dataset

Discover and download public datasets from Kaggle, UCI, HuggingFace, and Tianchi.

32|1|Updated May 19, 2026
One-click install
npx skills add https://github.com/woodfishhhh/EZ_math_model --skill dataset
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dataset
Source: https://github.com/woodfishhhh/EZ_math_model/tree/main/skills/ez-math-model/tools/dataset
Command: npx skills add https://github.com/woodfishhhh/EZ_math_model --skill dataset

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of quickly locating and downloading suitable public datasets when a math modeling task requires you to search for external data or benchmark against historical datasets.

Core Features & Use Cases

  • Public dataset discovery across Kaggle, UCI, HuggingFace, and Tianchi when the problem explicitly asks for “find similar data” or “supplement external data”.
  • Safety guardrail to avoid using this tool when the user’s attachments already contain the needed data (prevents silently fabricating “official” results).
  • Standardized landing workflow that saves downloaded datasets into a consistent directory structure and records source/license metadata for auditability.
  • Failure diagnostics including Kaggle token guidance, license constraints reminders, large-file handling guidance, and network-restricted fallback instructions.

Quick Start

Tell the agent to find a public dataset matching the topic, download it, and save it under workdir/<task_id>/attachments/external with an accompanying SOURCES.md.

Frequently Asked Questions about dataset

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

FAQPage Schema
How do I find public datasets for math modeling tasks?

To find public datasets for math modeling, you can instruct the agent to search across Kaggle, UCI, HuggingFace, and Tianchi. The Skill downloads matching external data into a standardized attachments directory and records source provenance in SOURCES.md.

What is the best way to download external data from Kaggle or HuggingFace?

The best way to download external data from Kaggle or HuggingFace is to request the agent to find and save the dataset under a standardized external attachments path. The workflow ensures datasets are stored consistently and includes a SOURCES.md file for license and source tracking.

Can I use this tool if my attachments already contain the needed dataset?

You should not use this tool if your attachments already contain the needed dataset. A safety guardrail prevents dataset lookup when existing attachments have sufficient data, ensuring the agent avoids fabricating official results.

Why does Kaggle dataset download fail and how do I fix authentication?

Kaggle dataset downloads often fail due to missing authentication tokens. The Skill provides failure diagnostics that include Kaggle token guidance, license constraint reminders, large-file handling instructions, and network-restricted fallback steps to resolve these issues.

Does this dataset discovery tool document data provenance and license metadata?

Yes, this dataset discovery tool documents data provenance and license metadata. It automatically generates a SOURCES.md file alongside downloaded datasets in the external attachments directory, ensuring auditability for historical benchmarks.