hugging-face-datasets

Query Hugging Face datasets with SQL via DuckDB integration.

1|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/yuxia214/-22 --skill hugging-face-datasets-yuxia214
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-datasets
Source: https://github.com/yuxia214/-22/tree/main/.cursor/skills/hugging-face-datasets
Command: npx skills add https://github.com/yuxia214/-22 --skill hugging-face-datasets-yuxia214

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 streamlines the process of creating, managing, and querying datasets on the Hugging Face Hub, enabling efficient data manipulation and transformation using familiar SQL syntax.

Core Features & Use Cases

  • Dataset Creation & Management: Initialize new datasets, configure them with system prompts, and manage their lifecycle.
  • SQL-Based Querying: Query any Hugging Face dataset using DuckDB SQL, including schema discovery, data sampling, aggregations, and transformations.
  • Multi-Format Support: Handles diverse dataset types like chat, classification, QA, and tabular data.
  • Use Case: You need to analyze a large dataset on Hugging Face to find all examples related to a specific topic and then push a filtered subset to a new repository.

Quick Start

Query the 'cais/mmlu' dataset for nutrition-related entries using SQL.

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, which enables schema discovery, data sampling, and advanced transformations through familiar SQL syntax without downloading the entire dataset locally.

What is the best way to manage Hugging Face dataset lifecycles programmatically?

Managing Hugging Face dataset lifecycles programmatically involves initializing new datasets, configuring them with system prompts, and handling diverse data types like chat, classification, and QA through integrated hub APIs.

Can I use DuckDB to analyze and filter large datasets on the Hugging Face Hub?

Yes, DuckDB supports content streaming and SQL-based querying to analyze large Hugging Face datasets, allowing you to perform aggregations and push filtered subsets to new repositories efficiently.

Does this SQL-based approach support various Hugging Face data formats like chat and tabular data?

Yes, this approach supports multi-format handling for diverse Hugging Face dataset types, including chat, classification, QA, and tabular data, enabling SQL transformations across these varied structures.

How do I create and configure a new dataset on Hugging Face for SQL querying?

To create and configure a new dataset, you initialize the repository, set up system prompts, and use DuckDB integration to enable immediate SQL-based querying and advanced data transformation workflows.

What are the limitations of using DuckDB SQL for Hugging Face dataset transformation?

Using DuckDB SQL for Hugging Face dataset transformation requires dependencies like pandas and huggingface_hub, meaning complex workflows involving the HF MCP server may need additional environment configuration to function correctly.