Colección de AI Agent Skills instalables para workflows de desarrollo de official trusted en Claude Code, Cursor y Windsurf.
Esta colección destaca skills oficiales de IA y herramientas confiables mantenidas por equipos first-party y actores sólidos del ecosistema. Está pensada para equipos que necesitan calidad predecible, documentación clara e integraciones listas para producción. MCP puede aportar como capa de compatibilidad, pero la prioridad son skills y herramientas prácticas para entregar productos de IA con mayor velocidad y confianza.
This collection should not trap users in comparison mode or pretend to install the whole collection. Its job is to narrow the shortlist to one skill, then send the next click into installation, validation, and rollout. Installation happens on the skill path.
Move from trusted discovery into the install flow, validation checklist, and first command path before comparing anything else.
Open the Install PathOnce the install path is clear, move into the solution, CLI, or editorial surface that best matches this collection. That keeps platform, framework, and operations demand narrowing into a more verifiable high-intent journey.
An editorial guide that explains why certain skills are trusted and how to choose among them.
Editorial guides let the site lead with reasoning instead of raw inventory.
Comparison pages are one of the best ways to prove independent judgment and avoid the mirror-site posture.
Comparisons make Killer-Skills look editorial-first instead of repo-wrapper-first.
Reviewed on 2026-04-16 against first-party ownership, documentation quality, install clarity, and production relevance. This is the safest collection to lead with after the site's corpus reset.
We prioritize this page because it lets users verify trust first and then move into one installation path, which is stronger for recovery than sending them into another repo crawl.
Use this collection when you need the safest first install before expanding into community or niche tools.
Use the collection as an editorial filter when deciding which tools are safe enough for a shared developer workflow.
Confirm what the CLI writes, how sync behaves, and what operators should verify after the install path is clear.
Use the agent-workflows solution page after installation to decide which trusted toolset best matches the job to be done.
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling
Guidelines for creating API routes in Expo Router with EAS Hosting
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (useLoaderData).
`@expo/ui/jetpack-compose` package lets you use Jetpack Compose Views and modifiers in your app.
`@expo/ui/swift-ui` package lets you use SwiftUI Views and modifiers in your app.
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
Build and distribute Expo development clients locally or via TestFlight
Un optimizador de prompt es una herramienta que mejora la eficiencia en la creación de instrucciones para AI Agents
El diseño de API REST es un conjunto de patrones y convenciones para crear APIs coherentes y fáciles de usar.
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Click-path-audit is a powerful AI agent skill that helps developers identify bugs in their UI by tracing every user-facing button and touchpoint. It benefits developers by providing a systematic approach to debugging, ensuring a seamless user experience.
La habilidad de onboarding de codebase es una función que analiza un codebase desconocido y genera una guía de onboarding estructurada.
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
Estándares de codificación C++ basados en las pautas de C++ Core, para escribir, revisar y refactorizar código C++ de manera moderna y segura
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitH...
The django-verification skill automates testing, linting, and security scans for Django projects, ensuring quality and security before release or PR. It benefits developers by saving time and reducing errors.
The foundation-models-on-device skill enables developers to build AI-powered features using Apple Intelligence on-device, generating or summarizing text without cloud dependency. It helps developers create privacy-preserving AI features with custom tool calling and snapshot streaming.
Pruebas Kotlin es un conjunto de patrones de testing para escribir tests confiables
Desarrollo de aplicaciones Laravel con pruebas automatizadas y cobertura de código utilizando PHPUnit y Pest.
La habilidad de agente de IA para patrones de servidor MCP permite a los asistentes de IA llamar a herramientas, leer recursos y utilizar promts desde tu servidor
La habilidad de agente de IA Nutrient es una herramienta de procesamiento de documentos que utiliza la API de Nutrient para convertir, extraer y redactar documentos.
La seguridad Perl se refiere a las prácticas y técnicas utilizadas para proteger las aplicaciones Perl contra ataques y vulnerabilidades de seguridad
The project-guidelines-example skill provides a template for project-specific skills, leveraging Next.js, FastAPI, and Claude API. It helps developers manage complex projects and improve coding efficiency.
