exploratory-data-analysis

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

3|Updated Oct 26, 2025
One-click install
npx skills add https://github.com/xiechy/climate-ai --skill exploratory-data-analysis-xiechy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/xiechy/climate-ai/tree/main/scientific-thinking/exploratory-data-analysis
Command: npx skills add https://github.com/xiechy/climate-ai --skill exploratory-data-analysis-xiechy

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?

This Skill provides an end-to-end toolkit for exploratory data analysis, enabling automatic data profiling, visualization, and markdown reporting to accelerate data understanding.

Core Features & Use Cases

  • Comprehensive data analysis: auto-loads and analyzes multiple formats; generates descriptive statistics and data quality insights.
  • Visualizations: correlation heatmaps, distribution plots, time-series, and categorical analyses.
  • Markdown report: Creates a ready-to-share, markdown-formatted report summarizing findings.

Quick Start

Provide a dataset file (CSV, Excel, JSON, Parquet) to analyze with the tool. Run the analysis:

  • python scripts/eda_analyzer.py <data_file_path> -o <output_directory> Generate visuals:
  • python scripts/visualizer.py <data_file_path> -o <output_directory>/eda_visualizations Review or export the markdown report template at assets/report_template.md and populate with insights.

Frequently Asked Questions about exploratory-data-analysis

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

FAQPage Schema
How do I generate exploratory data analysis reports from CSV and Excel files?

Exploratory data analysis automates profiling, visualization, and markdown reporting for tabular data. Run the analyzer on your CSV, Excel, JSON, or Parquet file to generate descriptive statistics, data quality metrics, correlation heatmaps, distribution plots, and a structured markdown report summarizing findings.

What data formats does exploratory data analysis support?

The analyzer auto-detects and processes CSV, Excel, JSON, and Parquet formats. It handles numeric and categorical summaries, missing-data analysis, outlier detection, and quality checks across all supported formats in a single workflow.

Can I use pandas and matplotlib for data profiling and visualization?

Yes. This Skill leverages pandas, numpy, scipy, matplotlib, and seaborn to profile data, compute statistics, detect outliers, assess distributions and correlations, and generate publication-ready visualizations alongside insights.

How do I create markdown reports from data analysis results?

The Skill automatically generates a markdown-formatted report template populated with profiling results, quality metrics, and insights. Export or customize the template at assets/report_template.md to create ready-to-share documentation of your analysis.

What's included in the data quality checks and profiling output?

Data profiling covers missing-data analysis, numeric and categorical summaries, distribution and correlation assessments, outlier detection, and quality metrics. Output includes visualizations, structured metadata, and a comprehensive markdown report summarizing all findings.

Do I need coding skills to run exploratory data analysis on my dataset?

Basic command-line familiarity is required to execute the analyzer and visualizer scripts with file paths and output directories. No advanced programming is needed; the Skill handles auto-detection, analysis, and report generation end-to-end.