huggingface-hub

Manage Hugging Face Hub repositories, datasets, and Spaces via the hf CLI.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/JKhyro/HERMES-AGENT --skill huggingface-hub-jkhyro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/JKhyro/HERMES-AGENT/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/JKhyro/HERMES-AGENT --skill huggingface-hub-jkhyro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the friction of working with Hugging Face Hub resources by giving you one CLI for authentication, repository management, dataset access, uploads, downloads, and operational workflows.

Core Features & Use Cases

  • Hub Operations: Create, delete, move, branch, tag, and sync model, dataset, and Space repositories.
  • Data and Model Workflows: Search listings, inspect metadata, query datasets with SQL, and transfer files with normal or large-folder uploads.
  • Platform Administration: Manage inference endpoints, jobs, buckets, cache, webhooks, collections, discussions, and pull requests from one interface.
  • Use Case: A machine learning engineer can authenticate once, upload a trained model, deploy an inference endpoint, and monitor or update the related repository without leaving the terminal.

Quick Start

Use the huggingface-hub skill to authenticate with Hugging Face and perform the exact Hub action you need, such as downloading a repository, uploading files, or managing datasets and endpoints.

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 Hub repositories from the terminal?

You can manage Hugging Face Hub repositories from the terminal by creating, deleting, moving, and branching model, dataset, and Space repos using the hf CLI for streamlined MLOps workflows.

Can I upload large folders to Hugging Face Hub via command line?

Yes, you can upload large folders to Hugging Face Hub via command line. The hf CLI supports resumable large-folder uploads to ensure reliable file transfers for massive datasets and models.

How do I query Hugging Face datasets with SQL from the CLI?

You can query Hugging Face datasets with SQL directly from the CLI. The hf CLI enables dataset SQL queries, allowing you to inspect metadata and search listings without leaving the terminal environment.

Does the hf CLI support deploying Hugging Face inference endpoints?

Yes, the hf CLI supports deploying Hugging Face inference endpoints. You can manage inference endpoints, execute jobs, and synchronize buckets entirely through command line platform administration.

What is the best way to automate Hugging Face Hub operations in MLOps?

Automating Hugging Face Hub operations in MLOps is best achieved using the hf CLI, which provides token-based login and JSON output specifically designed to support automated repository, dataset, and endpoint workflows.

Can I manage Hugging Face discussions and pull requests from the command line?

Yes, you can manage Hugging Face discussions and pull requests from the command line. The hf CLI allows you to handle discussions, pull requests, webhooks, and collections from a single terminal interface.