What problem does it solve? Interacting with the Hugging Face Hub through the web UI or raw API calls is slow and hard to automate. This Skill provides a complete reference for the modern hf command-line interface, enabling scripted management of models, datasets, Spaces, and compute jobs. ## Core Features & Use Cases - Repository Operations: Download, upload, create, duplicate, move, and delete models, datasets, and Spaces, including resumable uploads of large folders. - Data & Discovery: List and inspect datasets and models, run DuckDB SQL queries against dataset parquet files, and browse daily papers. - Infrastructure & Automation: Deploy Inference Endpoints, run compute jobs, manage S3-like buckets, webhooks, collections, and local cache. - Use Case: A machine learning engineer needs to publish a fine-tuned model. They authenticate with hf auth login, create a repository with hf repos create, and push weights using hf upload-large-folder for a resumable transfer. ## Quick Start Ask the assistant to download a specific model from the Hugging Face Hub, for example by saying: download the meta-llama/Llama-3-8B model using the hf CLI.
