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 CLI so you can search, download, upload, and manage models, datasets, Spaces, and compute jobs directly from the command line. ## Core Features & Use Cases - Repository Operations: Download and upload models and datasets, create or delete repos, manage branches, tags, and discussions/PRs. - Compute & Infrastructure: Deploy Inference Endpoints, run Jobs (including hf jobs uv for Python scripts), and manage Spaces with dev-mode and hot-reload. - Data & Automation: Query datasets with SQL via DuckDB, manage S3-like buckets, configure webhooks, and organize collections. - Use Case: You need to download a fine-tuned model, upload a large dataset folder with resumable uploads, and then deploy an inference endpoint — all scripted in one shell workflow using hf download, hf upload-large-folder, and hf endpoints deploy. ## Quick Start Ask the assistant to download a specific model from the Hugging Face Hub using the hf CLI, for example by requesting to download a repo such as meta-llama/Llama-3-8B to a local folder.
