skills.rest
pingqLIN
pingqLINCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

hugging-face-datasets

Manage Hugging Face datasets with SQL querying and push-to-hub.

Updated Mar 24, 2026
Search Tags:#automation#sql#data-management#datasets#hub#hugging-face
One-click install
npx skills add https://github.com/pingqLIN/UniText --skill hugging-face-datasets-pingqlin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hugging-face-datasets
Source: https://github.com/pingqLIN/UniText/tree/main/runtime/skills/hugging-face-datasets
Command: npx skills add https://github.com/pingqLIN/UniText --skill hugging-face-datasets-pingqlin

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Streamlines the creation, configuration, and ongoing management of Hugging Face datasets, combining repo provisioning, system-prompt configuration, data ingestion, and SQL-based exploration in a unified workflow.

Core Features & Use Cases

  • Create and configure dataset repositories on HF Hub with structured system prompts.
  • Add and validate data rows using templates (chat, QA, classification, etc.) and streaming updates.
  • Query and transform datasets locally with inline SQL, then push results back to HF Hub when needed.

Quick Start

Initialize a new Hugging Face dataset repository, configure a system prompt, and begin adding data through templates.

Frequently Asked Questions about hugging-face-datasets

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

FAQPage Schema
How do I create and configure a Hugging Face dataset repository with structured prompts?▼

To create and configure a Hugging Face dataset repository, you can initialize a new repo on the Hub and set up structured system prompts. This workflow supports templated data lifecycles and direct Hub integration for ongoing management.

Can I use SQL to query and transform Hugging Face datasets locally?▼

Yes, you can query and transform Hugging Face datasets locally using inline SQL. This functionality allows you to explore data directly and then push the transformed results back to the HF Hub when needed.

What data templates are supported for adding rows to Hugging Face datasets?▼

Supported data templates for adding and validating rows include chat, QA, and classification formats. These templates ensure structured data ingestion and streaming updates within your data-curation workflows.

Do I need an HF_TOKEN to manage Hugging Face datasets and push updates?▼

Yes, you need an HF_TOKEN environment variable to manage Hugging Face datasets. This token is required for repo creation, push-to-hub operations, and secure integration with your model training pipelines.

What is the best way to integrate Hugging Face dataset management into a model training pipeline?▼

The best way to integrate Hugging Face dataset management into a pipeline is using a unified workflow that combines repo provisioning, template validation, multi-format exports, and SQL-based exploration for research projects.

Does this Hugging Face dataset management approach work with pandas and DuckDB?▼

Yes, this approach works with pandas and DuckDB dependencies. It leverages these libraries to enable local SQL-based querying and data transformation before pushing the validated results back to the Hugging Face Hub.

Related Skills

Explore More Data & Analytics Skills→
Andrew-GirgisAndrew-Girgis

huggingface-tool-builder

Create reusable scripts for interacting with the Hugging Face API.

Community
Intermediate
sitammeursitammeur
1

hugging-face-datasets

Create, configure, and query Hugging Face Hub datasets with DuckDB SQL.

Community
Intermediate
BlackRoad-OS-IncBlackRoad-OS-Inc
1

hugging-face-datasets

Create, configure, and manage Hugging Face datasets via SQL queries and Hub operations.

Official
Advanced
nferrer-devnferrer-dev

hugging-face-datasets

Create, configure, and transform Hugging Face datasets with SQL via DuckDB.

Community
Advanced