hugging-face-datasets

Manage Hugging Face datasets with SQL querying via DuckDB.

3|Updated Nov 4, 2025
One-click install
npx skills add https://github.com/tayyabexe/skills --skill hugging-face-datasets-tayyabexe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hugging-face-datasets
Source: https://github.com/tayyabexe/skills/tree/main/skills/hugging-face-datasets
Command: npx skills add https://github.com/tayyabexe/skills --skill hugging-face-datasets-tayyabexe

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 familiar SQL syntax.

Core Features & Use Cases

  • SQL-Based Querying: Directly query any Hugging Face dataset using DuckDB SQL.
  • Dataset Management: Initialize new datasets, configure them with system prompts, and stream row updates.
  • Data Transformation: Filter, aggregate, and transform datasets using SQL.
  • Push to Hub: Save query results or transformed data as new datasets on Hugging Face Hub.
  • Use Case: Analyze a large dataset on Hugging Face by writing SQL queries to filter specific data points, aggregate statistics, and then push the processed subset to a new repository for further use.

Quick Start

Query the 'cais/mmlu' dataset for rows where the subject is 'nutrition' and limit the results to 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?

You can query Hugging Face datasets with SQL by using DuckDB to run standard SQL statements directly against the data. This Skill translates your SQL queries into efficient dataset operations for filtering and analysis without requiring manual downloads.

Can I push transformed data back to the Hugging Face Hub?

Yes, you can push transformed data back to the Hugging Face Hub. After filtering or aggregating datasets using SQL, the Skill allows you to save the processed results as a new dataset repository for future use.

Does this Skill support streaming row updates for Hugging Face datasets?

Yes, this Skill supports streaming row updates for Hugging Face datasets. It provides dataset management tools to initialize new datasets, configure them with system prompts, and stream new data rows dynamically.

How do I filter and aggregate large datasets on Hugging Face?

To filter and aggregate large datasets on Hugging Face, you write DuckDB SQL queries through this Skill. It enables direct data transformation, allowing you to extract specific data points and compute statistics efficiently.

Can I query Hugging Face datasets using pandas and DuckDB together?

Yes, you can query Hugging Face datasets using pandas and DuckDB together. This Skill integrates both dependencies, allowing you to manage dataset workflows and manipulate query results using familiar Python data structures.

Do I need to download an entire dataset to run SQL queries on Hugging Face?

No, you do not need to download an entire dataset to run SQL queries on Hugging Face. The Skill leverages DuckDB and the HF MCP server for comprehensive workflows, enabling direct SQL-based querying over diverse data formats.