Loading...
Loading...
Found 3,118 Skills
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Use when completing a task, implementing a feature, or before committing to verify work meets requirements and coding standards. Triggers: task completion, pre-commit check, pre-merge validation, plan alignment verification, post-refactor quality gate.
Privacy review and testing: evaluate PII handling, data flows, tracking inventory, consent mechanisms, storage practices, and data leakage risks with browser-based validation against GDPR, CCPA, and industry best practices.
TanStack Query v5 (React Query) server state management. Use for data fetching, caching, mutations, or encountering v4 migration, stale data, invalidation errors.
Ethical hacking and security testing methodologies using penetration testing tools, exploit frameworks, and manual security validation. Use when assessing application security posture and identifying exploitable vulnerabilities.
React 19 performance optimization guidelines for concurrent rendering, Server Components, actions, hooks, and memoization (formerly react-19). This skill should be used when writing React 19 components, using concurrent features, or optimizing re-renders. This skill does NOT cover Next.js-specific features like App Router, next.config.js, or Next.js caching (use nextjs-16-app-router skill). For client-side form validation with React Hook Form, use react-hook-form skill.
End-to-end browser testing with Playwright. Test user interactions, form validation, navigation, and visual feedback with full browser automation.
Redis expert for caching, pub/sub, data structures, and distributed systems patternsUse when "redis, caching strategy, cache invalidation, pub/sub, rate limiting, distributed lock, session storage, leaderboard, message queue, upstash, redis, caching, pub-sub, session, rate-limiting, distributed-lock, upstash, elasticache, memorystore" mentioned.
Luau best practices and clean code patterns for Roblox development. Use this skill when: - Writing new Luau modules, services, or controllers - Reviewing code for quality and maintainability - Setting up project structure and organization - Implementing error handling and validation - Managing memory and preventing leaks - Writing secure server-authoritative code - Following Roblox-specific conventions - Refactoring or improving existing code Triggers: "best practices", "clean code", "code review", "refactor", "code quality", "naming convention", "code style", "module pattern", "service pattern", "memory leak", "error handling", "pcall", "security", "server authority", "validation", "code organization"
End-to-end product development for iOS/macOS apps. Covers market research, competitive analysis, PRD generation, architecture specs, UX design, implementation guides, testing, and App Store release. Use for product planning, validation, or generating specification documents.
FastAPI framework mechanics and advanced patterns. Use when configuring middleware, creating dependency injection chains, implementing WebSocket endpoints, customizing OpenAPI documentation, setting up CORS, building authentication dependencies (JWT validation, role-based access), implementing background tasks, or managing application lifespan (startup/shutdown). Does NOT cover basic endpoint CRUD or repository/service patterns (use python-backend-expert) or testing (use pytest-patterns).
Orchestrates single user-invocable skill across 3 parallel scenarios with synchronized state and progressive difficulty. Use when running multi-scenario demos, comparative testing, or progressive validation workflows.