hugging-face-cli

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

1|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/FacuM/yolo-agent --skill hugging-face-cli-facum
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-cli
Source: https://github.com/FacuM/yolo-agent/tree/main/.claude/skills/hugging-face-cli
Command: npx skills add https://github.com/FacuM/yolo-agent --skill hugging-face-cli-facum

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines your interaction with the Hugging Face Hub, allowing you to manage models, datasets, and spaces directly from your terminal without navigating the website.

Core Features & Use Cases

  • Download/Upload: Effortlessly download models, datasets, and spaces to your local machine or upload your own creations to the Hub.
  • Repository Management: Create, delete, and manage repositories, branches, and tags.
  • Cache Operations: Efficiently manage your local Hugging Face cache.
  • Cloud Compute: Run jobs on Hugging Face's infrastructure.
  • Use Case: You need to download a specific model checkpoint for fine-tuning. Use this Skill to quickly download the required files and manage your local cache.

Quick Start

Use the hugging-face-cli skill to download the 'gpt2' model to your local directory.

Frequently Asked Questions about hugging-face-cli

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

FAQPage Schema
How do I download models from the Hugging Face Hub using the command line?

You can download models from the Hugging Face Hub by using the `hf` CLI tool to fetch required files directly to your local directory. This allows you to quickly retrieve specific model checkpoints for tasks like fine-tuning.

Can I manage Hugging Face repository branches and tags from my terminal?

Yes, you can manage Hugging Face repositories from your terminal by creating, deleting, and handling branches and tags. This eliminates the need to navigate the website for repository management tasks.

What is the best way to upload datasets to the Hugging Face Hub without using the website?

The best way to upload datasets to the Hugging Face Hub without the website is using the `hf` CLI tool. It enables you to upload your datasets directly from the terminal to your Hub repository.

How do I clear and manage my local Hugging Face cache?

You can manage your local Hugging Face cache by executing cache operations through the `hf` CLI tool. This functionality helps you efficiently handle downloaded files and free up local storage.

Does the Hugging Face CLI support running cloud compute jobs?

Yes, the Hugging Face CLI supports running cloud compute jobs. You can execute jobs directly on Hugging Face's infrastructure using the command-line interface.

Why use a command line interface for Hugging Face Hub operations instead of the web interface?

Using a command line interface for Hugging Face Hub operations streamlines your workflow by allowing direct terminal management of models, datasets, and spaces. This avoids browser navigation and enables quick local downloads or uploads.