pbi-data-cleaning

Profile Power BI semantic model columns and build a six-dimension trust scorecard.

Updated Aug 23, 2026

Search Tags:#profiling #data-quality #data-cleaning #outliers #trust-score #power-bi #missingness

Ready to run

npx skills add https://github.com/fabioc-aloha/PBI-Visual-Assistant --skill pbi-data-cleaning

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pbi-data-cleaning
Source: https://github.com/fabioc-aloha/PBI-Visual-Assistant/tree/main/.github/skills/pbi-data-cleaning
Command: npx skills add https://github.com/fabioc-aloha/PBI-Visual-Assistant --skill pbi-data-cleaning

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guide users through data cleaning analysis in business language. Scan for missingness, outliers, duplicates, type inconsistencies, and date quality issues. Build a trust scorecard before visualization to ensure decisions are based on reliable data.

Core Features & Use Cases

Profiles data columns to surface types, cardinality, and nulls.
Scan missingness and placeholders, detect outliers, and identify duplicates.
Check type consistency and date quality to catch formatting issues and time-related anomalies.
Build and interpret a 6-dimension trust scorecard (Completeness, Consistency, Uniqueness, Validity, Relationships, Timeliness) to guide visualization readiness.

Quick Start

Ask the assistant to run a comprehensive data cleaning analysis on your Power BI semantic model.

Frequently Asked Questions about pbi-data-cleaning

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

FAQPage Schema

How do I run a data cleaning analysis on a Power BI semantic model?▼

You can initiate data cleaning by asking the assistant to run a comprehensive analysis on your Power BI semantic model. This scans for missingness, outliers, duplicates, and type inconsistencies to ensure your data is ready for visualization.

What is a trust scorecard in Power BI data cleaning?▼

A trust scorecard in data cleaning evaluates visualization readiness across six dimensions: Completeness, Consistency, Uniqueness, Validity, Relationships, and Timeliness. It guides you to ensure decisions are based on reliable, high-quality data before reporting.

How do I detect outliers and missingness in Power BI datasets?▼

Detect outliers and missingness in Power BI datasets by applying data profiling and scanning techniques. This identifies nulls, placeholder values, and statistical anomalies to help surface data quality issues before visualization.

Can I check type consistency and date quality in Power BI without external tools?▼

Yes, you can check type consistency and date quality directly within your Power BI workflow. The analysis evaluates formatting issues, catches time-related anomalies, and ensures type consistency across datasets to prevent visualization errors.

When do I need data profiling before visualizing Power BI reports?▼

You need data profiling before visualizing Power BI reports when you must ensure decisions are based on reliable data. Profiling surfaces column types, cardinality, and nulls to catch hidden quality issues early in the pipeline.