# Giab Benchmark Validator

> Giab Benchmark Validator is an Agent Skill for testing & quality published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Genome in a Bottle benchmark validation skill for pipeline accuracy assessment

- Skill name: `giab-benchmark-validator`
- Category: [Testing & Quality](https://www.openparable.com/skill/testing-quality/1)
- Source: https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/domains/science/bioinformatics/skills/giab-benchmark-validator/SKILL.md
- Repository: a5c-ai/babysitter (1,548 GitHub stars when collected)

## SKILL.md

# 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)

---

Source: https://www.openparable.com/skill/testing-quality/giab-benchmark-validator (OpenParable). Cite the canonical URL above.