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
Pruebas de Rust: técnicas para escribir pruebas de unidad, integración y asíncronas
The santa-method AI agent skill provides multi-agent adversarial verification, helping developers ensure code accuracy and compliance by utilizing two independent review agents.
The search-first AI agent skill systematizes the research-before-coding workflow, assisting developers in finding existing tools and libraries before implementing custom code. This skill benefits developers by saving time and reducing redundant code.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build vid...
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
Translate visa application documents (images) to English and create a bilingual PDF with original and translation
Canary-watch es una habilidad de agente de IA que monitorea aplicaciones desplegadas para detectar regresiones y errores
Claude DevFleet es una habilidad de agente de IA que permite orquestar tareas de codificación en paralelo, con informes estructurados y seguimiento de progreso
This AI agent skill streamlines C++ testing with GoogleTest and CMake, helping developers write and maintain robust tests. It automates test workflows for efficient code validation.
Este conjunto de habilidades de agente de IA proporciona patrones de arquitectura Django para aplicaciones escalables y mantenibles
This AI agent skill provides a thorough Flutter/Dart code review, covering widget best practices, state management patterns, and clean architecture. Developers can improve their code quality and productivity with this skill.
El skill de patrones de Go proporciona mejores prácticas y convenciones para construir aplicaciones robustas y eficientes.
The laravel-patterns skill provides production-grade Laravel architecture patterns for scalable and maintainable applications, benefiting developers with improved workflow and app performance.
Reglas Distill es una habilidad de agente de IA que utiliza técnicas de aprendizaje automático para extraer principios transversales de habilidades y convertirlos en reglas.
Safety Guard is an AI agent skill that prevents destructive operations, ensuring safe coding practices for developers working on production systems. It protects against accidental data loss and system damage.
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
The springboot-verification skill automates testing and security scans for Spring Boot projects, helping developers ensure high-quality code. It integrates with Maven and Gradle for seamless workflow automation.
The customs-trade-compliance AI agent skill helps developers automate customs operations, ensuring lawful and cost-optimized movement of goods across borders. It assists with HS classification, duty calculations, and denied party screening, reducing the risk of penalties and seizures.
The energy-procurement skill helps senior energy managers optimize energy spend across multiple facilities. It analyzes tariff structures, identifies optimization opportunities, and evaluates demand charge mitigation strategies, leveraging AI coding for improved procurement decisions.
La planificación de la demanda de inventario es el proceso de predecir la demanda de productos y gestionar las existencias para minimizar los desabastecimientos y el exceso de inventario.
The production-scheduling AI agent skill helps senior production schedulers optimize job sequencing, line balancing, and changeover optimization, benefiting production management, planning, quality, and maintenance teams by maximizing throughput and meeting customer delivery commitments.
# Benchmark — Performance Baseline & Regression Detection ## When to Use - Before and after a PR to measure performance impact - Setting up performance baselines for a project - When users report "it feels slow" - Before a launch — ensure you meet performance targets - Comparing your stack agains...
Blueprint es un generador de planes de construcción que permite a los desarrolladores crear planes de acción detallados
La habilidad de agente de pruebas de navegador automatizadas permite probar la interfaz de usuario y la interacción en el navegador de manera automática
This AI agent skill provides universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development, helping developers maintain high-quality codebases. It assists in enforcing naming conventions, formatting, and structural consistency.
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.
La búsqueda Exa es una habilidad de agente de IA que utiliza el servidor Exa MCP para realizar búsquedas neurales en la web, el código y las empresas.
Kotlin Exposed es un conjunto de patrones de acceso a bases de datos que facilitan el uso de bases de datos en aplicaciones Kotlin.
El sistema de diseño de vidrio líquido de iOS 26 ofrece una experiencia de usuario única con efectos de desenfoque, reflexión y morfismo interactivo para SwiftUI, UIKit y WidgetKit.
Turbopack es un empaquetador incremental para Next.js que mejora la velocidad de desarrollo y actualizaciones en caliente.
Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.
Plankton es una herramienta de IA que se integra con Claude Code para garantizar la calidad del código en tiempo de escritura.
