data-analyzer

Conduct exploratory data analysis on structured data files with pandas, numpy, and scipy.

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/ckt520728/claude-skills --skill data-analyzer-ckt520728
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analyzer
Source: https://github.com/ckt520728/claude-skills/tree/main/data-analyzer
Command: npx skills add https://github.com/ckt520728/claude-skills --skill data-analyzer-ckt520728

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill offers a comprehensive solution for performing strict exploratory data analysis on structured data sources like CSV, Excel, JSON, Parquet, and SQLite. It ensures accuracy by relying solely on actual calculations from libraries like pandas, numpy, and scipy, without relying on LLM intuition.

Core Features & Use Cases

  • Exploratory Data Analysis: Load, profile, compute, visualize, and write reports on structured data.
  • Accurate Calculations: All numbers are derived from actual code computations, ensuring reliability.
  • Flexible Analysis: Handles various data types and sources, including clinical research, business KPIs, surveys, financial data, and experimental data.
  • Output: Provides descriptive statistics, visualizations, and detailed Markdown reports.

Quick Start

To begin an analysis, simply provide the data file and specify the type of analysis you want to perform. For example, you can say, "analyze this dataset" or "describe the distribution of the 'amount' column."

Frequently Asked Questions about data-analyzer

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

FAQPage Schema
How do I perform exploratory data analysis on a CSV file using pandas?

Exploratory data analysis on a CSV file involves loading the dataset with pandas, profiling data types, computing descriptive statistics using numpy and scipy, and generating visualizations with matplotlib. This Skill automates that entire workflow to produce accurate numerical reports.

Can I analyze structured data from SQLite databases and Parquet files?

Yes, you can analyze structured data from SQLite databases and Parquet files. This Skill directly handles multiple structured data sources, including CSV, Excel, JSON, Parquet, and SQLite, seamlessly loading and profiling them for rigorous analysis.

What is the best way to generate accurate statistical reports without relying on LLM intuition?

The best way to generate accurate statistical reports is by executing actual code computations. This Skill relies solely on libraries like pandas, numpy, and scipy for its calculations, ensuring all numbers in the descriptive statistics and visualizations are reliable.

Does this data analysis approach work for clinical research and financial datasets?

Yes, this data analysis approach works for clinical research and financial datasets. It is designed to handle a wide range of structured data types and sources, providing precise profiling, computations, and visualizations tailored to your specific domain.

How do I visualize data distributions and compute descriptive statistics step by step?

To visualize data distributions and compute descriptive statistics, you provide your structured data file and specify the desired analysis. The Skill computes the metrics using scipy and numpy, then renders the visualizations using matplotlib, outputting a detailed Markdown report.