Absortio

Email → Summary → Bookmark → Email

Add New Weekly Statistics About
← Back to list
Previous Next

GitHub - huggingface/skills

https://github.com/huggingface/skills • Feb 27, 2026 20:47

Extracto

Contribute to huggingface/skills development by creating an account on GitHub.

Resumen

Resumen Principal

Las Hugging Face Skills representan una innovadora estandarización para definir tareas de IA/ML, como la creación de conjuntos de datos, el entrenamiento y la evaluación de modelos. Estas habilidades son fundamentalmente interoperables con las principales herramientas de agentes de codificación, incluyendo OpenAI Codex, Anthropic Claude Code, Google DeepMind Gemini CLI y Cursor, adhiriéndose al formato estandarizado Agent Skill format. En la práctica, cada skill es una carpeta auto-contenida que encapsula instrucciones, scripts y recursos, permitiendo a un agente de IA abordar un caso de uso específico de manera eficiente. Esta aproximación modular y universal facilita enormemente la automatización y la gestión de flujos de trabajo complejos en el ecosistema de IA, proveyendo una capa de abstracción que unifica la interacción entre los desarrolladores y las diversas plataformas de agentes, garantizando una ejecución consistente y replicable de tareas de machine learning.

Elementos Clave

  • Interoperabilidad Universal: Las Hugging Face Skills están diseñadas para ser compatibles con un amplio espectro de herramientas de agentes de codificación líderes. Aunque cada herramienta puede utilizar una terminología diferente (por ejemplo, 'skills' en Anthropic, 'Agent Skills' en OpenAI Codex, 'extensions' en Google Gemini), este repositorio unifica la implementación, garantizando que un conjunto de instrucciones pueda ser entendido y ejecutado por cualquiera de estos agentes. Esto elimina barreras de compatibilidad y promueve un ecosistema de desarrollo más integrado.
  • Mecanismo de Funcionamiento Estructurado: Cada skill se materializa como una carpeta independiente que organiza un archivo SKILL.md, el cual incluye YAML frontmatter (nombre y descripción) y las directrices que el agente de codificación debe seguir. Complementariamente, estas carpetas pueden contener scripts auxiliares, plantillas y otros recursos necesarios para la ejecución de la tarea. Este diseño modular asegura que cada habilidad sea autosuficiente y fácilmente reutilizable o personalizable.
  • Proceso de Instalación y Activación Fluido: La integración de las skills varía según la herramienta, pero se simplifica mediante comandos específicos (como /plugin install <skill-name> para Claude Code, copiar archivos a directorios .agents/skills para Codex, o gemini extensions install . para Gemini CLI). Una vez instalada, un agente puede invocar la skill mencionándola directamente en las instrucciones, lo que desencadena la carga automática de las directrices de SKILL.md y los scripts asociados para completar la tarea.
  • Diversidad de Habilidades Especializadas: El repositorio ofrece un conjunto inicial de habilidades que cubren un amplio rango de operaciones críticas en el ciclo de vida de ML. Ejemplos incluyen gradio para construir UIs, hugging-face-cli para operaciones de Hub, hugging-face-datasets para gestión de datos, hugging-face-evaluation para resultados de evaluación, hugging-face-model-trainer para entrenamiento de modelos, hugging-face-paper-publisher para gestión de publicaciones científicas y hugging-face-trackio para seguimiento de experimentos, demostrando la versatilidad y aplicabilidad práctica de este enfoque.

Análisis e Implicaciones

Este marco de Hugging Face Skills tiene profundas implicaciones para la eficiencia en el desarrollo de IA, al permitir la automatización de tareas complejas mediante instrucciones de lenguaje natural. Fomenta un ecosistema más cohesivo y productivo para los desarrolladores de IA, acelerando la iteración y el despliegue de modelos y aplicaciones.

Contexto Adicional

Los usuarios también tienen la capacidad de contribuir o personalizar habilidades existentes, enriqueciendo continuamente la biblioteca disponible, y el archivo marketplace.json facilita la navegación humana por las skills disponibles.

Contenido

Hugging Face Skills

Hugging Face Skills are definitions for AI/ML tasks like dataset creation, model training, and evaluation. They are interoperable with all major coding agent tools like OpenAI Codex, Anthropic's Claude Code, Google DeepMind's Gemini CLI, and Cursor.

The Skills in this repository follow the standardized format Agent Skill format.

How do Skills work?

In practice, skills are self-contained folders that package instructions, scripts, and resources together for an AI agent to use on a specific use case. Each folder includes a SKILL.md file with YAML frontmatter (name and description) followed by the guidance your coding agent follows while the skill is active.

