data-quality-check

Name: data-quality-check
Availability: InStock
Author: shekerkamma

Validate dataset completeness and consistency before analysis workflows.

Updated May 22, 2026

Search Tags:#data integrity #data quality #data validation #consistency check #pre-analysis #completeness check #analysis prep

Ready to run

npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill data-quality-check-shekerkamma

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-quality-check
Source: https://github.com/shekerkamma/peopletech-marketplace/tree/main/plugins/ai-analyst/skills/ai-analyst/data-quality-check
Command: npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill data-quality-check-shekerkamma

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Running analysis on incomplete or inconsistent data leads to incorrect insights and poor business decisions. This skill eliminates that risk by validating your dataset's completeness and consistency before any analysis work begins, with its functionality built directly into the ask-question and run-analysis skills for seamless use.

Core Features & Use Cases

Completeness Validation: Checks for missing required fields, null values, and incomplete records across your dataset to ensure no critical data is missing.
Consistency Validation: Detects format mismatches, conflicting entries, and out-of-bound values that would skew analysis results.
Use Case: If you are pulling Q3 sales data from three different regional systems, this check catches missing region labels and mismatched currency formats before you run revenue forecasts, so you don't base strategic decisions on flawed data.

Quick Start

Use the ask-question or run-analysis skill to automatically validate your dataset's completeness and consistency before proceeding with any analysis work.

Frequently Asked Questions about data-quality-check

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

FAQPage Schema

How do I validate data completeness and consistency before running analysis?▼

Data completeness and consistency validation checks for missing required fields, null values, and format mismatches to eliminate the risk of flawed analysis outcomes from incomplete datasets. This ensures uniform formats before downstream reporting tasks begin.

Why does running revenue forecasts on data from multiple regional systems produce incorrect insights?▼

Running forecasts on multi-system data produces incorrect insights when missing region labels and mismatched currency formats skew the numbers. Validating dataset consistency beforehand catches these conflicting entries and out-of-bound values.

What is the best way to check for missing required fields and null values in pre-analysis prep?▼

The best way to check for missing required fields in pre-analysis prep is running a completeness validation process that detects incomplete records across your dataset, ensuring no critical data is missing before executing forecasting tasks.

Can I use this data validation check for operational and user datasets sourced from external systems?▼

Yes, you can use this data validation check for operational, user, and sales datasets sourced from multiple internal or external systems. It ensures all required fields are populated and data formats are uniform before analysis.

Do I need to manually configure consistency checks for mismatched currency formats in sales data?▼

No, you do not need to manually configure consistency checks for mismatched currency formats. The validation mechanism automatically detects format mismatches and conflicting entries when you use the run-analysis or ask-question workflow.