Profile tabular data and generate an HTML EDA report.
npx skills add https://github.com/Kamalyunus/claude-skills --skill eda-kamalyunus
Please help me install this Agent Skill. Skill: eda Source: https://github.com/Kamalyunus/claude-skills/tree/main/eda Command: npx skills add https://github.com/Kamalyunus/claude-skills --skill eda-kamalyunus
The EDA skill helps users explore, profile, and understand tabular data for data science or ML tasks, turning raw data into actionable insights that inform modeling decisions.
Upload a tabular dataset (CSV, Excel, Parquet) and ask me to analyze its structure, quality, and relationships to generate an actionable EDA report.
High-intent search queries and answers about installing and using this skill.
To perform exploratory data analysis on a CSV file, you upload the dataset and request a structural, quality, and relationship assessment. The skill profiles univariate distributions, detects anomalies, and outputs an actionable HTML report.
Data leakage detection during data profiling identifies features that improperly reveal the target variable, compromising model validity. This skill scans tabular datasets to uncover missingness mechanisms and target leakage, ensuring modeling readiness before training.
Yes, you can run data quality checks and anomaly detection on Excel or Parquet datasets. The skill accepts these formats natively, auditing missingness mechanisms and identifying anomalies to generate a comprehensive data understanding report.
To analyze data drift and feature correlations in tabular data, the skill evaluates distribution shifts and inter-feature relationships. It synthesizes these findings into a modeling roadmap, highlighting necessary cleaning steps and structural insights.
You need univariate profiling and target analysis for machine learning preparation when transitioning from raw data to model-ready features. This skill maps feature distributions and target relationships, flagging quality issues to guide your cleaning strategy.
dathereConvert tabular data files between CSV, TSV, Excel, JSONL, and Parquet formats.
JonathanMitchell1234Perform data cleaning, feature engineering, and statistical modeling with pandas and scikit-learn.
Veloxia-agencyAudit CSV datasets for completeness, consistency, validity, uniqueness, and timeliness.
Casper-StudiosAnalyze CSV datasets with statistics, quality checks, and visualizations.