La habilidad de agente de IA regex-vs-llm-structured-text para Claude Code proporciona un marco de decisión para elegir entre regex y LLM al parsear texto estructurado.
The tdd-workflow AI agent skill enforces test-driven development principles, ensuring comprehensive test coverage for developers. It streamlines coding workflows, reducing errors and increasing productivity.
La verificación de bucle es un sistema que verifica la calidad de las sesiones de Claude Code a través de fases de verificación
El equipo de agentes AI para Claude Code es una herramienta interactiva para componer y enviar equipos paralelos de manera eficiente
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
Bun es un runtime de JavaScript que ofrece una alternativa a Node.js con funcionalidades de administrador de paquetes, empaquetador y ejecutor de pruebas
El patrón de cache de hash de contenido utiliza hashes SHA-256 para almacenar resultados de procesamiento de archivos, mejorando la eficiencia y reduciendo la carga de trabajo
Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.
Investigación profunda es una función que utiliza firecrawl y exa MCP para producir informes de investigación exhaustivos.
La habilidad de agente de IA 'django-tdd' proporciona estrategias de testing con pytest-django y TDD para Django, mejorando la calidad del código.
Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.
La habilidad de lente de producto para Claude Code es una herramienta de desarrollo que ayuda a los desarrolladores a validar el 'por qué' detrás de cada característica y a tomar decisiones informadas sobre su producto.
Spring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services.
Spring Boot TDD es un enfoque de desarrollo que utiliza pruebas unitarias y de integración para garantizar la calidad del código
This AI agent skill enables developers to adopt Swift 6.2's concurrency model, ensuring single-threaded code by default and explicit background offloading. It helps resolve data-race safety compiler errors and optimizes app architecture.
Inyección de dependencias basada en protocolos para Swift, que permite simular el sistema de archivos, la red y las API externas para pruebas determinísticas.
Aprendizaje continuo v2 es un sistema de aprendizaje de agente de IA que convierte sesiones de Claude Code en conocimientos reutilizables
La habilidad de diseño de sistemas analiza y genera un sistema de diseño coherente para mejorar la consistencia visual de tu proyecto
La habilidad de cumplimiento de reglas para Claude Code ayuda a medir la conformidad de los agentes con las reglas y habilidades definidas.
Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.
Nuestra habilidad de agente de IA para la gestión de no conformidad de calidad ayuda a los ingenieros de calidad a gestionar el ciclo de vida completo de no conformidad, desde la inspección hasta la disposición final.
>
Carrier relationship management simplifies freight management for senior transportation managers, leveraging AI to optimize carrier onboarding, RFPs, and performance tracking.
La gestión de excepciones logísticas es el proceso de identificar y resolver problemas en la cadena de suministro, como retrasos, daños o pérdidas de mercancías.
La habilidad de agente de IA para Claude Code proporciona patrones de API de Anthropic para Python y TypeScript, cubriendo API de mensajes, transmisión, uso de herramientas y visión.
Un asistente interactivo para configurar Everything Claude Code
The deployment-patterns skill enables developers to optimize web application deployment workflows using CI/CD pipelines, Docker, and health checks, ensuring production readiness and zero downtime.
dmux-workflows es una habilidad de agente de IA que permite la orquestación de flujos de trabajo paralelos en Claude Code y otros entornos de desarrollo
The e2e-testing AI agent skill helps developers build robust end-to-end test suites using Playwright and Page Object Model, streamlining their workflow and improving productivity.
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
Patrones de pruebas de Go para escribir pruebas confiables y mantenibles siguiendo la metodología TDD
The laravel-verification skill automates environment checks, linting, static analysis, tests, and security scans for Laravel projects, benefiting developers by ensuring deployment readiness and security.
This AI agent skill provides comprehensive Perl testing patterns using Test2::V0, Test::More, and TDD methodology, helping developers ensure robust code quality and productivity.
This AI agent skill provides comprehensive Python testing strategies using pytest, TDD methodology, and best practices, helping developers write robust and maintainable code.
La herramienta de auditoría de habilidades de Claude es una habilidad de AI que analiza y mejora la calidad de las habilidades y comandos de Claude.
