skills.rest
tmorrowdev
tmorrowdevCOMMUNITY
Explore all skills by this author →
GitHub

data-exploration

Profile tabular datasets to surface structural metadata and column-level statistics.

1|Updated Feb 26, 2026
Search Tags:#schema#exploration#data-quality#correlation#outliers#data-profiling
One-click install
npx skills add https://github.com/tmorrowdev/data-plugin --skill data-exploration-tmorrowdev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-exploration
Source: https://github.com/tmorrowdev/data-plugin/tree/main/skills/data-exploration
Command: npx skills add https://github.com/tmorrowdev/data-plugin --skill data-exploration-tmorrowdev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Give analysts a repeatable methodology to quickly understand unfamiliar tabular data by surfacing table structure, column-level quality issues, distributions, and relationship candidates so that downstream analysis is faster and more reliable.

Core Features & Use Cases

  • Table and column profiling: Row/column counts, null rates, distinct counts, top/bottom values, and basic length/pattern checks for strings.
  • Metric and temporal summaries: Percentiles, mean/median, standard deviation, date ranges, gaps, and seasonality cues for time-series data.
  • Relationship discovery & documentation: Suggest foreign-key candidates, correlations, derived/redundant columns, and produce a schema documentation template for analyst handoff.
  • Use Case: Inspect a newly provisioned analytics table to decide whether it is analysis-ready, identify required cleaning steps, and draft common query patterns.

Quick Start

Profile the attached dataset and produce a concise data quality summary with column-level statistics, top anomalies, suggested next steps, and a schema documentation stub.

Frequently Asked Questions about data-exploration

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

FAQPage Schema
How do I profile a CSV file to understand its structure and data quality?▼

To profile a CSV file, you surface structural metadata, null rates, and column-level patterns to assess data quality. This process provides row counts, distinct values, and outlier detection to determine if the dataset is analysis-ready.

What is the best way to detect outliers and null rates in tabular data?▼

The best way to detect outliers and null rates in tabular data is through column-wise statistics and distribution analysis. This approach identifies data quality issues by calculating null percentages, percentile summaries, and flagging anomalous values.

Can I use data profiling to discover foreign-key candidates in SQL warehouse results?▼

Yes, you can use data profiling to discover foreign-key candidates in sampled SQL warehouse results. The profiling process evaluates column relationships and correlations to suggest potential foreign keys and identify redundant columns.

How do I generate schema documentation for analyst handoff from an uploaded Excel file?▼

You generate schema documentation for analyst handoff by profiling the uploaded Excel file to extract structural metadata and column statistics. This produces a template schema documentation stub summarizing table structure and relationship candidates.

Does data profiling work for time-series distribution analysis and seasonality detection?▼

Yes, data profiling works for time-series distribution analysis by calculating date ranges, temporal gaps, and seasonality cues. It provides metric summaries, mean and median calculations, and standard deviation metrics for temporal data.

Related Skills

Explore More Data & Analytics Skills→
cmetechcmetech

data-analyst

Ingest CSV, Excel, or JSON files and analyze them with SQL to produce dashboards, reports, or datasets.

Community
Advanced
aimentor606aimentor606

exploration

Profile dataset structure, quality, and schema patterns across tabular, event-log, and JSON sources.

Community
Intermediate
wardawgmalviciouswardawgmalvicious
2

fabric-monitoring

Monitor and diagnose Fabric Warehouse queries using queryinsights schema and DMVs.

Community
Advanced
cy-walicy-wali

explore-data

Profile datasets to assess shape, column types, null rates, and distributions.

Community
Intermediate