data-validation

Name: data-validation
Availability: InStock
Author: jaimedhenriques

Validate analyses for methodological errors, accuracy issues, and bias.

Updated Apr 1, 2026

Search Tags:#methodology #validation #qa #analysis #bias detection #reproducibility

Ready to run

npx skills add https://github.com/jaimedhenriques/finsyt --skill data-validation-jaimedhenriques

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-validation
Source: https://github.com/jaimedhenriques/finsyt/tree/main/artifacts/platform/.agents/skills/data-validation
Command: npx skills add https://github.com/jaimedhenriques/finsyt --skill data-validation-jaimedhenriques

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you review an analysis for mistakes, weak methodology, and hidden bias before it reaches stakeholders.

Core Features & Use Cases

Methodology Review: Checks whether the analysis approach, assumptions, and aggregation logic are sound.
Accuracy Verification: Confirms calculations, comparisons, and reported results are internally consistent.
Bias Detection: Looks for survivorship bias, selection bias, and other distortions that could mislead decisions.
Use Case: Use it when preparing a report, validating a dashboard summary, or sanity-checking a research note before publication.

Quick Start

Ask the Skill to review this analysis for methodological errors, accuracy issues, and bias before you share it 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 check my data analysis for methodological errors before sharing?▼

Bias detection in analytical reports identifies survivorship bias and selection bias to prevent distorted conclusions. It checks aggregation logic and calculation consistency to ensure reported results do not mislead stakeholders before publication.

How do I verify calculation consistency and reproducibility in a research note?▼

To review a dashboard summary for accuracy, confirm that calculations, comparisons, and reported results are internally consistent. This accuracy verification step ensures aggregation logic is sound and reproducible before the dashboard reaches stakeholders.

What is the best way to detect survivorship bias in a dataset?▼

Detecting survivorship bias in a dataset involves reviewing the analysis for selection biases and distortions that could mislead decisions. This bias detection ensures that only successful entities are not disproportionately represented in the final reported results.

Does this validation process work for reviewing stakeholder-facing dashboards?▼

Yes, this validation process works for reviewing stakeholder-facing dashboards. It applies to review workflows for reports and dashboards by checking aggregation logic, calculation consistency, and potential survivorship bias before the analytical work is shared.

What are the limitations of using automated validation for analytical reports?▼

A limitation of automated validation is that it requires the user to provide the full analytical context to effectively check methodology and reproducibility. It cannot detect external data sourcing errors or biases outside the provided analysis scope.