Hugging Face Skills: a Claude Code skill by Hugging Face
Official
For ML developers who want Claude to use the Hugging Face Hub, train models and ship demos. Skip it if you don't work with models or datasets on Hugging Face.
Before you install: The hf-cli skill's install line pipes a script from hf.co straight into bash, and its description asks to be used for anything AI or ML related.
- Score
- 64of 100
- Rank
- #216of 239
- Installs
- 3.6Kon skills.sh
- Stars
- 11.3Kon GitHub
- Security
- Mixed 5 scanners
- Updated
- 2026
- Context
- ~253tokens always
Install
npx skills add https://github.com/huggingface/skills Run it in your terminal. View the source
Most people install it straight from GitHub, where it has 11.3K stars, so its skills.sh count understates how widely it is used.
Using the Claude app rather than Claude Code? You can add a skill there too. How to add it in the app
What does Hugging Face Skills do?
Hugging Face Skills is a set of 26 official skills that teach Claude to work with the Hugging Face Hub and its libraries. hf-cli lists every command of the hf CLI: downloading and uploading models and datasets, managing repos, buckets, Spaces, webhooks, Inference Endpoints and compute Jobs. Other members train models with TRL or Unsloth on HF Jobs, fine-tune vision and sentence-transformers models, build Gradio demos and Spaces, query the Dataset Viewer API, read papers, estimate memory with hf-mem, pick GGUF models to run locally, and plan SageMaker deployments through a group of hf-cloud skills.
It comes as a set of skills that work together:
- hf-cli
- hf-cloud-aws-context-discovery
- hf-cloud-python-env-setup
- hf-cloud-sagemaker-deployment-planner
- hf-cloud-sagemaker-iam-preflight
- hf-cloud-sagemaker-production-defaults
- hf-cloud-serving-image-selection
- hf-mcp
- hf-mem
- huggingface-best
- huggingface-community-evals
- huggingface-datasets
When should you use Hugging Face Skills?
Use it when
- You need to download or upload a model or dataset
- You want to fine-tune a model on Hugging Face Jobs
- You are building a Gradio demo or Space
Skip it when
- You don't use the Hugging Face ecosystem
- Your company bars sending data to Hugging Face
What it needs and what it can touch
You need
- A Hugging Face account and access token
- The hf CLI
- An AWS account, only for the SageMaker skills
What it can do
- Runs shell commands (hf CLI, Python training scripts)
- Uploads, changes and deletes repos and buckets on your Hugging Face account
- Starts compute jobs, sandboxes and endpoints on Hugging Face
- Works with AWS SageMaker for the hf-cloud skills
From reading its instructions, not from running it.
Why it scores 64
Strongest on upkeep (100 of 100), weakest on adoption (25).
Is Hugging Face Skills safe to install?
At least one scanner raised a medium warning. Read the results below. Scanners often miss what other scanners catch, and a skill can change after a scan. Read its source before you install it.
| Scanner | Result | Date |
|---|---|---|
| Gen Agent Trust Hub | Passed | Oct 30, 2026 |
| Socket | Passed | Oct 30, 2026 |
| Snyk | Medium risk | Oct 30, 2026 |
| Runlayer | Passed | Mar 13, 2026 |
| ZeroLeaks | Low risk | Apr 16, 2026 |
Details
- Installs
- 3,598
- Repository stars
- 11,328
- Last repository change
- Tokens always loaded
- about 253
- Tokens when used
- about 8,197
- License
- Apache-2.0
- Data confidence
- High
Did it do the job for you?
Alternatives to Hugging Face Skills
All skills for this job-
Get Azure skillsAzure skills
For teams on Microsoft Azure who want Claude to plan, check and run deployments or build Foundry agents.
-
Get Firebase skillsFirebase skills
For app developers on Firebase who want Claude to run the CLI for setup, sign-in, hosting and Gemini features.
-
Get Google Agents CLIGoogle Agents CLI
For developers building AI agents with Google's ADK who want guidance from scaffold to deploy.
Hugging Face Skills