huggingface-hub

Manage Hugging Face Hub models and datasets via the hf CLI.

Updated May 13, 2026
One-click install
npx skills add https://github.com/skkeoriw/hermes-brain --skill huggingface-hub-skkeoriw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/skkeoriw/hermes-brain/tree/main/brain/hermes-home/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/skkeoriw/hermes-brain --skill huggingface-hub-skkeoriw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires hf, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines the process of interacting with the Hugging Face Hub, allowing users to efficiently search, download, upload, and manage models and datasets.

Core Features & Use Cases

  • Model and Dataset Management: Search, download, upload, and manage models and datasets from the Hugging Face Hub.
  • Authentication: Manage sessions and access tokens.
  • Repository Management: Create, delete, duplicate, move, branch, tag, and delete files in repositories.
  • Use Case: Quickly download a specific model or dataset from the Hub without navigating through the web interface.

Quick Start

Use the huggingface-hub skill to download the 'transformers' model with the command 'hf download transformers'.

Frequently Asked Questions about huggingface-hub

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download a model or dataset from the Hugging Face Hub via command line?

To download a Hugging Face Hub model or dataset, use the command 'hf download' followed by the repository name. This executes a direct command-line operation, retrieving files efficiently without navigating the web interface.

Can I manage Hugging Face repository branches and tags using the CLI?

Yes, you can manage Hugging Face repository branches and tags using the CLI. The Skill supports creating, deleting, duplicating, moving, and tagging repositories, allowing complete version control over your models and datasets directly from the command line.

Do I need a Hugging Face account to upload models and datasets?

Yes, uploading models and datasets requires a Hugging Face account. The Skill manages authentication sessions and access tokens to securely authorize repository modifications and uploads through the command line interface.

What is the best way to automate Hugging Face Hub interactions in Python?

The best way to automate Hugging Face Hub interactions in Python is by using the hf CLI within scripts. This Skill supports Python-based automation for searching, downloading, and managing models and datasets, integrating seamlessly with other tools.

Does the Hugging Face Hub CLI require internet access for repository management?

Yes, Hugging Face Hub repository management requires internet access. All operations, including searching, downloading, uploading, and managing models and datasets, communicate directly with the Hub's remote servers.

Can I search for specific models and datasets on the Hugging Face Hub without using the website?

Yes, you can search for specific models and datasets on the Hugging Face Hub without the website. The Skill utilizes the hf CLI to perform command-line searches, returning available models and datasets directly in your terminal.