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
24
Categorías
9
Herramientas compatibles
5
Colaboradores
1
Mostrando 1–21 de 24 Skills
Turns merged work, pull requests, issues, and user-visible behavior changes into accurate, audience-specific release notes with breaking-change and upgrade guidance.
Designs trustworthy product analytics events, properties, identity rules, validation, privacy boundaries, dashboards, and governance for product and growth decisions.
Designs reliable JSON and typed outputs for LLM features, including schemas, validation, recovery paths, versioning, examples, and contracts for downstream consumers.
Convierte un repositorio desconocido en una guía de ingeniería concisa que explica la arquitectura, las convenciones, la configuración local, las rutas de ejecución principales y las primeras contribuciones de bajo riesgo.
Audita interfaces de producto según requisitos prácticos de accesibilidad, incluidos la estructura semántica, el acceso mediante teclado, el comportamiento del foco, el contraste de color, los lectores de pantalla y los formularios.
Sets up and maintains Git hooks for a repository. Recommends a manager (Husky, Lefthook, or pre-commit), wires up pre-commit and commit-msg hooks for linting, formatting, type checks, secret scanning, and conventional-commit validation, and keeps hooks fast with staged-file filtering. Produces config plus a short contributor guide.
Builds robust webhook producers and consumers. Covers signature verification, idempotency keys, retry with exponential backoff, dead-letter handling, event ordering, and replay endpoints, and generates handler code plus tests so integrations survive duplicates and outages.
Diagnoses and fixes flaky tests by analyzing test code and CI failure history for common sources of nondeterminism such as time and timezone dependence, order dependence, shared mutable state, race conditions, and unmocked network calls. Proposes targeted fixes and quarantine strategies to keep the suite trustworthy.
Generates mobile application prototypes and implementations for iOS and Android. Creates SwiftUI views, Jetpack Compose layouts, and React Native components from descriptions or wireframe images. Handles navigation patterns, state management, and platform-specific design guidelines.
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.
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 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 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.
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.
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 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.
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.
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.