skills.rest
shanelindsay
shanelindsayCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

exploratory-data-analysis

Automate exploratory data analysis on tabular datasets and generate JSON results with a Markdown report.

2|Updated Oct 29, 2025
Search Tags:#visualization#eda#data-quality#data-profiling#exploratory-data-analysis#statistical-summaries
One-click install
npx skills add https://github.com/shanelindsay/agentic-r --skill exploratory-data-analysis-shanelindsay
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/shanelindsay/agentic-r/tree/main/skills/scientific-thinking/exploratory-data-analysis
Command: npx skills add https://github.com/shanelindsay/agentic-r --skill exploratory-data-analysis-shanelindsay

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, matplotlib, seaborn, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Exploratory Data Analysis (EDA) is essential for understanding data structure, quality, and relationships, and this toolkit automates the computation of summaries, distributions, correlations, outliers, and reports to save time and improve reliability.

Core Features & Use Cases

  • Automated statistical summaries for numeric and categorical variables
  • Missing data patterns, data-quality metrics, and outlier detection
  • Distribution analyses and correlation exploration
  • Markdown-ready report generation and visualization assets
  • Supports CSV, Excel, JSON, Parquet, TSV, and other common tabular formats

Quick Start

Provide a dataset to analyze and run the EDA workflow to produce a JSON analysis and markdown-ready report.

Frequently Asked Questions about exploratory-data-analysis

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

FAQPage Schema
How do I automate exploratory data analysis on a CSV or Parquet dataset?▼

How do I generate statistical summaries and data profiling reports for tabular data?

How do I generate statistical summaries and data profiling reports for tabular data?▼

To generate statistical summaries and data profiling reports, the toolkit analyzes numeric and categorical variables to detect missing data patterns, outliers, and distributions. It automatically produces visualization assets and a Markdown report template for immediate integration.

Does this data profiling workflow support JSON and Excel file formats?▼

What is the best way to detect outliers and missing data patterns in a dataframe?

What is the best way to detect outliers and missing data patterns in a dataframe?▼

The best way to detect outliers and missing data patterns is to apply automated statistical profiling using pandas and scipy. This approach identifies data-quality metrics and distribution anomalies, saving results as a structured JSON file for programmatic access.

Do I need Python data visualization libraries installed for EDA report generation?▼

Can I export exploratory data analysis results as a Markdown report?

Can I export exploratory data analysis results as a Markdown report?▼

Yes, you can export exploratory data analysis results as a Markdown report. The workflow generates a Markdown-ready report template alongside a JSON analysis file, allowing you to seamlessly integrate data-quality metrics and distribution insights into your documentation.

Related Skills

Explore More Data & Analytics Skills→
xiechyxiechy
3

exploratory-data-analysis

Analyze tabular datasets to generate profiling, statistics, and markdown reports.

Community
Intermediate
citedycitedy
31

Analytics Reporter

Transform raw marketing and business data into actionable insights.

Official
Advanced
dtbuchholzdtbuchholz

analyze-data

Automate data analysis with parallel agents for distribution, missing data, correlation, and outliers.

Community
Advanced
Mohamed-ElkahefMohamed-Elkahef

csv-data-visualizer

Generate interactive Plotly visualizations and statistical profiles from CSV datasets.

Community
Intermediate