La compactación estratégica es una habilidad de agente de IA que sugiere la compactación manual en intervalos lógicos para mejorar la productividad
The continuous-learning skill automates pattern extraction from Claude Code sessions, saving developers time and effort. It identifies and saves useful patterns for future use, enhancing AI coding workflows.
Un patrón de frontend es un conjunto de técnicas y estrategias para construir interfaces de usuario eficientes y escalables
Búsqueda de documentación es una función que utiliza Context7 MCP para proporcionar documentación actualizada
La investigación de mercado es el proceso de recopilar y analizar datos para informar decisiones comerciales con AI Agents
RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
This AI agent skill provides best practices for safe and reversible database migrations, benefiting developers working with PostgreSQL, MySQL, and common ORMs. It helps with schema changes, data migrations, and zero-downtime deployments.
Eval Harness es un marco de evaluación para sesiones de Claude Code que permite medir la confiabilidad y el rendimiento de los agentes de AI
The laravel-security skill provides comprehensive security guidance for Laravel applications, protecting against common vulnerabilities and ensuring secure deployment. Developers benefit from AI-driven security best practices for authentication, authorization, and more.
This skill provides Nuxt 4 app patterns for hydration safety, performance, and SSR-safe data fetching, benefiting developers with optimized routing and rendering decisions.
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
The Architecture Decision Records skill helps developers capture and manage architectural decisions made during coding sessions. It auto-detects decision moments, records context, alternatives considered, and rationale, maintaining an ADR log for future reference.
Un conjunto de patrones de diseño para Compose Multiplatform y Jetpack Compose que facilitan la creación de interfaces de usuario compartidas en múltiples plataformas
This AI agent skill provides structured concurrency patterns for Android and KMP projects, enabling developers to write efficient async code with Kotlin coroutines and Flows. It benefits developers by simplifying concurrent operations and error handling.
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
La herramienta de construcción de agentes es una habilidad de IA que se utiliza para mejorar la eficiencia de los agentes de IA al diseñar y optimizar espacios de acción y formatos de observación.
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
La habilidad de agente de inteligencia artificial para ClickHouse es una capacidad que proporciona patrones de análisis y técnicas de ingeniería de datos para optimizar las consultas de ClickHouse.
Iterative Retrieval es un patrón de agente de IA que refina progresivamente la recuperación de contexto
Estándares de codificación Java para servicios Spring Boot que mejoran la legibilidad y mantenibilidad del código
La habilidad de agente de IA para JPA proporciona patrones de diseño de entidades y relaciones para mejorar la eficiencia de las aplicaciones Spring Boot
El skill de patrones de servidor Ktor para Claude Code ofrece enrutamiento DSL, autenticación, WebSockets y más para mejorar la productividad.
Patrones de PyTorch para construir modelos de aprendizaje profundo robustos y eficientes
SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.
The frontend-slides skill helps developers create engaging HTML presentations from scratch or by converting PowerPoint files, using AI-powered visual exploration for non-designers.
Un bucle continuo de agente es un patrón de diseño que permite la creación de agentes autónomos con calidad y controles de recuperación
La escritura de artículos con AI Agents es una técnica que utiliza inteligencia artificial para crear contenido escrito
The content-engine AI agent skill helps developers create strong, platform-native content systems for various platforms, adapting one idea into multiple formats. It benefits developers, marketers, and content creators by streamlining content creation and repurposing.
nanoclaw-repl es un intérprete de línea de comandos (REPL) de código abierto para operar y extender NanoClaw v2
Enterprise-agent-ops operates long-lived agent workloads with controls for runtime lifecycle, observability, and safety, benefiting developers working with AI coding assistants like Claude Code.
La habilidad de agente de IA para materiales de inversores es una capacidad que ayuda a crear y actualizar documentos para inversores de manera consistente y creíble.
La habilidad de agente de IA para Claude Code permite a los ingenieros trabajar de manera más eficiente, utilizando la ejecución eval-first y la descomposición para mejorar la productividad.
AI-first engineering is a skill that helps developers design efficient processes, architectures, and code reviews for AI-assisted code generation, improving overall team productivity and code quality.
