skills.rest
shekerkamma
shekerkammaCOMMUNITY
Explore all skills by this author →
GitHub

explore-data

Profile connected CSV or parquet tables with column statistics and quality flags.

Updated May 22, 2026
Search Tags:#data exploration#csv analysis#distribution analysis#dataset profiling#schema preview#data quality check
One-click install
npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill explore-data-shekerkamma
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: explore-data
Source: https://github.com/shekerkamma/peopletech-marketplace/tree/main/plugins/ai-analyst/skills/ai-analyst/explore-data
Command: npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill explore-data-shekerkamma

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the friction of working with unfamiliar datasets by providing fast, guided discovery of table structures, schemas, data quality, and available content, so you can skip tedious manual inspection and move straight to meaningful analysis.

Core Features & Use Cases

  • Interactive Dataset Overviews: List all connected tables with row counts, date ranges, key entities, and suggested starting questions when no specific table is selected.
  • Deep Table & Column Profiling: View column types, null rates, sample rows, numeric distributions, categorical value counts, and outlier detection for any specified table or column.
  • Automated Data Quality Flagging: Automatically highlight critical issues like high null rates, low cardinality, and empty tables to avoid flawed analysis.
  • SWD-Compliant Visualizations: Generate clean, professional distribution charts and outlier plots that follow consistent styling standards for clear communication.
  • Use Case: If you just connected a new sales dataset with customer, transaction, and product tables, use this Skill to quickly identify which tables have the most complete data, check for missing values in the revenue column, and preview sample rows to spot potential analysis opportunities.

Quick Start

Use the explore-data skill to get a full overview of all tables, row counts, and data quality flags in your currently connected dataset.

Frequently Asked Questions about explore-data

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

FAQPage Schema
How do I profile a CSV dataset to check data quality and schema?▼

Dataset profiling provides interactive overviews of row counts, column types, null rates, and sample rows. It automatically flags critical issues like high null rates, low cardinality, and empty tables to help you avoid flawed analysis.

What is the best way to explore an unfamiliar parquet dataset?▼

Exploring an unfamiliar parquet dataset involves generating interactive overviews of all tables with row counts, date ranges, and key entities. This provides suggested starting questions and deep column-level profiling to help you understand available content quickly.

How do I check data distributions and identify outliers in a connected table?▼

Checking data distributions and identifying outliers requires deep table and column profiling. This process evaluates numeric distributions, categorical value counts, and generates SWD-compliant visualizations like distribution charts and outlier plots for clear communication.

Can I get a quick overview of all tables without running full analytical queries?▼

Yes, you can get a quick overview of all tables without running full analytical queries. Rapid dataset discovery features list all connected tables with row counts, date ranges, key entities, and suggested starting questions for immediate understanding.

Does dataset profiling work with both CSV and parquet file formats?▼

Yes, dataset profiling works with both CSV and parquet file formats. It enables rapid discovery and understanding of the structure, content, and quality of connected datasets by applying guided discovery to preview schemas and check data distributions.

Related Skills

Explore More Data & Analytics Skills→
bcmcpherbcmcpher

gen-data-dict

Generate a JSON data dictionary describing variables in merged CSV, TSV, or Parquet datasets.

Community
Intermediate
HwFeeHwFee

data-analyst

Analyze CSV, Excel, JSON, and SQL datasets to generate visual insights and reports.

Community
Intermediate
cy-walicy-wali

explore-data

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

Community
Intermediate
marlo9981marlo9981

schema-exploration

List tables, describe columns and data types, and identify foreign keys.

Community
Intermediate