fetch-dataset-from-huggingface

Community

Fetch HF datasets into a tool's data folder.

AuthorAlexKapadia
Version1.0.0
Installs0

System Documentation

What problem does it solve?

In Pixie, ingesting HuggingFace Hub datasets into a tool's workspace was manual and error-prone. This skill automates downloading public and token-gated datasets directly into the specific tool's data folder, enabling reproducible experiments and streamlined workflows.

Core Features & Use Cases

  • Supports public datasets and gated datasets using HF_TOKEN with zero code changes.
  • Downloads datasets into the tool's local workspace under tools/<tool_id>/data/datasets/<dataset_id>/files for reusability.
  • Validates target tool existence, updates dependencies as needed, and emits a manifest with dataset metadata for traceability.

Quick Start

Name a HuggingFace dataset (namespace/name) and it will be downloaded into the tool's data/datasets path.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: fetch-dataset-from-huggingface
Download link: https://github.com/AlexKapadia/Pixie/archive/main.zip#fetch-dataset-from-huggingface

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.