Ferramentas para engenheiros que desenvolvem software com IA: IDEs agênticos, construtores de aplicativos e a infraestrutura ao redor deles.
How to turn Claude into a structured adversary by assuming your plan already failed, and a ready-to-upload skill that automates the pre-mortem for any decision.
A curated breakdown of the Claude skills ecosystem, what skills are, how they work, and the handful worth installing first.
Best for Knowledge workers who need reliable document format conversions, such as PDF, DOCX, PPTX, and XLSX, on a daily basisExplores the cultural fade of color in products alongside nanoscale methods that make material color disappear through structural interference.
Best for Designers choosing palettes for products or interfacesA viral breakdown of AI agent loops, how Claude, ChatGPT, and Mira implement Plan-Execute-Verify cycles and when to actually build one.
Best for Builders who run the same AI task weekly or more and want compounding results instead of one-shot promptsAgent skill that breaks large UI files into reusable components for frontend developers using AI-assisted workflows.
Best for Refactoring monolithic UI files that have grown too large to edit easilyAgent 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 OpenTelemetry observability platform with traces, logs, metrics, service maps, session replay, and an AI agent MCP server, for backend and platform teams.
Best for Teams wanting unified traces, logs, metrics, service maps, and Kubernetes monitoring in a single OTel-native tool78+ animated shadcn/ui components plus 100+ AI agent patterns, distributed as copy-paste source, free, open-source, and zero npm lock-in.
Best for React and Tailwind teams already using shadcn/ui who want animated, accessible components without npm package overheadMCP gateway that gives AI agents like Claude Code, Cursor, and Codex one endpoint and one tool shape for every integration, with sandboxed execution and credential isolation by design.
Best for Teams running multiple MCP-compatible agents against a shared company tool stackOpen-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 inZero-dependency, SQLite-backed AI memory layer for agents, MCP-ready, local-first, and benchmarked against BEAM and LongMemEval.
Best for Builders who want persistent agent memory with zero infrastructure, no Postgres, Docker, or SaaS requiredVisual RAG pipeline that retrieves over screenshot tiles instead of parsed text, preserving tables, charts, and layout for more accurate document search.
Best for Builders doing RAG over documents where tables, charts, or layout carry meaning that HTML parsing silently dropsUm detector de cópias e colagens para código-fonte com suporte a mais de 200 formatos, motor baseado em Rust até 24-37x mais rápido, treze reporters, integrações com CI e pre-commit hooks, e saída pronta para IA incluindo uma skill de agente e servidor MCP.
Best for Encontrar duplicações de cópia e colagem em uma base de códigoUma coleção de spinners, loaders e animações de carregamento para aplicações web modernas, construída com React, Next.js, shadcn/ui, Tailwind CSS e Framer Motion.
Best for Adicionar spinners e animações de carregamento rapidamenteOpen-source React component kit for agentic AI apps: streaming chat, tool calls, reasoning, citations, and more, SDK-agnostic and fully owned by your codebase.
Best for React teams building agentic or chat interfaces who want streaming-ready components without writing them from scratchshadcn/ui, open-source, copy-owned UI components for developers building their own design system with full code control.
Best for Teams building a custom design system who need full ownership of component source codeOpen-source brand SVG icon library with 6,149+ typed, tree-shakeable icons for developers and designers.
Best for Apps that display third-party brand logos and want a single versioned npm dependencyFree repo scanner that checks GitHub and Bitbucket projects for malware, credential stealers, and crypto scams before you run their code.
Best for Developers vetting unfamiliar GitHub or Bitbucket repos before cloning or running them locallyAddy Osmani's essay on why more AI agents don't mean more shipped work, and how to architect your attention like a concurrent system.
Best for Developers building or scaling multi-agent coding workflowsResearch synthesis covering two 2025 papers on recursive multi-agent systems: RecursiveMAS and RAH, for developers building agentic pipelines.
Best for Developers designing or evaluating multi-agent orchestration architecturesAn 18-step practical guide to unlocking Claude's full capability through Projects, Custom Instructions, and a personal knowledge base.
Best for Daily Claude users who want persistent, personalized context without re-explaining themselves every sessionA technical argument for replacing text chunks with structured QA packets in RAG pipelines, for ML engineers and data architects building production retrieval systems.
Best for ML engineers and data architects who own a RAG ingestion pipeline and want to fix retrieval at the sourceClaude 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 file-format loaders for geospatial, tabular, and 3D data, with worker-thread and streaming support for big-data JS apps.
Best for Apps handling multiple geospatial or 3D formats (shapefiles, glTF, Arrow, CSVs, point clouds) through one unified APIOpen-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 workflowsContext compression MCP server and proxy for AI agents, cuts token usage 60-95% across tool outputs, logs, RAG, and files while preserving answer accuracy.
Best for Agentic workflows drowning in tool call outputs, logs, RAG results, and conversation history that inflate token costsFree, open-source shadcn-style registry of production-ready AI agent recipes for developers who want full code ownership with zero config.
Best for Teams that want full code ownership over agent logic without being locked into an opaque runtime dependencyA 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 SkillsUm framework de skeleton loading que gera telas de carregamento pixel-perfect a partir da sua UI real, sem medições manuais ou placeholders ajustados à mão, para React, Preact, Vue, Svelte 5, Angular e React Native.
Best for Skeletons pixel-perfect sem ajustes manuaisAs 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 biblioteca de efeito liquid-glass para a web, aplica refração realista de vidro, blur, aberração cromática e iluminação em qualquer elemento HTML usando shaders WebGL.
Best for Refração realista de vidro na web via WebGLUm pentester de IA autônomo e white-box para aplicações web e APIs; ele analisa seu código-fonte, identifica caminhos de ataque e executa exploits reais para comprovar vulnerabilidades com uma prova de conceito funcional. Execute localmente (código aberto) ou pela plataforma Keygraph.
Best for Pentest white-box automatizado de aplicações web e APIsUma biblioteca de animações de carregamento reutilizáveis no estilo dotmatrix para React e Next.js, instalável pelo registro do shadcn ou copiando o código-fonte direto da documentação.
Best for Loaders com estilo dotmatrix distintoUma 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 coleção interativa de transições CSS reutilizáveis e prontas para copiar, incluindo redimensionamento de cards, animações de modais e menus, pop de badges e muito mais, cada uma emitindo um snippet autocontido com um guard de reduced-motion.
Best for Adicionar micro-interações refinadas sem uma biblioteca de motionO toolkit open-source do GitHub para Spec-Driven Development. A Specify CLI transforma especificações executáveis em implementações funcionais, com suporte a diversos agentes de codificação com IA.
Best for Spec-Driven Development com agentes de IAUma 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 IAUma biblioteca Node.js para verificação de e-mails via SMTP, que checa sintaxe, registros MX do domínio e entregabilidade SMTP em tempo real, sinaliza endereços descartáveis e retorna um resultado estruturado de validade.
Best for Validar endereços de e-mail antes do envioOrquestração open-source da OpenAI para o Codex: transforma o trabalho do projeto em execuções de implementação isoladas e autônomas, para que as equipes gerenciem o trabalho em vez de supervisionar agentes de codificação.
Best for Gerenciar o trabalho em vez de supervisionar agentes de codificaçãoUm efeito animado de metal líquido em WebGL para React. Envolva um botão, chip ou ícone para adicionar um anel metálico em tempo real, com presets, temas, intensidade ajustável e reflexo de proximidade opcional em elementos vizinhos.
Best for Um destaque WebGL metálico premium em botões ou ícones principais