giab-benchmark-validator
Genome in a Bottle benchmark validation skill for pipeline accuracy assessment
npx skills add a5c-ai/babysitter --skill giab-benchmark-validator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 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)
- Purpose
- Capabilities
- Usage Guidelines
- Dependencies
- Process Integration
What does the giab-benchmark-validator skill do?
Genome in a Bottle benchmark validation skill for pipeline accuracy assessment
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill giab-benchmark-validator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.