create-data-package

Organize biomedical dataset files into structured data packages with manifests.

7|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/epiblastai/homeobox --skill create-data-package
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-data-package
Source: https://github.com/epiblastai/homeobox/tree/main/packages/polycomb/skills/create-data-package
Command: npx skills add https://github.com/epiblastai/homeobox --skill create-data-package

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires polycomb, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps turn scattered biomedical data files into a structured, discoverable data package ready for agent-based standardization and alignment, without modifying the source file contents.

Core Features & Use Cases

  • File Discovery and Download: Locate and download supported files from sources such as GEO, including supplementary datasets and metadata.
  • Data Classification: Organize files as observations, variables, matrices, libraries, or other informational resources, with feature spaces assigned where appropriate.
  • Collection Assembly: Create datasets and collections, coalesce files into a consistent directory layout, and write a manifest that records the package structure.
  • Use Case: Prepare a GEO single-cell experiment by downloading its data, extracting observation and variable tables from an AnnData file, adding publication metadata, and packaging everything for downstream harmonization.

Quick Start

Provide a dataset URL or local path and ask the skill to download the relevant files, organize them into datasets with appropriate tags, and create the collection manifest.

Frequently Asked Questions about create-data-package

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

FAQPage Schema
How do I organize biomedical dataset files from GEO into a structured package?

You can package single-cell matrices and metadata tables from GEO by downloading the relevant files, classifying them into datasets, and writing a collection manifest that records the package structure for downstream harmonization.

What is data packaging for single-cell experiments and why is it needed?

Data packaging for single-cell experiments is the process of structuring scattered research files into discoverable collections, which is needed to prepare raw data for reliable downstream standardization and alignment without modifying source contents.

Can I extract observation and variable tables from an AnnData file for dataset organization?

Yes, the skill supports extracting observation and variable tables from an AnnData file, classifying them appropriately, and adding them to the collection assembly for reliable downstream analysis.

Does data packaging require the polycomb Collection API to validate biomedical datasets?

Yes, biomedical data packaging requires the polycomb Collection API to download, classify, coalesce, validate, and manifest collection contents using supported file-format workflows.

What types of supplementary resources can be included when I package biomedical data?

When packaging biomedical data, you can include single-cell matrices, metadata tables, libraries, array files, publications, and supplementary resources sourced from GEO and similar research repositories.