Does it support standardized data outputs?

Yes, it enforces a specific output format for both data tables (TSV) and graphical assets (PNG with specific DPI settings) to ensure your results are always professional and ready for reports.

How does this skill improve my AI coding workflow?

It eliminates boilerplate code and manual setup by enforcing best practices for data integrity, high-resolution visualization standards, and structured TSV output formatting for reproducibility.

What specific capabilities does it provide?

It automates missing value checks, calculates key statistics (mean, std, median), generates 300 DPI high-resolution figures, and follows a rigorous quality assurance checklist for data accuracy.

When should I use this skill?

Use this skill when you need to perform consistent exploratory data analysis (EDA), generate automated statistical summaries, or create production-quality distribution charts from raw data files.

What does the Example Analysis Skill do?

This skill provides Claude with a standardized framework for data preparation, statistical analysis, and professional visualization using Python libraries like Pandas, NumPy, and Matplotlib.

Example Analysis Skill

Name: Example Analysis Skill
Author: nakkulla

bynakkulla

データサイエンスとML

Provides a standardized workflow for data preparation, exploratory analysis, and high-quality visualization using Python libraries.

概要

Acts as a foundational template for data science workflows within Claude Code, offering structured guidance for analyzing datasets from scratch. It leads users through a comprehensive process involving data cleaning with Pandas, statistical computation with NumPy, and the creation of publication-quality figures with Matplotlib. This skill is particularly useful for maintaining consistency across analytical tasks by enforcing best practices for data quality, reproducibility through random seeds, and systematic documentation of findings.

主な機能

Standardized data preparation and exploration procedures using Pandas and NumPy
Comprehensive quality assurance checklists for data integrity and statistical assumptions
Production-grade visualization templates for generating high-resolution distribution charts
Automated statistical analysis workflows for calculating means, standard deviations, and medians
0 GitHub stars
Standardized output formatting for TSV result tables and graphical assets

ユースケース

Creating reproducible data science pipelines with structured documentation and quality checks
Generating consistent statistical reports and visual charts for business or research projects
Performing initial exploratory data analysis on raw CSV or tabular datasets

概要

主な機能

Standardized data preparation and exploration procedures using Pandas and NumPy
Comprehensive quality assurance checklists for data integrity and statistical assumptions
Production-grade visualization templates for generating high-resolution distribution charts
Automated statistical analysis workflows for calculating means, standard deviations, and medians
0 GitHub stars
Standardized output formatting for TSV result tables and graphical assets

ユースケース

Creating reproducible data science pipelines with structured documentation and quality checks
Generating consistent statistical reports and visual charts for business or research projects
Performing initial exploratory data analysis on raw CSV or tabular datasets