Best Cursor Skills
Curated agent skills for Cursor's Agent mode — full-stack development, UI/design workflows, code review and testing. Install once via SKILL.md and it works across Cursor, Claude Code and Codex.
36 curated skills
⚡ Quick Setup: Skills in Cursor
Cursor reads skills from two locations — user-level and project-level. Unlike .cursorrules, skills load on demand and can bundle scripts and reference docs:
~/.cursor/skills/<skill-name>/SKILL.md— global skills for every Cursor workspace (also reads~/.agents/skills).cursor/skills/<skill-name>/SKILL.md— project skills committed with your repository
$ npx skills add <owner/repo>The skills CLI downloads the SKILL.md package from GitHub and drops it into the correct Cursor skills directory — no manual copying needed.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
frontend-ultimate
Ultimate 25+ years expert-level frontend skill covering Next.js, React, TypeScript, Tailwind CSS, styled-components, Redux, Zustand, Webpack, Vite, Parcel, Jest/Vitest testing, performance optimization, and ALL security aspects comprehensively (XSS, CSRF, injection, data privacy, CSP, dependency security, etc.). Covers all use cases (SPAs, PWAs, e-commerce, dashboards, real-time apps, mobile-responsive). Advanced features include A11y, Core Web Vitals, SEO, i18n, error handling, monitoring, component architecture, design patterns. Maximum security hardening, genius-level optimization, modernized development standards. Use when building ANY frontend application requiring enterprise security, performance, and scalability.
mcp-server-developer
Build, harden, document, and ship MCP servers to Claude standards with FastMCP 2.13+ architecture, disciplined tooling, and release-ready workflows.
super-dev
顶级 AI 开发战队 (God-Tier)。调度 10 位精英专家 (PM/架构/UI/UX/安全/代码/DBA/QA/DevOps/RCA),交付商业级研发资产。内置思维链 (CoT) 与实时市场情报系统。
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Agent Browser
A powerful skill for Claude agents.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
scikit-learn
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
tldr-code
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
ai-multimodal
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
browser-use
AI-driven browser automation via Model Context Protocol
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
codex-claude-cursor-loop
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality
moai-lang-go
Enterprise Go for systems and network programming Go 1.25.4, Fiber v3,
context-engine
Codebase search and context retrieval for any programming language. Hybrid semantic/lexical search with neural reranking. Use for code lookup, finding implementations, understanding codebases, Q&A grounded in source code, and persistent memory across sessions.
react-typescript
Modern React 19+ patterns with TypeScript including function components, hooks, state management, TanStack Query integration, form handling with Zod, error boundaries, and performance optimization. Use when building React applications, implementing components, or setting up state management.
ui-implementer
Implements UI components from scratch based on design references (Figma, screenshots, mockups) with intelligent validation and adaptive agent switching. Use when user provides a design and wants pixel-perfect UI implementation with design fidelity validation. Triggers automatically when user mentions Figma links, design screenshots, or wants to implement UI from designs.
ultrathink-detective
⚡ PRIMARY TOOL for: 'comprehensive audit', 'deep analysis', 'full codebase review', 'multi-perspective investigation', 'complex questions'. Combines ALL detective perspectives (architect+developer+tester+debugger). Uses Opus model. REPLACES grep/glob entirely. Uses claudemem v0.3.0 AST with ALL commands (map, symbol, callers, callees, context). GREP/FIND/GLOB ARE FORBIDDEN.
coder
Write, edit, and refactor code with full tool access - Use when you need to actually write or modify code, create files, run commands, or implement features.
playwright-browser-automation
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
ffmpeg
Guide for using FFmpeg - a comprehensive multimedia framework for video/audio encoding, conversion, streaming, and filtering. Use when processing media files, converting formats, extracting audio, creating streams, applying filters, or optimizing video/audio quality.
wordpress-plugin-core
Build secure WordPress plugins with core patterns for hooks, database interactions, Settings API, custom post types, REST API, and AJAX. Covers three architecture patterns (Simple, OOP, PSR-4) and the Security Trinity.Use when creating plugins, implementing nonces/sanitization/escaping, working with $wpdb prepared statements, or troubleshooting SQL injection, XSS, CSRF vulnerabilities, or plugin activation errors.
