Skip to content
FindOpenSource

Hugging Face Skills

Agent skills for AI/ML work on the Hugging Face Hub -- dataset creation, model training and evaluation, plus an hf CLI skill for core Hub operations.

Overview

Hugging Face Skills are Agent Skills definitions that teach a coding agent to work with the Hugging Face ecosystem. The recommended starting point is the hf-cli skill, which teaches the agent every hf command for managing models, datasets and Spaces on the Hub; further skills cover tasks such as building datasets, training and fine-tuning models, and running evaluations.

The skills work in Claude Code (as a plugin marketplace), Codex, Gemini CLI and Cursor, with a generated AGENTS.md as a fallback for agents that don't support skills yet. A good fit for ML engineers who want an agent to handle Hub chores and training runs without hand-holding.

Why it's in this catalog

Catalog rating: ★★★☆☆ (3/5)

The official way to give agents Hugging Face Hub skills; valuable for ML workflows, narrower audience than general coding skill sets.

  • Emerging
  • Vendor-backed
Categories
AI Agents & Agent Tools
Keywords
agent-skillhuggingfacemodel-trainingdatasets
Languages
Python, TypeScript, Shell
License
Apache-2.0

Compare with another project

Spotted an error? Suggest an edit on GitHub.