A collection of AI/ML skill definitions for coding agents to interact with the Hugging Face ecosystem.
huggingface-skills is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add huggingface/skillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This repository contains skill definitions that teach AI coding agents how to perform tasks like model training, dataset creation, and evaluation using Hugging Face tools. It works with popular coding agents such as Claude Code, Codex, Gemini CLI, and Cursor. You can install these skills to give your agent direct access to Hugging Face Hub operations.
Hugging Face Skills is a repository of standardized skill definitions for AI/ML tasks, designed to be interoperable with major coding agent tools like OpenAI Codex, Anthropic's Claude Code, Google DeepMind's Gemini CLI, and Cursor. Each skill is a self-contained folder with a SKILL.md file containing YAML frontmatter and guidance for the agent. The repository includes skills like hf-cli for Hugging Face Hub operations and huggingface-best for model recommendations. Installation varies by agent: for Claude Code, use /plugin install; for Codex, copy skills to .agents/skills; for Gemini CLI, use gemini extensions install; for Cursor, use the plugin manifests. The skills follow the Agent Skills standard and are also available through Cursor Marketplace and Codex Plugins Directory.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 52 days ago.
10631 GitHub stars indicate community interest.
32 open issues signal maintenance load.
Apache-2.0 license detected.
Automate model training and evaluation using Hugging Face libraries via a coding agent.
Search and recommend the best AI models for specific tasks using leaderboard data.
Manage Hugging Face Hub repositories, datasets, and Spaces through CLI commands.
Integrate AI/ML workflows into existing development pipelines with agent support.
Quickly prototype and deploy machine learning models using natural language instructions.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Skills execute commands on the user's machine; ensure the agent has appropriate permissions and review commands before execution.
Hugging Face Hub access tokens may be exposed if not handled securely; use environment variables or secret management.
10,631
Stars
701
Forks
32
Issues
Apache-2.0
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
A collection of AI/ML skill definitions for coding agents to interact with the Hugging Face ecosystem.
AI/ML developers who use coding agents to streamline model development., Data scientists looking to automate dataset creation and model evaluation., DevOps engineers integrating Hugging Face workflows into CI/CD pipelines.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing. Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, hyperframes.
Jun 7, 2026
4 security/trust notes recorded.
Setup difficulty is 2/5.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.