react-native-expo
Build React Native 0.76+ apps with Expo SDK 52. Covers mandatory New Architecture (0.82+), React 19 changes (propTypes/forwardRef removal), new CSS (display: contents, mixBlendMode, outline), Swift iOS template, and DevTools migration.Use when: building Expo apps, migrating to New Architecture, or troubleshooting "Fabric component not found", "propTypes not a function", "TurboModule not registered", or Swift AppDelegate errors.
nextjs
Build Next.js 16 apps with App Router, Server Components/Actions, Cache Components ("use cache"), and async route params. Includes proxy.ts (replaces middleware.ts) and React 19.2.Use when: building Next.js 16 projects, or troubleshooting async params (Promise types), "use cache" directives, parallel route 404s (missing default.js), or proxy.ts CORS.
elevenlabs-agents
Build conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs.Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT.Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflowsor tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labspackages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config.Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control,
cloudflare-workers-ai
Run LLMs and AI models on Cloudflare's global GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1,Flux image generation, BGE embeddings (2x faster, 2025), streaming support, and AI Gateway for cost tracking.Use when: implementing LLM inference, generating images, building RAG with embeddings, streaming AI responses,using AI Gateway, troubleshooting max_tokens defaults (breaking change 2025), BGE pooling parameter (not backwardscompatible), or handling AI_ERROR, rate limits, model deprecations, token limits.Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama-4-scout, @cf/google/gemma-3-12b-it,@cf/mistralai/mistral-small-3.1-24b-instruct, @cf/openai/gpt-oss-120b, workers ai models, ai inference,cloudflare llm, ai streaming, text generation ai, ai embeddings, bge pooling cls mean, image generation ai,workers ai rag, ai gateway, llama workers, flux image generation, deepgram aura, leonardo image generation,vision models ai, ai chat completion, AI_ERROR, rate li
ai-sdk-ui
Build React chat interfaces with Vercel AI SDK v5/v6. Covers v6 beta (agent integration, tool approval,auto-submit), v4→v5 migration (breaking changes), useChat/useCompletion/useObject/useAssistant hooks,and 12 UI error solutions (stream parsing, stale body values, React update depth).Use when: implementing AI SDK v5/v6 chat UIs, migrating v4→v5, troubleshooting "useChat failed to parsestream", "useChat no response", or "stale body values" errors, or integrating OpenAI assistants.
ai-maestro-code-graph-query
PROACTIVELY query the code graph database to understand relationships and impact of changes. Use this skill WHEN READING any file to understand context, when searching for files, when exploring the codebase, or when you need to understand what depends on a component. This is your primary tool for understanding code structure and avoiding breaking changes.
design
UI/UX design guidelines for interactions, animation, layout, accessibility, and visual design. Use when building UI components, designing user experiences, or implementing user-facing features.
impl
Implements features and writes code based on Plans.md tasks. Use when user mentions 実装, implement, 機能追加, コードを書いて, 機能を作って, feature, coding, 新機能, implementing functions, classes, or features, 新しい関数. Do not use for review or build verification.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents. Use for creating new applications, scaffolding projects, or building features from scratch.
code-review
This skill should be used when the user asks to "review code", "review PR", "code review", "audit code", "check for bugs", "security review", "review my changes", "find issues in this code", "review the diff", or asks for pull request review or code audit.
Cursor Skills FAQ
How do I add skills to Cursor?
Run `npx skills add <owner/repo>` in your terminal — the skills CLI places the package in the right folder. Manually, create ~/.cursor/skills/<skill-name>/SKILL.md for a global skill or .cursor/skills/<skill-name>/SKILL.md inside a project.
What's the difference between SKILL.md and .cursorrules?
.cursorrules is a single flat prompt file that applies to every chat in a project. Skills are modular, on-demand capability packs: Cursor loads a skill's SKILL.md only when the task calls for it, and a skill can bundle scripts, references and examples — far more powerful and context-efficient than one global rules file.
Do the same skills work in both Cursor and Claude Code?
Yes. SKILL.md is an open standard shared by Cursor, Claude Code, Codex, Windsurf and others — install once and the skill works across all of them.
Which skills are best for Cursor's Agent mode?
Frontend and full-stack skills pair especially well with Cursor: design-system helpers, component scaffolding, code review and test generation. Anything that turns a repeated workflow into a deterministic checklist.