Note

'Skills' is actually an Anthropic term used within Claude AI and Claude Code and not adopted by other agent tools, but we love it! OpenAI Codex uses the open Agent Skills format, where each skill is a directory with a SKILL.md file that Codex discovers from standard .agents/skills locations documented in the Codex Skills guide. Codex can also work with an AGENTS.md file. Google Gemini uses 'extensions' to define the instructions for your coding agent in a gemini-extension.json file. This repo is compatible with all of them, and more!

Tip

If your agent doesn't support skills, you can use agents/AGENTS.md directly as a fallback.

Installation

Hugging Face skills are compatible with Claude Code, Codex, Gemini CLI, and Cursor.

Claude Code

  1. Register the repository as a plugin marketplace:
/plugin marketplace add huggingface/skills
  1. To install a skill, run:
/plugin install <skill-name>@huggingface/skills

For example:

/plugin install hugging-face-cli@huggingface/skills

Codex

  1. Copy or symlink any skills you want to use from this repository's skills/ directory into one of Codex's standard .agents/skills locations (for example, $REPO_ROOT/.agents/skills or $HOME/.agents/skills) as described in the Codex Skills guide.

  2. Once a skill is available in one of those locations, Codex will discover it using the Agent Skills standard and load the SKILL.md instructions when it decides to use that skill or when you explicitly invoke it.

  3. If your Codex setup still relies on AGENTS.md, you can use the generated agents/AGENTS.md file in this repo as a fallback bundle of instructions.

Gemini CLI

  1. This repo includes gemini-extension.json to integrate with the Gemini CLI.

  2. Install locally:

gemini extensions install . --consent

or use the GitHub URL:

gemini extensions install https://github.com/huggingface/skills.git --consent
  1. See Gemini CLI extensions docs for more help.

Cursor

This repository includes Cursor plugin manifests:

  • .cursor-plugin/plugin.json
  • .mcp.json (configured with the Hugging Face MCP server URL)

Install from repository URL (or local checkout) via the Cursor plugin flow.

For contributors, regenerate manifests with:

Skills

This repository contains a few skills to get you started. You can also contribute your own skills to the repository.

Available skills

Name Description Documentation
gradio Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots. SKILL.md
hugging-face-cli Execute Hugging Face Hub operations using the hf CLI. Download models/datasets, upload files, manage repos, and run cloud compute jobs. SKILL.md
hugging-face-datasets Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. SKILL.md
hugging-face-evaluation 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 evaluations with vLLM/lighteval. SKILL.md
hugging-face-jobs Run compute jobs on Hugging Face infrastructure. Execute Python scripts, manage scheduled jobs, and monitor job status. SKILL.md
hugging-face-model-trainer Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes hardware selection, cost estimation, Trackio monitoring, and Hub persistence. SKILL.md
hugging-face-paper-publisher 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. SKILL.md
hugging-face-tool-builder Build reusable scripts for Hugging Face API operations. Useful for chaining API calls or automating repeated tasks. SKILL.md
hugging-face-trackio Track and visualize ML training experiments with Trackio. Log metrics via Python API and retrieve them via CLI. Supports real-time dashboards synced to HF Spaces. SKILL.md

Using skills in your coding agent

Once a skill is installed, mention it directly while giving your coding agent instructions:

  • "Use the HF LLM trainer skill to estimate the GPU memory needed for a 70B model run."
  • "Use the HF model evaluation skill to launch run_eval_job.py on the latest checkpoint."
  • "Use the HF dataset creator skill to draft new few-shot classification templates."
  • "Use the HF paper publisher skill to index my arXiv paper and link it to my model."

Your coding agent automatically loads the corresponding SKILL.md instructions and helper scripts while it completes the task.

Contribute or customize a skill

  1. Copy one of the existing skill folders (for example, hf-datasets/) and rename it.
  2. Update the new folder's SKILL.md frontmatter: 
    ---
name: my-skill-name
description: Describe what the skill does and when to use it
---

# Skill Title
Guidance + examples + guardrails
  3. Add or edit supporting scripts, templates, and documents referenced by your instructions.
  4. Add an entry to .claude-plugin/marketplace.json with a concise, human-readable description.
  5. Run: to regenerate and validate all generated metadata.
  6. Reinstall or reload the skill bundle in your coding agent so the updated folder is available.

Marketplace

The .claude-plugin/marketplace.json file lists skills with human-readable descriptions for the plugin marketplace. The CI validates that skill names and paths match between SKILL.md files and marketplace.json, but descriptions are maintained separately: SKILL.md descriptions guide when Claude activates the skill, while marketplace descriptions are written for humans browsing available skills.

Additional references

  • Browse the latest instructions, scripts, and templates directly at huggingface/skills.
  • Review Hugging Face documentation for the specific libraries or workflows you reference inside each skill.

Fuente: GitHub