huggingface-hub

Manage Hugging Face Hub models, datasets, and Spaces via CLI operations.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/shiftrepo/aws --skill huggingface-hub-shiftrepo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/shiftrepo/aws/tree/main/HermesAgent/skills/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/shiftrepo/aws --skill huggingface-hub-shiftrepo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Centralize and simplify the management of Hugging Face Hub resources (models, datasets, and Spaces) via a single command-line interface.

Core Features & Use Cases

  • Search, download, and upload models and datasets from the Hub.
  • Manage repositories, run SQL-like queries on datasets, and deploy inference endpoints.
  • Use with automated ML pipelines to streamline model versioning, deployment, and discovery.

Quick Start

Install the Hugging Face CLI and run hf models list to view available models.

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 models and datasets from the command line?

You can manage Hugging Face Hub models, datasets, and Spaces by using a single CLI to search, download, upload, and handle repository operations. This approach centralizes ML workflow automation tasks directly from the command line.

Can I run SQL queries on Hugging Face datasets via the CLI?

Yes, you can run SQL-based queries directly on Hugging Face datasets via the CLI. This feature allows you to retrieve and filter specific dataset records without needing to download the entire repository locally first.

How do I deploy Hugging Face inference endpoints in automated ML pipelines?

You can deploy Hugging Face inference endpoints in automated ML pipelines by executing dedicated CLI commands. This process requires authentication via tokens to securely provision and manage endpoints across your projects.

Does the Hugging Face CLI require authentication tokens for uploading models?

Yes, the Hugging Face CLI requires authentication via tokens for uploading models and managing repositories. Token-based authentication ensures secure access when pushing versioned assets or deploying inference endpoints.

What is the best way to automate model versioning and discovery for MLOps?

The best way to automate model versioning and discovery for MLOps is using a centralized CLI to search, download, and upload models to the Hub. This approach simplifies tracking and retrieving model iterations across various projects.

Can I manage Hugging Face Spaces using the same command line interface?

Yes, you can manage Hugging Face Spaces using the same command line interface designed for models and datasets. It provides a unified tool to handle repository management and deployment operations across all Hub resources.