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
Arte algorítmico es un movimiento estético computacional que se expresa a través de código.
La habilidad de agente de IA para Claude Code es una capacidad que permite a los desarrolladores crear aplicaciones potenciadas por LLM con la API de Claude o el SDK de Anthropic.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of Word doc, word document, .docx, or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads....
La habilidad MCP Builder permite crear servidores de alta calidad que habilitan a los LLM a interactuar con servicios externos a través de herramientas bien diseñadas.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
The skill-creator AI agent skill empowers developers to craft, refine, and perfect skills, streamlining AI coding workflows. It assists in creating new skills, editing existing ones, and evaluating performance for optimal results.
El skill xlsx es una capacidad que permite a los agentes de inteligencia artificial interactuar con archivos de hoja de cálculo
Nuestra habilidad de agente de IA para comunicaciones internas ayuda a escribir informes de estado, actualizaciones de liderazgo y noticias de la empresa de manera eficiente.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
La habilidad de AI Agent para PPTX permite crear y editar presentaciones de forma eficiente, incluyendo la lectura y extracción de texto, edición de plantillas y combinación de archivos.
The slack-gif-creator AI agent skill provides utilities and knowledge for creating animated GIFs optimized for Slack, helping developers create engaging animations for their teams.
La herramienta de construcción de artefactos web es una suite de herramientas para crear artefactos web complejos utilizando tecnologías de frontend modernas como React y Tailwind CSS.
La habilidad de diseño de canvas es una capacidad de agente de IA que crea arte visual en documentos .png y .pdf.
La co-autoría de documentos es una habilidad de agente de IA que proporciona un flujo de trabajo estructurado para la creación colaborativa de documentos
La habilidad de diseño frontend es una capacidad que permite a los agentes de IA crear interfaces de usuario atractivas y funcionales para componentes web, páginas y aplicaciones.
La habilidad brand-guidelines es una herramienta de agente de IA que aplica los colores y la tipografía oficiales de Anthropics a cualquier artefacto.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Subagent-driven development automates independent tasks using fresh subagents, ensuring high-quality results and fast iteration for developers. It streamlines AI coding workflows.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when implementing any feature or bugfix, before writing implementation code
Use when you have a spec or requirements for a multi-step task, before touching code
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Esta habilidad de agente de IA para Claude Code te permite recibir y responder a la revisión de código de manera efectiva, verificando la precisión técnica y evitando la implementación ciega
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
La revisión de código es el proceso de evaluar y mejorar la calidad del código
La habilidad de ejecución de planes permite a los agentes de IA cargar, revisar y ejecutar planes de implementación de forma eficiente.
Transformers.js permite ejecutar modelos de aprendizaje automático de última generación directamente en JavaScript. Soporta tareas de NLP, visión por computadora y audio.
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
This skill enables running Python workloads on Hugging Face cloud infrastructure, ideal for developers. It handles data processing, batch inference, experiments, and model training without requiring local GPU/TPU setup.
Un entrenador de modelos de lenguaje que utiliza TRL en la infraestructura de Hugging Face Jobs.
The huggingface-paper-publisher skill provides comprehensive tools for AI engineers and researchers to publish, manage, and link research papers on Hugging Face Hub, streamlining workflow and enhancing collaboration.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs...
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
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.
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
The Hugging Face Papers skill enables developers to look up and read AI research papers in markdown, and access structured metadata such as authors and linked models. This skill benefits developers and researchers by providing easy access to AI research insights.
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
This skill enables developers to test Hugging Face models locally, streamlining backend selection and model comparisons. It supports inspect-ai and lighteval for efficient evaluations.
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
La habilidad de Hugging Face Datasets para Claude Code permite la exploración y extracción de datos de forma eficiente. Utiliza la API de Dataset Viewer para fetch subset/split metadata, paginar filas, buscar texto y aplicar filtros.
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.
The design-md skill analyzes Stitch projects, synthesizing a semantic design system into DESIGN.md files, benefiting developers by streamlining design workflows with AI coding.
shadcn-ui es una colección de componentes reutilizables para aplicaciones web
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
Stitch Loop is an AI agent skill that enables autonomous frontend builders to iteratively develop websites using Stitch. It integrates pages into site structures and prepares instructions for the next iteration, streamlining AI coding workflows for developers.
