel-kv
Imported from https://github.com/secondsky/claude-skills.
drizzle-orm-d1
Drizzle ORM for Cloudflare D1 provides a type-safe SQL query builder and schema management tool that enables developers to build robust D1 databases with automatic migrations, relational queries, and transaction support while preventing common D1 errors.
cloudflare-zero-trust-access
Imported from https://github.com/secondsky/claude-skills.
open-source-contributions
This skill provides best practices and validation scripts for open source contributions, ensuring clean PRs with proper testing, focused features, and professional communication to save maintainers time and prevent common errors.
shadcn-vue
Imported from https://github.com/secondsky/claude-skills.
google-gemini-api
Imported from https://github.com/secondsky/claude-skills.
hono-routing
This skill provides type-safe Hono API development with routing, middleware, and RPC support, enabling request validation using Zod/Valibot and preventing common errors like middleware type inference issues and validation failures.
sql-query-optimization
Imported from https://github.com/secondsky/claude-skills.
websocket-implementation
This skill implements scalable real-time WebSocket communication with connection management, room-based messaging, and horizontal scaling support, ideal for building chat systems, live notifications, collaborative tools, and real-time dashboards.
vercel-blob
Imported from https://github.com/secondsky/claude-skills.
skill-name
This skill provides a comprehensive template for creating Claude skills with structured documentation, best practices, and issue prevention guidelines to ensure reliable and maintainable implementations.
tailwind-v4-shadcn
This skill provides a production-tested setup for initializing React projects with Tailwind CSS v4 and shadcn/ui, covering architecture, dark mode, common gotchas, and fixes for theming issues to ensure a fast, error-free implementation.
zustand-state-management
Imported from https://github.com/secondsky/claude-skills.
nextjs
This skill provides expert guidance for Next.js 16 App Router development, covering Server Components, Server Actions, caching patterns, and React 19.2 features, while helping to avoid common errors and implement production-ready performance optimizations.
systematic-debugging
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
moai-workflow-templates
Provides a unified system for managing code templates, GitHub issue templates, and project optimization workflows. Includes smart merge algorithms to preserve user customizations during template updates and backup restoration capabilities.
git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
skill-developer
Provides detailed guidance for creating and managing Claude Code skills with auto-activation. Covers skill structure, trigger patterns, hook mechanisms, enforcement levels, and testing procedures. Includes practical examples and configuration templates.
chess-commentator
This skill should be used when analyzing chess positions. Automatically triggers when users provide FEN positions for analysis or ask about specific chess positions. Provides engine-powered analysis with natural language explanations of best moves, key variations, and strategic/tactical themes.
erlang-otp-behaviors
Use when oTP behaviors including gen_server for stateful processes, gen_statem for state machines, supervisors for fault tolerance, gen_event for event handling, and building robust, production-ready Erlang applications with proven patterns.
syzlang-ioctl-basics
Syzkaller syzlang syntax basics for describing ioctl syscalls
Speaker Clustering Methods
Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown, KMeans when count is known, and always normalize embeddings before clustering.
pytorch-core
Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration. Covers optimizations like pin_memory and lazy module initialization. (pytorch, tensor, autograd, nn.Module, optimizer, training loop, state_dict, pin_memory, lazylinear, requires_grad)
browser-testing
VERIFY your changes work. Measure performance, CLS. Use BEFORE and AFTER making changes to confirm fixes. Includes ready-to-run scripts: measure-cls.ts, detect-flicker.ts