Agent skill · data analytics · aj-geddes
Exploratory Data Analysis
Discover patterns, distributions, and relationships in data through visualization, summary statistics, and hypothesis generation for exploratory data analysis, data profiling, and initial insights
Why this skill is useful
Provides specific Python code snippets for conducting exploratory data analysis that the AI wouldn't reliably generate on its own.
What it needs
Requires matplotlib, numpy, pandas, seaborn installed locally. About 3k tokens when loaded. Last updated 2026-03-04. 307 stars on the source repository.
What this skill does
Exploratory Data Analysis (EDA) Overview Exploratory Data Analysis (EDA) is the critical first step in data science projects, systematically examining datasets to understand their characteristics, identify patterns, and assess data quality before formal modeling. Core Concepts Data Profiling: Understanding basic statistics and data types Distribution Analysis: Examining how variables are distributed Relationship Discovery: Identifying patterns between variables Anomaly Detection: Finding outliers and unusual patterns Data Quality Assessment: Evaluating completeness and consistency When to Use Starting a new dataset analysis Understanding data before modeling Identifying data quality issues Generating hypotheses for testing Communicating insights to stakeholders Implementation with Python Advanced EDA Techniques Key Questions to Ask 1. What are the data dimensions and types? 2. How are key variables distributed? 3. What patterns exist between variables? 4. Are there obvious data quality issues? 5. What outliers or anomalies exist? 6. What hypotheses can we generate? Best Practices Start with data profiling before visualization Check data types and missing values early Visualize distributions before jumping to analysis Document interesting findings and anomalies Create summaries for stakeholder communication Use domain knowledge to interpret patterns Common Pitfalls Skipping data quality checks Over-interpreting patterns in small datasets Ignoring domain context Insufficient data visualization Not documenting findings systematically Deliverables Data quality report with missing values and duplicates Summary statistics and distribution charts Correlation and relationship visualizations List of notable patterns and anomalies Hypotheses for further investigation Data cleaning recommendations
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aj-geddes/exploratory-data-analysis