skills.rest
Himanshu040604
Himanshu040604COMMUNITY
Explore all skills by this author →
WebsiteGitHub

hugging-face-datasets

Query and transform Hugging Face datasets using SQL via DuckDB.

Updated Mar 5, 2026
Search Tags:#data management#sql#data transformation#duckdb#datasets#hugging face
One-click install
npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill hugging-face-datasets-himanshu040604
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hugging-face-datasets
Source: https://github.com/Himanshu040604/codex-skills-setup/tree/main/assets/codex/skills/claude-import/skills/plugins/huggingface-skills%40claude-plugins-official/skills/hugging-face-datasets
Command: npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill hugging-face-datasets-himanshu040604

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 process of creating, managing, querying, and transforming datasets hosted on the Hugging Face Hub, making data manipulation more accessible and powerful.

Core Features & Use Cases

  • SQL-Based Querying: Directly query any Hugging Face dataset using standard SQL syntax via DuckDB.
  • Dataset Creation & Management: Initialize new dataset repositories, configure them with system prompts, and add data using predefined templates.
  • Data Transformation: Filter, aggregate, and reshape datasets using SQL queries.
  • Push to Hub: Save transformed data as new datasets on Hugging Face Hub.
  • Use Case: You need to analyze a large dataset on Hugging Face to find all entries related to a specific topic and then create a smaller, filtered dataset containing only those entries.

Quick Start

Query the 'cais/mmlu' dataset to select all 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 using SQL?▼

You can query Hugging Face datasets using SQL by leveraging DuckDB's `hf://` protocol to directly run standard SQL syntax against Hub repositories for filtering and analysis.

Can I filter a large Hugging Face dataset and push the results to a new repository?▼

Yes, you can filter large Hugging Face datasets using SQL queries and push the transformed data directly to new dataset repositories on the Hugging Face Hub.

What is the best way to manage and initialize Hugging Face dataset repositories?▼

The best way to manage Hugging Face datasets is using Python scripts to initialize repositories, configure them with system prompts, and add data through predefined templates.

Does this workflow support streaming dataset content from Hugging Face?▼

Yes, the workflow supports dataset content streaming from Hugging Face, allowing you to process and transform data dynamically using DuckDB and Python scripts.

Do I need DuckDB to transform Hugging Face datasets with SQL?▼

Yes, DuckDB is required as a dependency to execute SQL-based data transformation and querying directly against Hugging Face datasets using the `hf://` protocol.

Related Skills

Explore More Data & Analytics Skills→
luokai25luokai25

hugging-face-datasets

Manage Hugging Face Hub dataset lifecycles with SQL queries and transformations.

Community
Advanced
yangqiongyangqiong

Report Generator Skill

Generate HTML data reports from pandas DataFrames with summaries and analyses.

Community
Intermediate
POWERFULMOVESPOWERFULMOVES
1

hugging-face-dataset-creator

Create and manage Hugging Face Hub datasets with streaming support.

Community
Intermediate
ihatesea69ihatesea69
3

hugging-face-datasets

Manage Hugging Face datasets with SQL queries via DuckDB and hf:// protocol.

Community
Advanced