skills.rest
AlexKapadia
AlexKapadiaCOMMUNITY
Explore all skills by this author →
GitHub

fetch-dataset-from-kaggle

Fetch Kaggle datasets into a Pixie tool's data folder with credentials.

6|1|Updated May 17, 2026
Search Tags:#automation#provenance#fetch#credentials#datasets#kaggle#tool-data
One-click install
npx skills add https://github.com/AlexKapadia/Pixie --skill fetch-dataset-from-kaggle
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fetch-dataset-from-kaggle
Source: https://github.com/AlexKapadia/Pixie/tree/main/.claude/skills/fetch-dataset-from-kaggle
Command: npx skills add https://github.com/AlexKapadia/Pixie --skill fetch-dataset-from-kaggle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Downloads a Kaggle dataset or competition into a Pixie tool's data folder using the user's Kaggle credentials. Use when the user asks to fetch, download, or import a Kaggle dataset for a named tool. Do NOT use for HuggingFace (fetch-dataset-from-huggingface), URLs (fetch-dataset-from-url), local files (import-dataset-from-local), or Kaggle notebooks.

Core Features & Use Cases

  • Securely fetch Kaggle datasets and competitions for a named Pixie tool.
  • Generate a manifest, license, and citations, and place files under tools/<tool_id>/data/datasets/<dataset_id>/files/, with provenance.
  • Enforce safety and scope rules: per-tool context, user Kaggle credentials management, and separation from other fetchers.

Quick Start

Ask Pixie to fetch a Kaggle dataset for a specified tool and store it under the tool's data/datasets directory.

Frequently Asked Questions about fetch-dataset-from-kaggle

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

FAQPage Schema
How do I download a Kaggle dataset into a Pixie tool?▼

Fetching a Kaggle dataset securely downloads the data into a named Pixie tool's data folder using your validated Kaggle credentials. This process ensures per-tool scoping and generates a manifest for provenance.

Can I import Kaggle competition data for a specific tool?▼

Yes, you can fetch Kaggle competition datasets for a named Pixie tool. The data is placed under the tool's datasets directory with proper license and citation files for provenance.

How are Kaggle credentials handled when fetching datasets?▼

Kaggle credentials are handled securely and validated during the fetch process. They are scoped per-tool to ensure safe credential management and separation from other fetchers.

Does this fetcher work with HuggingFace datasets or local files?▼

No, this fetcher is exclusively for Kaggle datasets and competitions. You should use separate fetchers for HuggingFace datasets, URLs, or local files to ensure correct data routing and scoping.

What provenance files are generated when fetching Kaggle data?▼

Fetching Kaggle data generates a manifest, license, and citations placed alongside the dataset files. This ensures full provenance tracking under the specific tool's data directory.

Related Skills

Explore More Data & Analytics Skills→
al-steval-stev

atlassian-setup

Configure Atlassian API credentials for Jira and Confluence access.

Community
Intermediate
datheredathere
3.7k

csv-wrangling

Automate CSV data wrangling workflows with qsv for indexing, profiling, transforming, and exporting.

Official
Intermediate
AradotsoAradotso
5

snowflake-dbt-airbnb-analytics

Automate ETL workflows with Snowflake, dbt, and Streamlit.

Official
Advanced
cas-bigdatalabcas-bigdatalab
541

remote_formatter

Retrieve datasets from HuggingFace Hub and format them as JSONL.

Official
Intermediate