Skills
El registro abierto de Skills para agentes de IA: prompts estructurados y flujos de trabajo con modelos recomendados, ejemplos y herramientas compatibles.
Algunas descripciones forman parte del piloto de traducción automática y aún no han sido revisadas.
Skills
100
Categorías
9
Herramientas compatibles
7
Colaboradores
2
Mostrando 85–100 de 100 Skills
Audits project dependencies for security vulnerabilities, license compliance, maintenance status, and bundle size impact. Identifies outdated packages, suggests alternatives for abandoned libraries, and flags risky transitive dependencies.
Analyzes and resolves git merge conflicts by understanding the intent of both sides. Examines the conflict markers, surrounding context, and commit history to produce a correct merged result that preserves both changes without breaking functionality.
Generates production-ready React components with TypeScript, proper props interfaces, accessibility attributes, responsive design, and test files. Follows modern patterns including Server Components, Suspense boundaries, and composition over inheritance.
Generates TypeScript type definitions from various sources — JSON data, API responses, database schemas, or plain descriptions. Produces strict types with proper generics, utility types, discriminated unions, and JSDoc comments.
Summarizes research papers, technical articles, and documentation into structured briefs. Extracts key findings, methodology, limitations, and practical implications. Adapts output format from executive summary to detailed technical breakdown.
Designs and implements comprehensive error handling for APIs. Covers error response formats (RFC 7807 Problem Details), HTTP status code selection, error logging strategies, retry logic, and client-friendly error messages with proper i18n support.
Generates Docker Compose configurations from application requirements. Handles service dependencies, networking, volumes, health checks, environment variables, and multi-stage builds. Supports development and production profiles.
Generates complete OpenAPI 3.1 specifications from API descriptions, existing code, or route definitions. Includes request/response schemas, authentication, error responses, examples, and server configurations. Produces valid YAML ready for Swagger UI.
Reviews web interfaces for WCAG 2.1 AA compliance. Identifies accessibility barriers including missing ARIA attributes, keyboard navigation issues, color contrast problems, and screen reader incompatibilities. Provides remediation code with proper semantic HTML.
Designs and implements CI/CD pipelines for various platforms (GitHub Actions, GitLab CI, Jenkins, CircleCI). Covers build, test, lint, security scan, deploy stages with proper caching, parallelization, and environment management.
Generates comprehensive unit tests for existing code, covering happy paths, edge cases, error conditions, and boundary values. Follows testing best practices including the test pyramid, DAMP over DRY, and the Arrange-Act-Assert pattern. Adapts to the project's existing test framework and conventions.
Generates comprehensive documentation from code including API references, README files, architecture decision records (ADRs), inline comments, and user guides. Adapts tone and detail level to the target audience (developers, end-users, stakeholders).
Generates optimized SQL queries from natural language descriptions. Supports multiple dialects (PostgreSQL, MySQL, SQLite, SQL Server), handles complex joins, subqueries, window functions, and CTEs. Includes query explanation and performance optimization hints.
Analyzes datasets to extract insights, identify patterns, and generate visualizations. Supports exploratory data analysis (EDA), statistical testing, trend detection, and report generation. Works with CSV, JSON, and database outputs.
Systematic debugging workflow that helps identify, isolate, and fix bugs. Follows a structured approach: reproduce, localize, reduce, fix, guard. Analyzes error messages, stack traces, and logs to pinpoint root causes rather than symptoms.
Revisión automatizada de código que ofrece comentarios aplicables sobre calidad, posibles errores, problemas de rendimiento, vulnerabilidades de seguridad e incumplimientos de estilo. Analiza los cambios con el rigor de un ingeniero sénior y aporta sugerencias concretas con ejemplos de código.
Skills frente a servidores MCP
¿cuál es la diferencia?Skillsel «qué hacer»
Una Skill reúne conocimientos prácticos —instrucciones, un prompt de ejemplo y modelos recomendados— para que un agente realice una tarea de forma consistente. Las Skills aportan conocimiento, no nuevas conexiones.
Servidores MCPel «cómo conectarse»
Un servidor MCP proporciona nuevas capacidades a un agente conectándolo con sistemas reales —bases de datos, API o archivos— mediante un transporte. MCP añade conexiones y acciones, no instrucciones de tarea.
Regla práctica: usa una Skill cuando necesites que el modelo realice bien una tarea y un servidor MCP cuando necesites conectarlo con una herramienta o sistema. Se complementan: una Skill puede utilizar las herramientas que proporciona un servidor MCP.
¿Has creado una Skill útil?
Envía un archivo SKILL.md: es de código abierto y está mantenido por la comunidad.