🔌

hugging-face-tool-builder

🔌Plugin

huggingface/skills

VibeIndex|
What it does
|

Official Hugging Face skills defining AI/ML tasks like dataset creation, model training, and evaluation. Interoperable with Claude Code, OpenAI Codex, Gemini CLI, and Cursor using the standardized Agent Skill format.

Overview

Hugging-face-tool-builder is a skill from the Hugging Face Skills collection that provides AI coding agents with guidance for building tools on the Hugging Face platform. It follows the standardized Agent Skill format and is interoperable with all major coding agent tools including Claude Code, OpenAI Codex, Google Gemini CLI, and Cursor.

Key Features

  • Tool Building Guidance - Structured instructions for creating and deploying tools that integrate with the Hugging Face ecosystem
  • Cross-Agent Compatibility - Works with Claude Code, OpenAI Codex, Gemini CLI, and Cursor through standardized skill/agent definitions
  • Plugin Marketplace Installation - Install via /plugin marketplace add huggingface/skills and then install the specific skill through the plugin system
  • Self-Contained Skill Format - Each skill packages instructions, scripts, and resources in a folder with a SKILL.md file containing YAML frontmatter and guidance

Who is this for?

This skill is designed for AI/ML engineers and developers who want to build custom tools on the Hugging Face platform using AI coding agents. It is especially useful for those creating tooling for model inference, evaluation, or integration workflows within the Hugging Face ecosystem.

🏪

Part of

huggingface-skills

Installation

Add marketplace in Claude Code:
/plugin marketplace add huggingface/skills
Step 2. Install plugin:
/plugin install hugging-face-tool-builder@huggingface-skills
1,195
-
Last UpdatedFeb 6, 2026

More from this repository10

🏪
huggingface-skills🏪Marketplace

Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub

🔌
hugging-face-jobs🔌Plugin

Official Hugging Face skills defining AI/ML tasks like dataset creation, model training, and evaluation. Interoperable with Claude Code, OpenAI Codex, Gemini CLI, and Cursor using the standardized Agent Skill format.

🔌
hugging-face-evaluation🔌Plugin

Official Hugging Face skills defining AI/ML tasks like dataset creation, model training, and evaluation. Interoperable with Claude Code, OpenAI Codex, Gemini CLI, and Cursor using the standardized Agent Skill format.

🎯
hf-cli🎯Skill

A skill for the Hugging Face Hub CLI (hf), enabling downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, and jobs on the Hugging Face Hub. Replaces the deprecated huggingface-cli.

🔌
hugging-face-datasets🔌Plugin

Official Hugging Face skills defining AI/ML tasks like dataset creation, model training, and evaluation. Interoperable with Claude Code, OpenAI Codex, Gemini CLI, and Cursor using the standardized Agent Skill format.

🎯
huggingface-gradio🎯Skill

Official Hugging Face Gradio skill for building Python web UIs and ML demos — covers the `Interface` high-level wrapper, `Blocks` low-level layout with explicit event wiring, `ChatInterface` for chatbots, core component signatures (Textbox, etc.), streaming inputs/outputs, custom CSS/JS, and sharing your app.

🎯
huggingface-datasets🎯Skill

Explores, queries, and extracts data from any Hugging Face dataset via the Dataset Viewer REST API and npx tooling with zero Python dependencies — split/config discovery, row pagination, text search, filtering, SQL via parquetlens, and CLI upload.

🎯
huggingface-llm-trainer🎯Skill

Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment.

🎯
huggingface-papers🎯Skill

Hugging Face agent skills for AI/ML tasks like dataset creation, model training, and evaluation, interoperable with major coding agent tools.

🎯
transformers-js🎯Skill

Part of the official Hugging Face Skills collection, this skill teaches AI coding agents how to work with Transformers.js for running machine learning models directly in the browser and Node.js environments.