hugging-face-cli

Manage Hugging Face Hub resources via the hf CLI.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/erenisiklar/Pusula --skill hugging-face-cli-erenisiklar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-cli
Source: https://github.com/erenisiklar/Pusula/tree/main/.claude/skills/hugging-face-cli
Command: npx skills add https://github.com/erenisiklar/Pusula --skill hugging-face-cli-erenisiklar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The Hugging Face Hub CLI (hf) enables developers to manage models, datasets, spaces, and compute tasks from the terminal, reducing friction and enabling automation across HF workflows.

Core Features & Use Cases

  • Manage authentication and tokens for Hugging Face Hub access.
  • Download and upload models, datasets, and spaces to and from the Hub.
  • Create, update, and delete repositories and files; manage cache and compute jobs; operate endpoints and workflows.
  • Use cases include CI/CD model publishing, local development, and automation of repetitive Hub tasks.

Quick Start

Install the hf CLI and run a basic login followed by a sample download.

Frequently Asked Questions about hugging-face-cli

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

FAQPage Schema
How do I automate Hugging Face Hub tasks from the command line?

You can automate Hugging Face Hub tasks using the hf CLI to manage authentication, download and upload models or datasets, and handle repository operations within automation scripts.

Can I use the hf CLI for CI/CD model publishing to the Hugging Face Hub?

Yes, the hf CLI supports CI/CD model publishing by enabling terminal-based authentication and upload commands to push models, datasets, and spaces directly to the Hugging Face Hub.

How do I manage Hugging Face repository files and compute jobs via the terminal?

Manage Hugging Face repository files and compute jobs by executing hf CLI commands to create, update, or delete repositories, manage cache, and operate compute endpoints and workflows.

What is the best way to handle Hugging Face Hub authentication in local development?

Handle Hugging Face Hub authentication in local development by running the hf CLI login command to securely configure access tokens for your terminal session and automation scripts.

Does the Hugging Face CLI support downloading and uploading spaces?

Yes, the Hugging Face CLI supports downloading and uploading spaces, allowing you to transfer spaces to and from the Hub alongside your models and datasets.

Why use the hf CLI instead of manual Hugging Face Hub repository management?

Use the hf CLI to reduce friction and enable automation across Hugging Face workflows, replacing repetitive manual Hub tasks with scriptable terminal commands for repository and compute management.