Hugging Face Skills
Agent Skills for AI/ML work on the Hugging Face Hub: dataset creation, model training, evaluation and core hf CLI operations.
Tags
Description
Skills follow the standardized Agent Skills format. The recommended starting point is the hf-cli skill, which teaches an agent the hf commands (search models, manage datasets and buckets, launch Spaces, run jobs); further workflow skills install with hf skills add <skill-name>.
Related
- Agent Skills Specification: Open format for packaging agent capabilities as folders with a SKILL.md (YAML frontmatter + instructions) plus optional scripts and resources.
Guides & comparisons
- Agent skill packs, skills CLIs and registries (Comparison): How Agent Skills are installed, discovered and shared across Claude Code, Codex, Gemini CLI, Cursor and Copilot, and how the main installers (skills CLI, plugin marketplaces) and skill packs compare on format, harness support, licence and install command.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)