Profile numeric and categorical variables and generate an EDA audit summary.
npx skills add https://github.com/qa-aman/claude-skills --skill eda-report
Please help me install this Agent Skill. Skill: eda-report Source: https://github.com/qa-aman/claude-skills/tree/main/skills/by-role/data-scientist/eda-report Command: npx skills add https://github.com/qa-aman/claude-skills --skill eda-report
Automates exploratory data analysis and reporting to help analysts quickly understand a dataset's quality, structure, and key statistics before modeling or decision making.
Load your dataset and run the EDA workflow to produce a structured report.
High-intent search queries and answers about installing and using this skill.
Automating exploratory data analysis reporting involves loading your CSV or Excel dataset to automatically profile variables, detect data quality issues, and output a structured summary with distribution insights and an audit log.
A structured EDA report includes data quality notes, numeric and categorical variable profiling, distribution and correlation insights, top variable insights, and recommended next steps for analytics projects.
Yes, you can use this EDA workflow to detect data quality issues by profiling variables to surface missing values, outliers, wrong types, and cardinality, generating an audit-ready summary for your dataset.
The best way to profile numeric and categorical columns is running an automated EDA workflow that surfaces distribution, skew, and cardinality, delivering concise variable insights and recommended next steps.
No specific dependencies are required to generate a data quality audit log. You simply load your CSV or Excel dataset and run the EDA workflow to produce the audit log and summary.
You need exploratory data analysis before modeling or decision making to quickly understand a dataset's quality, structure, and key statistics, ensuring your data is ready for downstream analytics tasks.
JayRHaClean messy tabular datasets with pandas using auditable transformation steps.
dtbuchholzStructure data science tasks with EDA, statistical analysis, and model development.
jadzoghaibGenerate statistical graphics with seaborn and matplotlib for data exploration.
WynterJonesAnalyze datasets to produce statistical summaries and data-driven reports.
