Hub documentation
Skills
Single Sign-On (SSO) Audit Logs Storage Regions Data Studio for Private datasets Resource Groups (Access Control) Advanced Compute Options Advanced Security Tokens Management Publisher Analytics Gating Group Collections Network Security Rate Limits Blog Articles
PRO Plan Repositories Getting Started with Repositories Repository Settings Storage Limits Storage Backend (Xet) Local Cache Pull Requests & Discussions Notifications Collections Webhooks GitHub Actions Notebooks Next Steps Licenses
Models The Model Hub Model Cards Eval Results Leaderboard Data Gated Models Uploading Models Downloading Models Integrated Libraries Model Widgets Model Inference Models Download Stats Model Release Checklist Local Apps Frequently Asked Questions Advanced Topics
Datasets Datasets Overview Dataset Cards Gated Datasets Uploading Datasets Uploading Datasets (for LLMs) Downloading Datasets Streaming Datasets Integrated Libraries Data Studio Datasets Download Stats
Spaces Spaces Overview Spaces GPU Upgrades Spaces ZeroGPU Spaces Dev Mode Spaces Disk Usage & Storage Spaces Custom Domain Spaces as MCP servers Spaces as Agent Tools Spaces as API Endpoints Gradio Spaces Streamlit Spaces Static HTML Spaces Docker Spaces Embed your Space Run Spaces with Docker Spaces Configuration Reference Sign-In with HF button Featured Spaces Spaces Changelog Advanced Topics
Storage Buckets new Jobs Jobs Overview Quickstart Pricing and Billing Manage Jobs Configuration Popular Images Examples & Tutorials Schedule Jobs Webhook Automation Reference
Agents Agents Overview Hugging Face CLI for AI Agents Hugging Face MCP Server Hugging Face Agent Skills Building agents with the HF SDK Local Agents with llama.cpp Agent Libraries
Other Skills
Looking for the
hfCLI Skill? It’s the quickest way to connect your agent to the Hugging Face ecosystem. See the Hugging Face CLI for AI Agents guide.
Hugging Face provides a curated set of Skills built for AI builders. Train models, create datasets, run evaluations, track experiments. Each Skill is a self-contained SKILL.md that your agent follows while working on the task.
Skills work with all major coding agents: Claude Code, OpenAI Codex, Google Gemini CLI, and Cursor. Learn more about the format at agentskills.io.
Installation
Claude Code
OpenAI Codex
Gemini CLI
Cursor
# register the skills marketplace
/plugin marketplace add huggingface/skills
# install a specific Skill
/plugin install <skill-name>@huggingface/skillsAvailable Skills
| Skill | What it does |
|---|---|
hf-cli | Hub operations via the hf CLI: download, upload, manage repos, run jobs |
huggingface-datasets | Explore datasets, paginate rows, search text, apply filters |
huggingface-llm-trainer | Train or fine-tune LLMs with TRL (SFT, DPO, GRPO) on HF Jobs |
huggingface-vision-trainer | Train object detection and image classification models |
huggingface-community-evals | Run evaluations against models on the Hugging Face Hub on local hardware |
huggingface-trackio | Track and visualize ML training experiments with Trackio |
huggingface-papers | Look up and read Hugging Face paper pages in markdown |
huggingface-paper-publisher | Publish and manage research papers on the Hub |
huggingface-tool-builder | Build reusable scripts for HF API operations |
gradio | Build Gradio web UIs and demos |
transformers-js | Run ML models in JavaScript/TypeScript with WebGPU/WASM |
Using Skills
Once installed, mention the Skill directly in your prompt:
- “Use the HF model trainer Skill to fine-tune Qwen3-0.6B with SFT on the Capybara dataset”
- “Use the HF evaluation Skill to add benchmark results to my model card”
- “Use the HF datasets Skill to create a new dataset from these examples”
Your agent loads the corresponding SKILL.md instructions and helper scripts automatically.
Resources
- Skills Repository - Browse and contribute
- Agent Skills format - Specification and docs
- CLI Guide - Hugging Face CLI for AI Agents
- MCP Guide - Use alongside Skills