Agent skills are reusable capability packs — folders of structured instructions, and sometimes scripts and reference files, that teach an AI coding agent how to do a specific job the same way every time. Install one once and the agent loads it on demand instead of you re-explaining context every session, which keeps its working memory lean. This is the curated, community-ranked index of the best skills for Claude Code, the Claude apps, Cursor, and other agent runtimes.
Agent skill that breaks large UI files into reusable components for frontend developers using AI-assisted workflows.
Agent skills for UI builders, by the creators of Tailwind CSS and Refactoring UI, wires into Claude Code, Cursor, and Codex to ship interfaces that look designed, not generated.
Best for Teams using coding agents for frontend work who want output that reflects senior design judgment, not generic AI defaultsOpen-source collection of 45+ AI agent skills for marketing, CRO, SEO, copywriting, analytics, and growth, built for Claude Code, Cursor, and any Agent Skills-compatible agent.
Best for Technical marketers and founders using Claude Code, Cursor, Windsurf, or OpenAI Codex who want marketing domain knowledge baked inClaude skill that turns UI screenshots, Figma exports, and wireframes into semantic, accessible HTML or JSX, no styling included, by design.
Best for Converting screenshots, Figma exports, mockups, or wireframes into a clean semantic scaffold before any styling passAgent skill for adapting desktop UIs to mobile, tablet, and desktop breakpoints, built by the makers of Tailwind CSS and Refactoring UI.
Best for Teams using AI agents to build UIs who need reliable mobile, tablet, and desktop breakpoint coverageAgent skill that regenerates light-mode raster images as true dark-mode variants using gpt-image-2, for interface builders using Claude Code, Cursor, or Codex.
Best for Teams shipping dark mode who need raster image assets that look designed rather than filteredAgent skill for adding thoughtfully designed dark mode to existing UIs, balances contrast across text, surfaces, borders, and images for Claude Code, Cursor, Codex, and more.
Best for Teams with a finished light-mode UI who want dark mode that looks designed rather than auto-invertedAgent skill for Tailwind CSS cleanup: sorts, deduplicates, and resolves conflicting utility classes inside Claude Code, Cursor, and other coding agents.
Best for Teams where multiple agents or developers touch the same Tailwind components, causing class string entropyui.sh Brand Kit skill: generate a visual brand direction board with site mockups, typography, and color from a single prompt, for Codex-powered coding agents.
Best for Teams starting a new product who want a coding agent to build UI with a coherent visual identity from day oneui.sh Ideas skill for AI coding agents: generate and compare multiple UI design directions in the browser before committing to one.
Best for Teams that want to explore multiple UI directions before committing any design to the codebaseClaude/Codex/Cursor skill from the Tailwind CSS team that upgrades AI-generated UI from generic to designer-quality, in any existing project.
Best for Teams using Claude Code or Codex to ship UI who want output that looks senior-designer reviewed, not AI-interpolatedOpen-source PM skills marketplace: 68 AI skills and 42 workflows across 9 Claude plugins for product managers doing discovery, strategy, execution, and launch.
Best for PMs using Claude Code or Claude Cowork who want framework-driven decisions baked into daily AI workflowsA catalog of repeatable AI agent workflows with built-in feedback loops, plus an installable skill for finding, adapting, and designing your own loops.
Best for Teams using Codex, Cursor, or Claude Code who want agents to iterate reliably instead of making one-shot guessesColeção pública de Agent Skills de exemplo da Anthropic para o Claude: pastas independentes de instruções, scripts e recursos abrangendo tarefas criativas, técnicas e empresariais, incluindo as skills de documentos que alimentam as capacidades de arquivos do Claude.
Best for Aprender a criar Agent SkillsAs skills de agente do dia a dia de Matt Pocock para engenharia de verdade, não para vibe coding. Skills pequenas, composáveis e independentes de modelo (instaláveis via skills.sh), com configuração guiada e integração com rastreador de issues.
Best for Alinhar um agente antes de ele escrever códigoUma lista curada de recursos sobre Generative Engine Optimization (GEO), voltada para a otimização de conteúdo para motores de resposta baseados em IA, como ChatGPT, Perplexity, Claude e Google AI Overviews, abrangendo artigos científicos, ferramentas, estratégias e estudos de caso.
