sweetviz-3-dataset-comparison-compare
About
This skill enables automated comparison of two datasets (like train/test splits) using Sweetviz to generate detailed visual reports. It helps developers quickly identify distribution differences, missing values, and statistical variations between datasets. Use it during exploratory data analysis to validate dataset splits and detect data drift.
Quick Install
Claude Code
Recommendednpx skills add vamseeachanta/workspace-hub -a claude-code/plugin add https://github.com/vamseeachanta/workspace-hubgit clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/sweetviz-3-dataset-comparison-compareCopy and paste this command in Claude Code to install this skill
GitHub Repository
Related Skills
autoviz
OtherAutoViz automates exploratory data analysis with a single line of code, generating comprehensive visualizations and detecting patterns like correlations and outliers. It automatically selects chart types, handles both categorical and numerical features, and can export reports to HTML or Jupyter notebooks. Use this skill for rapid, automated EDA to understand your dataset's structure and key insights before deeper analysis.
bsee-sodir-extraction
OtherThis skill extracts and processes offshore energy data from the BSEE (Gulf of Mexico) and SODIR (Norway) regulatory databases. Use it to programmatically access production metrics, well information, field data, and HSE records for analysis. It supports tasks like economic modeling, compliance tracking, and comprehensive energy data aggregation.
streamlit-3-layout-and-organization
OtherThis skill provides Streamlit layout components for organizing dashboard interfaces. It covers creating multi-column layouts with adjustable ratios and implementing sidebar navigation with interactive widgets. Use it when you need to structure complex Streamlit applications with clear visual organization.
ydata-profiling-1-basic-profile-report-generation
OtherThis skill generates comprehensive data quality reports from pandas DataFrames using ydata-profiling. It creates interactive HTML reports with statistical summaries, visualizations, and data quality assessments. Developers should use it for initial exploratory data analysis to quickly understand dataset structure, distributions, and potential issues.
