huggingface-hub

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

Updated May 4, 2026
One-click install
npx skills add https://github.com/JamesFincher/gengar --skill huggingface-hub-jamesfincher
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/JamesFincher/gengar/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/JamesFincher/gengar --skill huggingface-hub-jamesfincher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the guesswork and repetitive clicks involved in finding, downloading, uploading, and operating on Hugging Face models, datasets, and Spaces from the command line.

Core Features & Use Cases

  • Hub browsing and asset operations: Search and manage repositories and their files for models, datasets, and Spaces.
  • Dataset and compute workflows: List dataset parquet resources and run SQL queries against them using DuckDB-backed tooling.
  • Production-oriented management: Create/sync storage buckets, manage webhooks, and operate inference endpoints and jobs for automation.
  • Use Case: You need to quickly fetch the exact dataset revision used for training and verify cached content before running an MLOps pipeline.

Quick Start

Ask the agent to download a specific repository from the Hugging Face Hub by running: hf download your-namespace/your-repo-id.

Frequently Asked Questions about huggingface-hub

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

FAQPage Schema
How do I download a specific model or dataset from the Hugging Face Hub via CLI?

Use the hf download command with your namespace and repo ID to fetch Hugging Face Hub assets. The Skill manages repository files for models, datasets, and Spaces, supporting specific revisions and quiet outputs for MLOps automation.

Can I run SQL queries directly against Hugging Face datasets?

Yes, you can query Hugging Face datasets by listing parquet resources and running SQL against them. The Skill utilizes DuckDB-backed tooling to execute compute workflows and query dataset contents directly from the command line.

Does this tool support managing inference endpoints and hub storage buckets?

Yes, the tool supports production-oriented MLOps management including creating and syncing hub storage buckets, operating inference endpoints, and managing jobs. It also handles webhooks and repository lifecycle automation.

How do I handle Hugging Face Hub authentication for CLI automation?

Proper Hub authentication handling is required to manage Hugging Face workflows via the hf CLI. The Skill supports JSON and quiet outputs specifically to enable seamless automation for searching, uploading, and operating on assets.

What is the best way to search for models and Spaces on the Hugging Face Hub?

The best way to search for assets is using the hf CLI to browse and manage repositories. The Skill removes repetitive clicks by enabling direct command-line searching for Hugging Face models, datasets, and Spaces.