Personal Genomics

Analyze local DNA data against reference datasets to generate health and ancestry reports.

15|1|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/wkyleg/personal-genomics --skill personal-genomics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Personal Genomics
Source: https://github.com/wkyleg/personal-genomics/tree/main
Command: npx skills add https://github.com/wkyleg/personal-genomics --skill personal-genomics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, reportlab, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill empowers individuals to analyze their raw DNA data locally, providing deep insights into health risks, pharmacogenomics, ancestry, and traits without compromising privacy.

Core Features & Use Cases

  • Comprehensive Health Analysis: Understand genetic predispositions for diseases, carrier statuses, and health risks.
  • Personalized Pharmacogenomics: Discover how your genes affect medication response and metabolism.
  • Detailed Ancestry & Traits: Explore your deep ancestry signals and understand genetic influences on physical traits.
  • Use Case: Upload your 23andMe or AncestryDNA data to get a detailed report on your genetic predispositions to conditions like heart disease, your response to common medications, and insights into your ancestral origins.

Quick Start

Analyze my DNA file located at ~/Downloads/genome.txt.

Frequently Asked Questions about Personal Genomics

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

FAQPage Schema
How do I analyze raw DNA data locally for health risks and ancestry?

Local DNA analysis processes your raw genome file entirely on your machine using Python scripts and reference datasets like 1000 Genomes and ClinVar. It evaluates over 1600 validated markers across 30 categories to produce a detailed health and ancestry report.

Can I check pharmacogenomics and disease risk from 23andMe data?

Yes, you can check pharmacogenomics and disease risk from 23andMe data by providing your raw genome text file to the local scripts. The analysis cross-references your data with PharmGKB and GWAS Catalog to identify medication responses and genetic predispositions.

Does local DNA analysis work with pandas and numpy?

Local DNA analysis requires pandas and numpy to run the Python scripts that process your genetic data. These libraries handle the numerical operations and data manipulation needed to evaluate genetic markers and generate your report.

What is the best way to generate a private DNA analysis report?

The best way to generate a private DNA analysis report is by running local Python scripts that use reportlab to build the document. This ensures your raw genetic data never leaves your machine while producing a detailed breakdown of your haplogroups and carrier status.

What reference datasets are needed for comprehensive genetic data analysis?

Comprehensive genetic data analysis requires reference datasets including 1000 Genomes, HGDP, SGDP, ClinVar, PharmGKB, and GWAS Catalog. These datasets provide the validated baseline markers used to determine your ancestry, disease risk, and pharmacogenomic profile.