Paquetes de plugins
Nuestro recorrido del contó 2 708 paquetes de plugins en los marketplaces que leemos, en 3 105 fichas. 22 aparecieron en los últimos 7 días y 0 se fueron en los últimos 30. El líder por Estrellas (GitHub) es superpowers, con 298 mil.
Los más populares
Ordenados por Estrellas (GitHub), la cifra que publica este marketplace. Las cifras de distintos marketplaces nunca se suman.
-
Superpowers teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging, and red/green TDD. Additionally, it teaches Claude how to…
Estrellas en GitHub: 297 609 -
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Estrellas en GitHub: 285 737 -
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Estrellas en GitHub: 161 091 -
Auto-activation works differently per agent: Claude Code uses SessionStart hooks, this repo's Codex dogfood setup uses .codex/hooks.json, Gemini uses context files…
Estrellas en GitHub: 111 029 -
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Estrellas en GitHub: 99 711 -
Understand Anything is a Claude Code plugin that analyzes your project with a multi-agent pipeline, builds a knowledge graph of every file, function, class, and dependency, then…
Estrellas en GitHub: 85 924 -
Great design prompts require design vocabulary. Most people don't have it. You can't ask for "more vertical rhythm" if you've never used those words. Impeccable gives you commands…
Estrellas en GitHub: 79 844 -
Connect Mem0 to Claude to give your agent persistent memory across sessions. Claude can store user preferences, project context, and conversation history, then search, update, or…
Estrellas en GitHub: 66 990 -
last-30-days is a Claude Code skill that searches the web and delivers a structured 30-day digest on any topic you choose. Simply ask Claude about a subject and it will run…
Estrellas en GitHub: 63 970 -
Estrellas en GitHub: 54 186
-
AI-powered Draw.io diagram generation with real-time browser preview. Create flowcharts, architecture diagrams, and more through natural language.
Estrellas en GitHub: 36 172 -
Real-time statusline HUD for Claude Code - context health, tool activity, agent tracking, and todo progress
Estrellas en GitHub: 28 461 -
Playwright Pro turns your AI coding agent into a senior test automation engineer. Instead of generating tutorial-quality tests with brittle CSS selectors, Playwright Pro enforces…
Estrellas en GitHub: 28 021 -
MCP is the protocol for tool access. We're the virtualization layer for context.
Estrellas en GitHub: 26 639 -
Teaches AI coding agents to create and maintain promptfoo eval suites. Encodes best practices like deterministic assertions first, file-based test organization, correct…
Estrellas en GitHub: 25 902 -
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
Estrellas en GitHub: 18 741 -
Comprehensive SEO analysis plugin for Claude Code. Performs full site audits with 11 parallel subagents and 0-100 health scoring across technical SEO (crawlability, indexability…
Estrellas en GitHub: 18 700 -
Open-source browser agent driven via CDP — direct browser control, 79K stars, YC W25. browser-harness gives Claude Code direct, low-level control of a real Chrome browser via the…
Estrellas en GitHub: 18 391 -
66 specialized skills for full-stack development: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6…
Estrellas en GitHub: 11 827 -
Build, train, evaluate, and use open source AI models, datasets, and spaces.
Estrellas en GitHub: 11 157
Nuevos en los últimos 30 días
-
Create and retrieve from a Foundry IQ knowledge base using File, Azure Blob, or ADLS Gen2, then connect an existing Prompt or Hosted Agent.
-
Azure Local skills covering standard deployments (Azure Stack HCI, 1-16 node hyperconverged, rack-aware clusters) and multi-rack (rack scale) deployments built on Network Fabric…
-
Kusto graph analysis, IRQL security hunting pipelines, and graph visualization skills for Azure Data Explorer.
-
Azure cost analysis, estimation, optimization, and governance workflows backed by Azure Resource Manager MCP.
-
AKS operational skills for troubleshooting, known issues, GPU inference, and packet capture.
-
Experimental Expo skills for APIs that are not finalized. Skills graduate to the expo plugin when stable.
-
Run growth marketing, SEO and AI answer-engine visibility for a product through AfterLaunch over MCP. Reads a ranked backlog of prepared, ready-to-ship growth moves.
-
The Rokha MCP server plus the first-party skills: find a capability, run it, keep the trace.
-
YouTube outlier finder and competitor research. Ranks a channel's recent uploads and Shorts by how far each beat that channel's own baseline views, compares channels, and sweeps a…
-
Deterministic decision capture + pre-task veto warnings from your self-hosted RoBrain stack
Qué suelen ejecutar y pedir estos plugins
- Se ejecutan en un servidor remoto
- 14% Proporción de plugins con un endpoint remoto: la herramienta de IA habla con un servidor en internet.
- Se ejecutan en tu equipo
- 5% Proporción de plugins que la herramienta de IA inicia localmente, como paquete o comando local.
- Mediana de secretos pedidos
- 0,0 La mitad de los plugins de aquí pide esta cantidad de ajustes secretos (claves de API, tokens) o menos, según los declaran sus marketplaces.
- Paquetes con hooks
- 23% Proporción de paquetes de plugins que ejecutan hooks de shell ante eventos de la herramienta de IA.
Contado sobre los plugins activos de esta página. Las proporciones y medianas se indican solo para grupos de al menos 20 plugins; describen declaraciones, no una revisión de seguridad.
Dónde se publican
Cuántos de estos plugins publica cada marketplace. Un plugin puede estar en varios, así que las líneas no suman el total.
Las filas proceden de nuestros últimos recorridos por los marketplaces. Un plugin publicado en varios marketplaces es una fila, con la cifra del marketplace por el que se ordena la lista. Las cifras de GitHub ordenan un plugin solo cuando su repositorio no contiene otro plugin que sigamos; la cifra de un repositorio compartido se muestra como la de todo el repositorio y no ordena.
Todos los plugins para herramientas de IA · Estadísticas de plugins para herramientas de IA
Datos de Copilot CLI: github/awesome-copilot. Datos de Claude Code: claude-plugins-community. Datos de Claude Code: claude-plugins-official. Datos de Community GitHub marketplaces. Datos de Copilot CLI: github/copilot-plugins. Datos de Cursor: cursor/plugins. Datos de Docker MCP Catalog. Datos de Claude: knowledge-work-plugins. Datos de Official MCP Registry. Datos de Codex: openai-curated (openai/plugins). . No publicamos datos de contacto de los editores de plugins.
De dónde salen los datos: cómo se elabora el catálogo