data-validation

Validate data analyses for accuracy, bias, and aggregation logic.

1|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/kiryteo/opencode-setup --skill data-validation-kiryteo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-validation
Source: https://github.com/kiryteo/opencode-setup/tree/main/skills/data-validation
Command: npx skills add https://github.com/kiryteo/opencode-setup --skill data-validation-kiryteo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

QA analyses before sharing with stakeholders — ensure accuracy, detect bias, and verify aggregation logic for reproducibility and credibility.

Core Features & Use Cases

  • Pre-Delivery QA Checklist: A structured checklist to verify data sources, freshness, completeness, null handling, deduplication, and filter correctness.
  • Calculation & Presentation Checks: Validate aggregation logic, denominators, date alignment, and ensure charts/tables accurately reflect data.
  • Documentation & Reproducibility: Produce clear documentation templates to support audit trails and governance.

Quick Start

Review the data-analysis results using the Pre-Delivery QA Checklist before sharing with stakeholders.

Frequently Asked Questions about data-validation

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

FAQPage Schema
How do I run QA checks on data analysis results before sharing them with stakeholders?

To run QA checks on data analysis results, apply a structured pre-delivery checklist that verifies data sources, completeness, null handling, and deduplication to ensure accuracy and reproducibility before sharing with stakeholders.

What is survivorship bias detection in data validation and when do I need it?

Survivorship bias detection in data validation identifies hidden skew from filtered-out populations in model outputs and reports. You need it during pre-delivery QA to verify aggregation logic and ensure data credibility.

How do I validate aggregation logic and denominators in reports for accuracy?

To validate aggregation logic and denominators in reports, check calculation and presentation accuracy by verifying date alignment, confirming denominator values, and ensuring charts and tables accurately reflect the processed data.

Can I create reproducible documentation for data quality checks and audit trails?

Yes, you can create reproducible documentation for data quality checks by using standardized documentation templates that support audit trails and governance, ensuring your validation process and reporting remain fully traceable.

What is the best way to check data freshness and filter correctness before delivering an analysis?

The best way to check data freshness and filter correctness is to systematically review data sources against a structured QA checklist, verifying query filters and data recency to guarantee pre-delivery analysis accuracy and reproducibility.

Does data validation work for model outputs and reports or just raw datasets?

Data validation works for model outputs and reports, as well as pre-delivery analyses. It applies structured checklists to verify data quality, detect survivorship bias, and validate aggregation logic across all output formats.