Stitch Design es una herramienta de diseño de sistemas de diseño que ayuda a los desarrolladores a crear diseños de UI de alta fidelidad
Remotion es una herramienta de generación de video programática
The react:components skill transforms Stitch designs into clean, modular React code using system-level networking and AST-based validation, helping frontend engineers streamline their workflow.
Nuestra habilidad de análisis de rendimiento web utiliza Chrome DevTools MCP para medir los vitales web centrales y identificar problemas de rendimiento
Un agente de inteligencia artificial en Cloudflare es un programa que utiliza el SDK de Agents para automatizar tareas y procesos en la plataforma.
Un servidor MCP en Cloudflare es una integración del SDK de MCP con Workers de Cloudflare.
Sandbox-sdk es una habilidad de agente de AI que proporciona un entorno de ejecución de código seguro y aislado.
Durable Objects es una habilidad de agente de inteligencia artificial que permite crear y revisar objetos duraderos en Cloudflare para aplicaciones estatales y coordinadas.
La habilidad de agente de IA para mejores prácticas de Cloudflare Workers ayuda a los desarrolladores a escribir y revisar código de manera eficiente
La habilidad del agente AI Wrangler para Claude Code permite a los desarrolladores implementar y gestionar Workers en Cloudflare de manera eficiente.
La habilidad de agente de inteligencia artificial para Cloudflare es una plataforma integral que permite a los desarrolladores crear aplicaciones escalables y seguras
The Cloudflare Agents SDK enables developers to build stateful AI agents, durable workflows, and real-time WebSocket applications. It provides a range of capabilities, including persistent state, callable RPC, and scheduling.
The backend-code-review skill reviews Python code for quality, security, and maintainability, providing actionable fixes and suggestions. It benefits developers by improving their code and workflow.
La refactorización de componentes es una técnica para simplificar y optimizar componentes de software complejos.
Esta habilidad de agente de inteligencia artificial permite a Claude generar pruebas de frontend de alta calidad para el proyecto Dify
Guide for implementing oRPC contract-first API patterns in Dify frontend. Trigger when creating or updating contracts in web/contract, wiring router composition, integrating TanStack Query with typed contracts, migrating legacy service calls to oRPC, or deciding whether to call queryOptions directly vs extracting a helper or use-* hook in web/service.
This frontend-code-review skill reviews frontend files, such as .tsx, .ts, and .js, and applies a checklist to ensure code quality, performance, and business logic, helping developers and teams maintain high standards.
Un patrón de consulta y mutación frontend que utiliza TanStack Query y oRPC para crear contratos en web/contract
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
La revisión de seguridad es una habilidad de agente AI que analiza el código para detectar vulnerabilidades de seguridad y proporcionar informes de confianza.
Un analizador de seguridad de habilidades de agentes de IA que detecta vulnerabilidades de seguridad
Warden skill: evaluates first-pass findings and proposes deterministic lint rules that could permanently catch the same patterns. Requires Wardens multi-pass pipeline (phase 2).
Esta habilidad de agente de AI ayuda a crear y mantener la documentación de AGENTS.md, aplicando las mejores prácticas para mantener la documentación concisa y de alta calidad.
La revisión de rendimiento de Django es el proceso de identificar y solucionar problemas de rendimiento en aplicaciones Django.
La herramienta de escritura de solicitudes de extracción para Claude Code ayuda a crear solicitudes de extracción siguiendo las convenciones de Sentry. Automatice la creación de PR con esta habilidad de agente de IA.
Un skill de commit es una herramienta que ayuda a los desarrolladores a crear mensajes de commit coherentes y consistentes
La habilidad de agente de IA para crear presentaciones de datos con React, Vite y Recharts.
Un agente de simplificación de código es una herramienta que mejora la claridad y mantenibilidad del código
Este agente AI organiza proyectos en formato SRED para su presentación, conectando con Notion, Linear y Github para generar un documento listo.
