huggingface-hub

Manage Hugging Face Hub repositories, datasets, and inference endpoints via CLI.

1|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/icyzh/hermes-web --skill huggingface-hub-icyzh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/icyzh/hermes-web/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/icyzh/hermes-web --skill huggingface-hub-icyzh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill streamlines the interaction with the Hugging Face Hub, removing the complexity of manual repository management, file synchronization, and infrastructure deployment.

Core Features & Use Cases

  • Repository Management: Create, move, and delete models, datasets, or spaces directly from the command line.
  • Data & Model Operations: Efficiently download, upload, and sync large datasets or model weights between local storage and the Hub.
  • Infrastructure Control: Manage Inference Endpoints and monitor compute jobs, including resource tracking and deployment scaling.

Quick Start

Use the huggingface-hub skill to download the latest version of a specific model repository by providing its ID.

Frequently Asked Questions about huggingface-hub

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

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

You can manage Hugging Face models and datasets from the command line by using a unified CLI to create, move, and delete repositories, as well as synchronize large files directly with the Hub.

What is the best way to download large model weights from the Hugging Face Hub?

The best way to download large model weights from the Hugging Face Hub is through automated CLI synchronization, which efficiently handles large-scale data transfers between local storage and remote repositories.

Can I deploy and monitor Hugging Face Inference Endpoints via CLI?

Yes, you can deploy and monitor Hugging Face Inference Endpoints via CLI commands to manage compute jobs, track resources, and scale cloud-based inference infrastructure directly.

Do I need authenticated access to upload datasets to the Hugging Face Hub?

Yes, you need authenticated access to the Hugging Face platform to perform secure write operations like uploading datasets, model weights, and managing repository lifecycle changes.

What are the limitations of automating Hugging Face Hub workflows via command line?

Automating Hugging Face Hub workflows via command line requires authenticated platform access for secure read and write operations, and relies entirely on CLI availability for executing end-to-end MLOps synchronization.