Best for Aprender sobre Generative Engine Optimization (GEO)Uma habilidade de design para Claude Code, Cursor e Codex que se recusa a parecer gerada por IA: escolhe uma macroestrutura para o briefing, aplica um dos vinte temas e executa dezenas de verificações anti-slop antes de emitir o resultado.
Best for Projetar UI que não pareça gerada por IAUm framework de habilidades agênticas e metodologia de desenvolvimento de software para agentes de codificação, com habilidades combináveis e instruções que orientam um fluxo de trabalho spec-first, TDD e orientado a subagentes no Claude Code, Codex, Cursor, Gemini e muito mais.
Best for Fornecer aos agentes uma metodologia de desenvolvimento completa e opinativaUma biblioteca de frameworks de modelos mentais e pensamento crítico empacotados como habilidades do Claude Code, incluindo primeiros princípios, pensamento sistêmico, OODA, pré-mortem e mais, invocados por nome por meio de um roteador, com um pipeline de avaliação transparente.
Best for Oferecer ao Claude Code frameworks de raciocínio estruturadoUma skill de IA que fornece inteligência de design a agentes de codificação, com regras de raciocínio e estilos de UI para geração de UI/UX profissional em diversas plataformas e frameworks.
Best for Estruturar um design system a partir de um briefing de projetoInstruções de agente compartilhadas, habilidades de fluxo de trabalho reutilizáveis e scripts auxiliares com poucas dependências, criados por Peter Steinberger, para agentes de codificação no estilo Codex e Claude.
Best for Compartilhar um único conjunto de regras e habilidades de agente entre reposUma habilidade de agente que audita qualquer codebase com seu modelo mais capaz e escreve planos de implementação autocontidos para modelos mais baratos (ou humanos) executarem.
Best for Auditar um codebase desconhecido ou legadoThe Agent Skills format was popularized by Anthropic's Claude: a skill is a directory with a SKILL.md file — a name, a short description, and Markdown instructions — optionally bundled with helper scripts and resources. The agent reads only the one-line description until a task matches, then pulls in the full skill. This “progressive disclosure” is what makes skills scale: you can install dozens without bloating the context window, because the model only loads the body of the ones it actually needs.
Skills are portable, composable, and inspectable. The same skill can run across projects and, increasingly, across tools that adopt the format, and several can stack on a single task. Because most are open source and version-controlled, you can read exactly what the agent will be told before you install it. Browse the ranked list below, open any skill for its source and setup steps, and upvote the ones that earn a permanent place in your setup.
An agent skill is a packaged set of instructions — and sometimes scripts and reference files — that teaches an AI coding agent how to perform a specific task reliably. Instead of re-explaining context each session, you install the skill once and the agent carries that knowledge forward whenever a matching task comes up.
A skill is a folder containing a SKILL.md file with a name, a description, and Markdown instructions. The agent keeps only the short description in context and loads the full skill on demand when a task matches — a pattern called progressive disclosure that lets you keep many skills installed without using up the model's context window.
Most skills install by placing the skill folder in your agent's skills directory, adding it through the tool's plugin or extension system, or pointing the agent at the skill's repository. Open any skill below and follow its link for the exact, source-specific steps.
A skill is knowledge: instructions that shape how the agent behaves. An MCP server is a live connection: it gives the agent new tools and data (a database, an API, a filesystem). They're complementary — a skill can tell the agent how and when to use the tools an MCP server exposes.
Claude Code and the Claude apps support the Agent Skills format natively, and because skills are plain Markdown folders, other agent runtimes are adopting the pattern. Each entry notes the tools it's built for.
The majority of skills listed here are open source and free to use. Open an entry and follow its link to confirm the license and any requirements before depending on it.
Yes. Create a folder with a SKILL.md file, write a clear name and description so the agent knows when to use it, then add your instructions and any helper scripts. Many of the skills below are good templates to start from.
Entries are ranked by community upvotes — one per account — with the newest finds surfaced under the New tab. Everything is human-reviewed before it appears.