Un AI Agent Skill que aplica las pautas de marca de Sentry para crear contenido de usuario
GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to review GitHub Actions, audit workflows, check CI security, GHA security, workflow security review, or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain at...
Find-bugs es una habilidad de agente de IA que revisa cambios de ramas locales para detectar errores y problemas de seguridad.
La habilidad de escritura de agentes de IA es una capacidad que permite crear y mejorar habilidades de agentes de IA
The code-review skill performs automated code reviews based on Sentry engineering practices, helping developers improve code quality and security. It assists with identifying runtime errors, performance issues, and security vulnerabilities.
La habilidad de agente AI de revisión de control de acceso de Django ayuda a identificar vulnerabilidades de IDOR y a proteger la autorización de usuario
Iterate-pr es una herramienta de automatización que itera en una PR hasta que todos los controles de CI pasen
Go back through the previous year of work and create a Notion doc that groups relevant links into projects that can then be documented as SRED projects.
La habilidad de agente de IA 'create-branch' es una función que automatiza la creación de ramas Git siguiendo las convenciones de nombramiento de Sentry.
La habilidad de revisión de GitHub es una función de agente AI que recupera notificaciones de revisión para solicitudes de revisión abiertas en GitHub
The doc-coauthoring AI agent skill provides a structured workflow for collaborative document creation, benefiting developers and writers. It helps ensure efficient context transfer and refined content through a three-stage process.
The blog-writing-guide skill helps developers create high-quality technical blog posts for the Sentry engineering blog, following specific writing standards and voice. It assists in writing, reviewing, and improving content for a developer audience.
Create-pr es un skill que permite crear y editar solicitudes de extracción de manera eficiente
The skill-creator AI agent skill redirects to the canonical sentry-skills:skill-writer workflow, enabling developers to create and update skills efficiently with AI coding.
Helps users discover and install agent skills when they ask questions like how do I do X, find a skill for X, is there a skill that can..., or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
The create-skill AI agent skill automates workflows and integrates APIs for Claude Code, enhancing developer productivity. It teaches the agent focused workflows, leveraging markdown and optional scripts.
La habilidad de agente de IA 'create-pr' crea solicitudes de extracción de GitHub con títulos formateados correctamente que pasan la validación de CI
Fetch and display the full transcript from a Loom video URL. Use when the user wants to get or read a Loom transcript.
Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input.
Used to download images/attachments. Typically pre-installed.
Required for creating GitHub issues. Must be authenticated (gh auth login)
Quick reference for n8n patterns. Full docs /AGENTS.md
>
El desarrollo basado en especificaciones permite una integración más eficiente de APIs y flujos de datos
Do not reset back to the generic directory. Move sideways through these adjacent high-intent collections to narrow the shortlist toward the install path that best matches your team.
A workflow-first collection that explains why related skills belong together and what job they solve.
Workflow collections add first-party judgment that generic skill detail pages struggle to communicate.
A platform-specific collection for one of the clearest demand clusters in the product ecosystem.
Platform collections let the site recover with narrower, more trustworthy topical intent.
A clean surface for editor-specific demand with explicit workflow intent.
Editor-specific demand should land on curated surfaces, not random repo coverage.
A platform collection that turns IDE demand into a stronger curated hub.
The more specific the editor intent, the more important curated selection becomes.
This collection should not keep users browsing forever. These three questions explain how to shortlist, install, and validate the next step.
Estas colecciones están diseñadas para automatización de flujos, procesos, documentos, datos y pilas de habilidades reutilizables.
El directorio es mejor para búsqueda directa, mientras las colecciones ayudan a encontrar habilidades complementarias agrupadas por flujo completo.
Sí. Las habilidades de estas colecciones generalmente funcionan en Claude Code, Cursor, Windsurf y otros entornos mediante instalación unificada.
These are the supporting surfaces for this collection after the install direction is clear and the primary next paths have already narrowed the decision.
A use-case page for users searching for repeatable automation patterns instead of one-off tools.
Workflow automation demand is easier to satisfy with curated intent clusters than with flat directory coverage.
A workflow-first collection that explains why related skills belong together and what job they solve.
Workflow collections add first-party judgment that generic skill detail pages struggle to communicate.