skills.rest
Epiphytic
EpiphyticOFFICIAL
Explore all skills by this author →
WebsiteGitHub

data-validation

Validate analysis results for data quality, calculation accuracy, and reporting reliability.

7|Updated Feb 6, 2026
Search Tags:#quality assurance#analytics#data validation#sql#bias detection#reproducibility
One-click install
npx skills add https://github.com/Epiphytic/ai-plugin-translator --skill data-validation-epiphytic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-validation
Source: https://github.com/Epiphytic/ai-plugin-translator/tree/main/packages/core/test/fixtures/regression-output/knowledge-work-plugins/data/skills/data-validation
Command: npx skills add https://github.com/Epiphytic/ai-plugin-translator --skill data-validation-epiphytic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps prevent inaccurate analysis results by providing a structured review process for data quality, calculation logic, bias risks, and reproducibility before stakeholder delivery.

Core Features & Use Cases

  • Analysis QA Checklist: Reviews source selection, data freshness, null handling, joins, calculations, metrics, and presentation quality.
  • Bias and Error Detection: Identifies issues such as survivorship bias, denominator shifts, join explosions, and misleading comparisons.
  • Reproducibility Standards: Guides documentation of assumptions, methodology, queries, and validation steps for repeatable analysis workflows.

Quick Start

Use the data-validation skill to review my analysis for accuracy issues, bias risks, and reproducibility gaps.

Frequently Asked Questions about data-validation

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

FAQPage Schema
How do I validate SQL aggregations and joins before sharing analysis results?▼

To validate SQL analysis results, you need a structured QA checklist that reviews source selection, data freshness, null handling, and calculation accuracy. This ensures joins, aggregations, and metrics are verified for stakeholder delivery.

What is data validation and bias detection in analytics workflows?▼

Data validation in analytics is the process of checking data quality and calculation accuracy to identify bias risks like survivorship bias, denominator shifts, and join explosions before reporting insights to stakeholders.

How do I check my analysis for reproducibility gaps and documentation standards?▼

To check analysis reproducibility, you document assumptions, methodology, queries, and validation steps. Applying structured documentation standards ensures your data validation workflow is repeatable and transparent for future reviews.

Can this data validation process detect survivorship bias and misleading metric comparisons?▼

Yes, the data validation process detects survivorship bias, denominator shifts, join explosions, and misleading comparisons. It applies structured QA procedures to review metrics and identify calculation errors in analytics.

What is the best way to review analytics edge cases and assumptions before stakeholder delivery?▼

The best way to review analytics edge cases and assumptions is applying a structured QA checklist. This data validation process verifies calculation logic, checks data quality, and ensures reporting reliability before delivery.

Related Skills

Explore More Data & Analytics Skills→
omeraltnomeraltn

agency-analytics-reporter

Transform raw business data into analytics reports with SQL and Python.

Community
Advanced
grandahagrandaha

ai-process-assessment:building-checkpoint

Render source-traced engagement data into deterministic .docx validation documents.

Community
Advanced
travisjneumantravisjneuman
88

statistics-verifier

Verify statistical claims by auditing methodology, significance testing, and bias.

Community
Advanced
anomalyarmoranomalyarmor
1

armor-investigate

Diagnose root causes of stale data and triggered alerts using lineage and historical monitoring data.

Official
Advanced