skills.rest
thbraet
thbraetCOMMUNITY
Explore all skills by this author →
GitHub

explore-data

Generate a Jupyter notebook and CRISP-DM summary document from exploratory data analysis.

Updated Mar 20, 2026
Search Tags:#visualization#eda#notebook#feature-engineering#exploratory-data-analysis#crisp-dm#data-understanding
One-click install
npx skills add https://github.com/thbraet/claude-template --skill explore-data-thbraet
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: explore-data
Source: https://github.com/thbraet/claude-template/tree/main/skills/explore-data
Command: npx skills add https://github.com/thbraet/claude-template --skill explore-data-thbraet

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill performs advanced exploratory data analysis to reveal patterns, anomalies, and hypotheses that drive feature engineering and model decisions within CRISP-DM workflows.

Core Features & Use Cases

  • Univariate, bivariate, and multivariate analyses with structured outputs.
  • Temporal pattern detection and subgroup analysis for complex datasets.
  • Generates a working notebook (notebooks/2.3-data-exploration.ipynb) and a CRISP-DM style summary document for documentation and reproducibility.

Quick Start

Provide a dataset path or name and run explore-data to generate the notebook and the CRISP-DM summary artifact.

Frequently Asked Questions about explore-data

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

FAQPage Schema
How do I perform exploratory data analysis for CRISP-DM data understanding?▼

Generate a comprehensive EDA report by providing a dataset path to this skill, which outputs a working Jupyter notebook with visualizations and a CRISP-DM style summary markdown document for feature engineering readiness.

Can I use this skill to detect temporal patterns in time-series data?▼

Yes, temporal pattern detection is supported for time-series datasets. The skill performs temporal analysis alongside subgroup analysis to reveal complex data patterns and inform modeling decisions within your CRISP-DM workflow.

Does exploratory data analysis output a reproducible notebook for feature engineering?▼

The skill generates a reproducible Jupyter notebook containing code, visualizations, and narrative, alongside a CRISP-DM summary document at docs/crisp-dm/2-data-understanding/2.3-data-exploration.md for documentation.

What is the best way to document bivariate and subgroup analysis for modeling decisions?▼

Document bivariate and subgroup analyses by generating a CRISP-DM style summary markdown file. This skill automatically produces the summary alongside a working notebook to capture patterns, anomalies, and modeling decisions.

Do I need any specific dependencies to run exploratory data analysis on my dataset?▼

No specific dependencies are required to run the exploratory data analysis. You simply provide a dataset path or name to generate the EDA notebook and CRISP-DM summary artifacts for your data understanding phase.

Related Skills

Explore More Data & Analytics Skills→
KaranKathur06KaranKathur06

data-science-expert

Convert raw tabular and time-series data into modeling-ready datasets with statistical analysis.

Community
Advanced
vignesh2027vignesh2027
6

data-scientist-pro

Run end-to-end data science workflows from EDA to SHAP interpretation.

Community
Advanced
thbraetthbraet

build-model

Automate CRISP-DM 4.3 model building with MLflow tracking and documentation.

Community
Advanced
thbraetthbraet

collect-initial-data

Document data acquisition and initial inventories for CRISP-DM workflows.

Community
Intermediate