skills.rest
swarm-ai-research
swarm-ai-researchOFFICIAL
Explore all skills by this author →
Website𝕏@ResearchSwarmAIGitHub

Programmatic EDA

Profile local CSV, Parquet, and Excel datasets with pandas and numpy, outputting Markdown reports.

Updated Jun 3, 2026
Search Tags:#data#profiling#report#eda#outliers#nulls
One-click install
npx skills add https://github.com/swarm-ai-research/aeon --skill programmatic-eda-swarm-ai-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Programmatic EDA
Source: https://github.com/swarm-ai-research/aeon/tree/main/skills/programmatic-eda
Command: npx skills add https://github.com/swarm-ai-research/aeon --skill programmatic-eda-swarm-ai-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Systematic exploratory data analysis on a dataset to surface structure, nulls, outliers, distributions, and correlations, and to produce a shareable profiling report.

Core Features & Use Cases

  • Structural overview: shape, memory, data types, and a sample of rows.
  • Null profiling: identify and quantify missing values per column with threshold guidance.
  • Outlier detection: flag potential anomalies using IQR and z-score methods.
  • Distribution & correlation exploration: generate descriptive statistics, histograms, and correlation checks to surface relationships.
  • Report generation: deliver a Markdown report and a findings summary that can be shared with stakeholders.

Quick Start

Run the programmatic-eda workflow on a dataset path to generate a structural overview, nulls, outliers, distributions, correlations, and a findings report.

Frequently Asked Questions about Programmatic EDA

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

FAQPage Schema
How do I automate EDA on a CSV file in Python?▼

Automate EDA on a CSV file by running the programmatic workflow to compute structural overviews, nulls, outliers, distributions, and correlations, outputting a Markdown report. It requires Python with pandas and numpy installed.

What is the best way to check data quality and missing values in a dataset?▼

Data quality checks identify and quantify missing values per column with threshold guidance using automated null profiling. This surfaces structural issues and missing data patterns to help you prepare datasets for analysis.

Can I use pandas to detect outliers in Excel and Parquet files?▼

Yes, you can detect outliers in Excel and Parquet files using pandas by flagging potential anomalies with IQR and z-score methods. The workflow processes local files to surface distribution anomalies and data quality issues.

Does exploratory data analysis include correlation and distribution reporting?▼

Exploratory data analysis includes correlation and distribution reporting by generating descriptive statistics, histograms, and correlation checks. This surfaces relationships within the dataset and delivers a shareable Markdown findings summary.

Do I need numpy and pandas installed to generate a data profiling report?▼

Yes, you need numpy and pandas installed to generate a data profiling report. The included scripts rely on these Python libraries to compute overviews, nulls, distributions, correlations, and reporting templates.

Related Skills

Explore More Data & Analytics Skills→
xiechyxiechy
3

dask

Parallelize pandas and NumPy workflows with Dask DataFrames and Arrays.

Community
Intermediate
TurnaboutHeroTurnaboutHero
12

researcher

Analyze cross-repository patterns to inform strategic research decisions.

Community
Intermediate
yangqiongyangqiong

Data Visualization Skill

Generate line, bar, scatter, histogram, box, and heatmap plots with Matplotlib and Seaborn.

Community
Intermediate
nahisahonahisaho
3

scientific-data-profiling

Profile datasets with ydata-profiling and Great Expectations to generate EDA reports and quality scores.

Community
Advanced