hf-cli

Manage Hugging Face Hub resources with the `hf` command-line tool.

1|Updated Jan 6, 2026
One-click install
npx skills add https://github.com/zichdan/FASHIONISTAR_ANTAGRAVITY --skill hf-cli-zichdan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hf-cli
Source: https://github.com/zichdan/FASHIONISTAR_ANTAGRAVITY/tree/main/.agents/skills/hf-cli
Command: npx skills add https://github.com/zichdan/FASHIONISTAR_ANTAGRAVITY --skill hf-cli-zichdan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires huggingface_hub, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the complex processes of managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub, making AI and ML workflows more accessible and efficient.

Core Features & Use Cases

  • Centralized Management: Handle authentication, manage local cache, manage Hugging Face Buckets, run or schedule jobs on Hugging Face infrastructure, manage Hugging Face repos, and much more with a single command.
  • Comprehensive Functionality: Offers a wide array of commands like downloading, uploading, syncing, authenticating, and more.
  • Use Case: For a researcher who wants to manage their datasets and models on the Hugging Face Hub, the hf-cli Skill simplifies this process with a unified command interface.

Quick Start

Install the Hugging Face Hub CLI tool hf by running curl -LsSf https://hf.co/cli/install.sh | bash -s. Use hf --help to explore available commands.

Frequently Asked Questions about hf-cli

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

FAQPage Schema
How do I manage Hugging Face Hub models and datasets from the command line?

The Hugging Face CLI tool provides a unified command interface to download, upload, and authenticate models, datasets, and spaces. It consolidates complex Hub management tasks into a single streamlined command-line workflow.

Can I schedule jobs and manage Hugging Face Spaces through a CLI?

Yes, you can schedule jobs and manage Hugging Face Spaces through a CLI. The tool facilitates running jobs on Hugging Face infrastructure and managing repos, buckets, and papers alongside your standard model and dataset operations.

Do I need Python to use the Hugging Face Hub CLI tool?

Yes, you need Python to use the Hugging Face Hub CLI tool, as execution requires the Python-based `hf` command. It depends on the `huggingface_hub` library to interact with the Hub infrastructure.

What's the best way to authenticate and manage local cache for Hugging Face ML models?

The best way to authenticate and manage local cache for Hugging Face ML models is using a centralized CLI. It handles authentication tokens and local cache management natively alongside model and dataset synchronization.

How to install the Hugging Face CLI for AI and ML resource management?

To install the Hugging Face CLI for AI and ML resource management, run the installation script `curl -LsSf https://hf.co/cli/install.sh | bash -s`. Once installed, use `hf --help` to explore available commands.

Why use a unified CLI for Hugging Face repo and dataset management instead of web interfaces?

Using a unified CLI for Hugging Face repo and dataset management automates complex workflows that web interfaces cannot handle efficiently. It allows researchers and developers to programmatically sync, upload, and manage multiple resources at scale.