What is the output of a profiling session?

It produces a standardized Data Profile Summary in Markdown, documenting tables, findings, and analysis implications.

Which database engines are supported by this skill?

The skill provides guidance and SQL templates for PostgreSQL, MySQL, SQLite, and SQL Server.

Why should I use this before starting a data analysis task?

Systematic profiling prevents 'garbage in, garbage out' scenarios by identifying missing values, outliers, and incorrect join assumptions before you write complex logic.

Does this skill modify or write to my database?

No, this skill is designed for read-only data exploration and profiling to understand structure and quality without altering data.

Can it handle very large tables?

Yes, it uses optimized SQL aggregation and metadata queries to provide summaries without the need to fetch entire datasets into memory.

Data Profiler & Explorer

Name: Data Profiler & Explorer
Author: tilmon-engineering

bytilmon-engineering

•

データベース管理

Automates systematic data profiling and exploration across multiple SQL database dialects.

概要

This skill provides a structured framework for understanding unfamiliar datasets through a rigorous 4-phase profiling process: schema discovery, quality assessment, distribution analysis, and relationship identification. It helps developers and data analysts eliminate guesswork by verifying data assumptions, identifying NULL patterns, and mapping foreign key relationships before performing deep analysis or writing complex queries. Whether you are using PostgreSQL, MySQL, SQLite, or SQL Server, this skill ensures your data foundation is solid and well-documented.

主な機能

Foreign key and join cardinality discovery tools
Comprehensive NULL and data quality assessment templates
4-Phase systematic profiling workflow (Schema, Quality, Distribution, Relationships)
Cross-dialect SQL support for major database engines
Time-series and categorical distribution analysis
2 GitHub stars

ユースケース

Onboarding to a new project with an unfamiliar or undocumented database schema
Auditing data quality before migrating or integrating new data sources
Troubleshooting unexpected results or anomalies in analytical queries

概要

主な機能

Foreign key and join cardinality discovery tools
Comprehensive NULL and data quality assessment templates
4-Phase systematic profiling workflow (Schema, Quality, Distribution, Relationships)
Cross-dialect SQL support for major database engines
Time-series and categorical distribution analysis
2 GitHub stars

ユースケース

Onboarding to a new project with an unfamiliar or undocumented database schema
Auditing data quality before migrating or integrating new data sources
Troubleshooting unexpected results or anomalies in analytical queries