create-eda-report

Run a statistics pipeline and EDA notebook to generate JSON/CSV reports and plots.

3|Updated Jun 3, 2022
One-click install
npx skills add https://github.com/Hohlas/SoSimple --skill create-eda-report
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-eda-report
Source: https://github.com/Hohlas/SoSimple/tree/main/.kilocode/skills/create-eda-report
Command: npx skills add https://github.com/Hohlas/SoSimple --skill create-eda-report

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual, repetitive work of running project-level exploratory data analysis by orchestrating statistics gathering and notebook execution to generate ready-to-use reports and visuals.

Core Features & Use Cases

  • Automated statistics collection: runs a statistics pipeline to produce key summaries and distributions.
  • EDA notebook execution: executes the EDA notebook to generate plots and insights.
  • Output reports: creates JSON/CSV summaries such as statistics_summary.json, class_balance_report.csv, feature_distributions.csv, and an executed notebook with visuals.

Quick Start

Initiate the full EDA workflow for your dataset by invoking the analyze trigger.

Frequently Asked Questions about create-eda-report

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

FAQPage Schema
How do I automate exploratory data analysis for my project dataset?

To automate exploratory data analysis, this Skill orchestrates a statistics pipeline and executes an EDA notebook to generate structured summaries, visualizations, and ready-to-use reports without manual intervention.

What outputs are generated by an automated EDA notebook execution?

Automated EDA notebook execution produces JSON and CSV summaries such as statistics_summary.json, class_balance_report.csv, and feature_distributions.csv, alongside an executed notebook containing generated visual plots.

Do I need a statistics.py script to run automated project-level data analysis?

Yes, the workflow validates and executes a statistics.py step to collect key summaries and distributions before running the EDA notebook, ensuring project-level data analysis tasks have the required statistical foundation.

Can I use this to generate class balance reports and feature distributions automatically?

Yes, you can automatically generate class balance reports and feature distributions by triggering the workflow, which runs the statistics pipeline to produce these specific CSV outputs for your dataset.

What is the best way to run a statistics pipeline and EDA notebook together?

The best way to run a statistics pipeline and EDA notebook together is to invoke the analyze trigger, which coordinates both steps to validate execution and produce structured summaries alongside visual reports.