hugging-face-datasets

Manage Hugging Face Hub datasets with DuckDB SQL queries and transformations.

Updated Feb 28, 2026
One-click install
npx skills add https://github.com/mashharuki/Mistral-Worldwide-Hackathon --skill hugging-face-datasets-mashharuki
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-datasets
Source: https://github.com/mashharuki/Mistral-Worldwide-Hackathon/tree/main/.agents/skills/hugging-face-datasets
Command: npx skills add https://github.com/mashharuki/Mistral-Worldwide-Hackathon --skill hugging-face-datasets-mashharuki

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires huggingface_hub, duckdb, datasets, pandas, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the entire lifecycle of Hugging Face datasets, from creation and configuration to advanced SQL-based querying and transformation, making dataset management efficient and accessible.

Core Features & Use Cases

  • Dataset Lifecycle Management: Initialize new repositories, configure system prompts, and stream row updates.
  • SQL-Based Querying: Use DuckDB SQL to query, analyze, and transform any Hugging Face dataset directly.
  • Multi-Format Support: Handles diverse dataset types like chat, text classification, QA, and tabular data.
  • Use Case: You need to analyze a large dataset on Hugging Face to find all examples related to 'climate change' and then filter them for a specific sentiment. You can use SQL queries to perform this analysis and even push the filtered subset to a new repository.

Quick Start

Use the hugging-face-datasets skill to query the 'cais/mmlu' dataset for rows where the subject is 'nutrition'.

Frequently Asked Questions about hugging-face-datasets

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query Hugging Face datasets using SQL?

You can query Hugging Face datasets using SQL by leveraging DuckDB integration to directly analyze and transform dataset rows, filtering for specific conditions without downloading the entire dataset locally.

Can I push filtered Hugging Face dataset rows to a new repository?

Yes, after querying and filtering rows with DuckDB SQL, you can stream updates and push the transformed subset to initialize and populate a new dataset repository on the Hugging Face Hub.

What data formats does the Hugging Face datasets skill support?

The skill supports diverse dataset formats including chat conversations, text classification, QA pairs, and tabular data, allowing you to manage and transform these structures via SQL.

Do I need a Python environment to manage Hugging Face datasets with DuckDB?

Yes, you need a Python environment configured with uv and the huggingface_hub library to initialize repositories, manage dataset lifecycles, and execute DuckDB SQL transformations.

How do I initialize a new dataset repository on Hugging Face Hub?

You can initialize a new dataset repository by using the lifecycle management tools to configure system prompts, set up the structure, and stream row updates directly to the Hugging Face Hub.

What is the best way to analyze large Hugging Face datasets for specific topics?

The best way to analyze large Hugging Face datasets is using DuckDB SQL queries to filter rows based on specific topics and sentiments, enabling efficient analysis without full local downloads.