huggingface-skills

Q: How to install huggingface-skills?

Create the skills directory: mkdir -p .claude/skills. Then run: mkdir -p .claude/skills && curl -o .claude/skills/huggingface-skills.md https://raw.githubusercontent.com/huggingface/skills.git/main/SKILL.md. Finally, /huggingface-skills in Claude Code.

Q: What is huggingface-skills best for?

huggingface-skills is categorized under Development.

Official PluginDevelopmentby Anthropic

Build, train, evaluate, and use open source AI models, datasets, and spaces.

First seen 4/17/2026

Summary

This skill integrates Hugging Face's ecosystem into Claude Code, enabling developers to build, train, evaluate, and deploy open source AI models, datasets, and Spaces directly from the command line.

It streamlines workflows for model discovery, fine-tuning, and sharing, making it easier to leverage the Hugging Face Hub without leaving your development environment.

Install & Usage

Create the skills directory

mkdir -p .claude/skills

Download the skill file

mkdir -p .claude/skills && curl -o .claude/skills/huggingface-skills.md https://raw.githubusercontent.com/huggingface/skills.git/main/SKILL.md

Invoke in Claude Code

/huggingface-skills

Use Cases

Search and load any model or dataset from the Hugging Face Hub for experimentation or fine-tuning.

Fine-tune a pre-trained transformer model on a custom dataset using a single command.

Evaluate a model's performance on a benchmark dataset and compare results with leaderboard metrics.

Create and push a new dataset or model to the Hugging Face Hub for collaboration.

Deploy a model as a Hugging Face Space with a Gradio or Streamlit interface.

List and manage your personal repositories and tokens on the Hugging Face Hub.

Usage Examples

/huggingface-skills search models --query 'text-classification' --limit 5

/huggingface-skills train --model 'bert-base-uncased' --dataset 'imdb' --epochs 3

/huggingface-skills evaluate --model 'my-finetuned-model' --dataset 'glue/mrpc'

View source on GitHub

Security Audits

LicenseUnknownSourcePassRepositoryPass

Frequently Asked Questions

What is huggingface-skills?

This skill integrates Hugging Face's ecosystem into Claude Code, enabling developers to build, train, evaluate, and deploy open source AI models, datasets, and Spaces directly from the command line. It streamlines workflows for model discovery, fine-tuning, and sharing, making it easier to leverage the Hugging Face Hub without leaving your development environment.

How to install huggingface-skills?

To install huggingface-skills: create the skills directory (mkdir -p .claude/skills), then run: mkdir -p .claude/skills && curl -o .claude/skills/huggingface-skills.md https://raw.githubusercontent.com/huggingface/skills.git/main/SKILL.md. Finally, /huggingface-skills in Claude Code.

What is huggingface-skills best for?

huggingface-skills is a skill categorized under Development. Created by Anthropic.

What can I use huggingface-skills for?

huggingface-skills is useful for: Search and load any model or dataset from the Hugging Face Hub for experimentation or fine-tuning.; Fine-tune a pre-trained transformer model on a custom dataset using a single command.; Evaluate a model's performance on a benchmark dataset and compare results with leaderboard metrics.; Create and push a new dataset or model to the Hugging Face Hub for collaboration.; Deploy a model as a Hugging Face Space with a Gradio or Streamlit interface.; List and manage your personal repositories and tokens on the Hugging Face Hub..