hugging-face-datasets

Create, manage, and query Hugging Face datasets with DuckDB SQL.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/keremtoker468-dotcom/restoran --skill hugging-face-datasets-keremtoker468-dotcom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-datasets
Source: https://github.com/keremtoker468-dotcom/restoran/tree/main/.claude/skills/hugging-face-datasets
Command: npx skills add https://github.com/keremtoker468-dotcom/restoran --skill hugging-face-datasets-keremtoker468-dotcom

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the creation, management, and querying of datasets on the Hugging Face Hub, enabling efficient data manipulation and analysis using SQL.

Core Features & Use Cases

  • Dataset Lifecycle Management: Initialize, configure, and stream updates to Hugging Face datasets.
  • SQL-Based Querying: Query, transform, and sample datasets using familiar SQL syntax via DuckDB.
  • Multi-Format Support: Handles various dataset types including chat, classification, QA, and tabular data.
  • Use Case: Analyze a large Hugging Face dataset like MMLU by running SQL queries to filter specific subjects, aggregate data, and push transformed subsets to new repositories.

Quick Start

Use the hugging-face-datasets skill to query the 'cais/mmlu' dataset with the SQL command 'SELECT * FROM data WHERE subject='nutrition' LIMIT 10'.

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 with SQL?

Query Hugging Face datasets with SQL by leveraging DuckDB integration to run familiar SQL syntax for filtering, aggregating, and transforming data directly on Hub repositories. It supports analyzing large datasets like MMLU without manual downloading.

Can I manage a Hugging Face dataset lifecycle including initialization and updates?

Yes, you can manage a Hugging Face dataset lifecycle by initializing repositories, configuring system prompts, and streaming row updates. This enables continuous data management and structured updates for various dataset types including chat and tabular formats.

Does DuckDB work with Hugging Face Hub for data transformation?

DuckDB works with the Hugging Face Hub to enable advanced data transformation via SQL. You can query, sample, and transform datasets using DuckDB, then push the resulting subsets to new Hugging Face repositories.

What types of Hugging Face datasets can I transform using SQL?

You can transform various Hugging Face dataset types using SQL, including chat, classification, QA, and tabular data. This multi-format support allows flexible SQL-based manipulation across different machine learning data structures.

What is the best way to analyze a large dataset like MMLU on Hugging Face?

The best way to analyze a large dataset like MMLU on Hugging Face is running SQL queries via DuckDB to filter specific subjects and aggregate data. You can then push transformed subsets to new repositories for targeted analysis.