huggingface-hub

Search, download, upload, and manage Hugging Face Hub artifacts.

1|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/eddielueng/hermes-agent-zh --skill huggingface-hub-eddielueng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huggingface-hub
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/skills/mlops/huggingface-hub
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill huggingface-hub-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Hugging Face Hub operations can be slow and error-prone when you manually browse, download, upload, and deploy artifacts across models, datasets, and Spaces.

Core Features & Use Cases

  • Search, download, and upload Hub artifacts: Quickly fetch files from a repo or upload updates (including large folders) to keep work reproducible.
  • Datasets querying with SQL: Run DuckDB-powered SQL over dataset parquet URLs to extract exactly what you need for analysis or evaluation.
  • Inference endpoints and Spaces management: Deploy, scale-to-zero, pause/resume endpoints, and manage Spaces workflows like dev-mode and hot-reload.

Quick Start

Run the command hf datasets sql SELECT COUNT(*) FROM parquet_table WHERE split='train' on the dataset you want to analyze.

Frequently Asked Questions about huggingface-hub

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

FAQPage Schema
How do I query Hugging Face datasets with SQL?

You can query Hugging Face datasets with SQL by running DuckDB-powered SQL commands directly over dataset parquet URLs to extract specific data splits for analysis. Use the hf CLI datasets sql command to execute SELECT statements on parquet tables.

How do I manage Hugging Face Spaces and inference endpoints via CLI?

Manage Hugging Face Spaces and inference endpoints via CLI by deploying, scaling to zero, pausing, and resuming resources through structured hf commands. This supports Spaces workflows including dev-mode and hot-reload for iterative deployment.

Can I automate Hugging Face Hub repository uploads for large folders?

Yes, you can automate Hugging Face Hub repository uploads for large folders using the hf CLI. It supports structured command usage with JSON output compatibility, ensuring reproducible artifact uploads without manual browser interaction.

Do I need Hub authentication to download models and datasets using the hf CLI?

Yes, Hub authentication is required to interact with the Hugging Face Hub using the hf CLI. You must authenticate your environment to search, download, and manage models, datasets, and storage artifacts programmatically.

What is the best way to search and fetch files from a Hugging Face repository?

The best way to search and fetch files from a Hugging Face repository is using the hf CLI to efficiently download artifacts. This method replaces manual browsing and ensures reproducible access to models and datasets.

Why use CLI commands instead of the web interface for Hugging Face Hub operations?

Use CLI commands for Hugging Face Hub operations to avoid slow and error-prone manual browsing. The hf CLI enables automated, structured repository lifecycle management and dataset querying, yielding JSON outputs for seamless automation workflows.