Agent Skills: GIAB Benchmark Validator Skill

Genome in a Bottle benchmark validation skill for pipeline accuracy assessment

bioinformaticsID: a5c-ai/babysitter/giab-benchmark-validator

Install this agent skill to your local

pnpm dlx add-skill https://github.com/a5c-ai/babysitter/tree/HEAD/plugins/babysitter/skills/babysit/process/specializations/domains/science/bioinformatics/skills/giab-benchmark-validator

Skill Files

Browse the full folder contents for giab-benchmark-validator.

Download Skill

Loading file tree…

plugins/babysitter/skills/babysit/process/specializations/domains/science/bioinformatics/skills/giab-benchmark-validator/SKILL.md

Skill Metadata

Name
giab-benchmark-validator
Description
Genome in a Bottle benchmark validation skill for pipeline accuracy assessment

GIAB Benchmark Validator Skill

Purpose

Enable Genome in a Bottle benchmark validation for pipeline accuracy assessment.

Capabilities

  • Truth set comparison
  • hap.py/vcfeval execution
  • Sensitivity/specificity calculation
  • Stratified performance metrics
  • Difficult region analysis
  • Validation report generation

Usage Guidelines

  • Use appropriate GIAB reference samples
  • Compare against truth sets with hap.py
  • Calculate sensitivity and specificity
  • Stratify by region type and variant class
  • Analyze performance in difficult regions
  • Generate comprehensive validation reports

Dependencies

  • hap.py
  • vcfeval
  • GIAB resources

Process Integration

  • Analysis Pipeline Validation (pipeline-validation)
  • Whole Genome Sequencing Pipeline (wgs-analysis-pipeline)