huggingface-hub

Manage Hugging Face Hub models, datasets, repos, and endpoints via CLI.

87|20|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/openaeon/OpenAEON --skill huggingface-hub-openaeon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/openaeon/OpenAEON/tree/main/skills/huggingface-hub
Command: npx skills add https://github.com/openaeon/OpenAEON --skill huggingface-hub-openaeon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

You need a fast, reliable way to search, download, upload, and manage Hugging Face Hub resources without manually navigating the web UI.

Core Features & Use Cases

  • Model, Dataset, and Repo Operations: Download and upload files, sync content to buckets, and retrieve information about models and datasets by ID.
  • Dataset Querying with SQL: Run SQL queries over dataset parquet files using hf datasets sql.
  • Deployment & Infrastructure Management: Deploy and manage inference endpoints, run Hub jobs, and manage Spaces behaviors like dev-mode and hot-reload.
  • Collaboration Workflows: Manage discussions and pull requests through hf discussions commands.

Quick Start

Run: "Use hf to list popular models and show details for a specific model like openai/clip-vit-base-patch32."

Frequently Asked Questions about huggingface-hub

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

FAQPage Schema
How do I download and upload Hugging Face models from the command line?

You can download and upload Hugging Face models from the command line using the `hf` CLI. It provides command-line operations for discovering, downloading, uploading, and managing Hub models, datasets, and Spaces without navigating the web UI.

Can I run SQL queries over Hugging Face datasets?

Yes, you can run SQL queries over Hugging Face datasets. The `hf datasets sql` command allows you to run SQL queries directly over dataset parquet files for fast, structured data inspection.

How do I deploy and manage Hugging Face inference endpoints for production?

To deploy and manage Hugging Face inference endpoints for production, use the `hf` CLI. It supports deployment and infrastructure management, allowing you to deploy inference endpoints and run Hub jobs directly from the command line.

What's the best way to manage Hugging Face Spaces and pull requests in MLOps workflows?

The best way to manage Hugging Face Spaces and pull requests in MLOps workflows is using the `hf` CLI. It enables Spaces behaviors like dev-mode and hot-reload, plus manages discussions and pull requests through `hf discussions` commands.

Do I need authentication to automate Hugging Face Hub asset synchronization to buckets?

Yes, you need authentication to automate Hugging Face Hub asset synchronization to buckets. The CLI requires `hf` authentication to securely sync content to buckets and supports structured outputs for automation via JSON formatting flags.