Hugging Face Skill

This skill exposes the full Hugging Face Hub surface — both the huggingface-cli command-line tool and the huggingface_hub Python library — to every assistant interaction. It reads HF_TOKEN from the environment for authenticated operations; public read-only operations work without a token.

Token scope: HF_TOKEN is only required for private/gated model downloads, any upload, repo creation/deletion, and Space management. All public model/dataset browsing and downloads work without one.

Security Notice

• Set HF_TOKEN in your shell environment or .env file — never hard-code it in scripts.
• Use fine-grained tokens (read-only or repo-scoped) over full write tokens where possible. Create them at https://huggingface.co/settings/tokens
• Gated models (Llama, Gemma, etc.) require both a token and accepted model terms on the Hub web UI.
• HF_HUB_OFFLINE=1 prevents all network calls — safe for air-gapped or CI environments where the cache is pre-populated.

Installation

Minimum install

pip install huggingface_hub

Recommended install with all extras

pip install "huggingface_hub[cli,torch,tensorflow,fastai,dev]"

Enable fast downloads (optional)

pip install hf_transfer
export HF_HUB_ENABLE_HF_TRANSFER=1

Verify install

huggingface-cli version
huggingface-cli whoami       # requires HF_TOKEN

Authentication

Login (writes token to ~/.cache/huggingface/token)

huggingface-cli login
# or non-interactively:
huggingface-cli login --token $HF_TOKEN

Logout

huggingface-cli logout

Check current identity

huggingface-cli whoami

Environment variable (preferred for CI/scripts)

export HF_TOKEN=hf_...

The library reads HF_TOKEN automatically — no explicit login needed when this var is set.

Downloading Models and Datasets

Download an entire model repo

huggingface-cli download \x3Corg/model>
# Example:
huggingface-cli download google/gemma-2b

Download a single file

huggingface-cli download \x3Corg/model> \x3Cfilename>
huggingface-cli download openai/whisper-large-v3 config.json

Download to a specific directory

huggingface-cli download \x3Corg/model> --local-dir ./models/mymodel

Download a dataset repo

huggingface-cli download \x3Corg/dataset> --repo-type dataset

Download a specific revision (branch, tag, or commit SHA)

huggingface-cli download \x3Corg/model> --revision v1.0
huggingface-cli download \x3Corg/model> --revision abc1234

Download specific file patterns (glob)

huggingface-cli download \x3Corg/model> --include "*.safetensors"
huggingface-cli download \x3Corg/model> --exclude "*.bin" --include "*.safetensors"

Download gated model (requires token + accepted terms)

HF_TOKEN=hf_... huggingface-cli download meta-llama/Llama-3-8B

Uploading to the Hub

Upload a single file

huggingface-cli upload \x3Corg/repo> \x3Clocal_file> \x3Cpath_in_repo>
huggingface-cli upload myorg/mymodel weights.safetensors model/weights.safetensors

Upload an entire folder

huggingface-cli upload \x3Corg/repo> \x3Clocal_folder> \x3Cpath_in_repo>
huggingface-cli upload myorg/mymodel ./model_dir .

Upload to a dataset repo

huggingface-cli upload myorg/mydataset ./data . --repo-type dataset

Upload to a Space

huggingface-cli upload myorg/myspace ./app . --repo-type space

Upload with commit message

huggingface-cli upload myorg/mymodel ./weights . --commit-message "Add fp16 weights"

Upload large folder (multi-part, resumable)

huggingface-cli upload-large-folder myorg/mymodel --repo-type model ./large_model_dir

Repository Management

Create a repo

huggingface-cli repo create \x3Crepo-name>
huggingface-cli repo create my-model --type model
huggingface-cli repo create my-dataset --type dataset
huggingface-cli repo create my-space --type space

Delete a repo

huggingface-cli repo delete \x3Corg/repo>

Get repo info

huggingface-cli repo info \x3Corg/repo>
huggingface-cli repo info google/gemma-2b

Tags

huggingface-cli tag create  \x3Corg/repo> \x3Ctag>      --message "Release v1.0"
huggingface-cli tag list    \x3Corg/repo>
huggingface-cli tag delete  \x3Corg/repo> \x3Ctag>

Cache Management

Scan cache (see what's stored locally)

huggingface-cli scan-cache

Delete unused cache entries interactively

huggingface-cli delete-cache

Show cache size summary

huggingface-cli scan-cache --verbose

Python API — Quick Patterns

See templates/python_patterns.txt for full copy-paste code. Core entry point:

import os
from huggingface_hub import HfApi

api = HfApi(token=os.environ.get("HF_TOKEN"))

Use scripts/hf_helper.py as a CLI wrapper over the Python API for search, info, and cache operations without a browser.

Environment Variables

Best Practices

1. Prefer --local-dir over default cache for reproducible paths

The default cache uses content-addressed symlinks. Use --local-dir ./models/name when you need a stable, self-contained directory for an application.

2. Pin revisions in production

Always pass --revision \x3Ccommit-sha> in production downloads. Branches like main are mutable and can silently update between runs.

3. Use --include/--exclude to skip unnecessary weights

Large models ship both .bin and .safetensors formats. Download only what your framework uses:

huggingface-cli download \x3Cmodel> --include "*.safetensors" --exclude "*.bin"

4. Pre-populate cache before going offline

huggingface-cli download \x3Cmodel>        # fills cache
export HF_HUB_OFFLINE=1                 # subsequent loads use cache only

5. Use fine-grained tokens with minimal scope

Create per-project tokens at https://huggingface.co/settings/tokens — read-only tokens cannot accidentally delete or overwrite repos.

6. Commit model cards alongside weights

Every upload is a git commit. Include a README.md (model card) in the upload folder so the repo is immediately browseable on the Hub.

7. Use upload-large-folder for models over ~50 GB

upload-large-folder uses multi-part upload with automatic retry and deduplication — far more reliable than upload for very large checkpoints.

Troubleshooting