data-analysis

Perform descriptive statistics, filtering, aggregation, and correlation on CSV and JSON data with pandas and numpy.

164|16|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/EXboys/skilllite --skill data-analysis-exboys
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/EXboys/skilllite/tree/main/.skills/data-analysis
Command: npx skills add https://github.com/EXboys/skilllite --skill data-analysis-exboys

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Analyze CSV/JSON data with statistics, filtering, and aggregation.

Core Features & Use Cases

  • Describe: compute summary statistics (mean, std, min, max, etc.)
  • Filter: filter rows by column conditions
  • Aggregate: group-by aggregation (sum, mean, count, etc.)
  • Correlate: compute correlation matrix for numeric columns Use-case: Apply to business datasets to derive insights such as revenue trends by region.

Quick Start

Provide a JSON payload with operation and data to perform the analysis and return results.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I compute summary statistics and aggregation on CSV data?

You can analyze CSV data by passing a JSON payload specifying operations like describe, filter, aggregate, or correlate, which executes pandas and numpy functions to normalize inputs and return structured JSON results for business datasets.

Can I use pandas to compute a correlation matrix for numeric columns in JSON files?

Yes, pandas computes correlation matrices for numeric columns in JSON inputs by validating data shapes, normalizing formats, and returning structured JSON results containing the numeric correlation output directly.

Does this data analysis approach require Python and specific libraries installed?

Yes, it requires Python 3.x with pandas and numpy installed to validate input shapes, normalize input formats, and return structured JSON results for statistics and aggregation operations.

What is the best way to filter rows by column conditions in tabular datasets?

The best way to filter rows by column conditions in tabular datasets is to submit a JSON payload with the filter operation, which uses pandas to apply conditions and returns the filtered rows as structured JSON results.

How do I clean and group financial tabular data to derive revenue trends by region?

Clean and group financial tabular data to derive revenue trends by region using the aggregate operation, which handles data cleaning and group-by aggregation on CSV and JSON inputs with pandas, returning structured JSON summary results.

What are the limitations of using pandas for descriptive statistics on large tabular inputs?

Limitations include requiring Python 3.x with numpy installed and relying on validated input shapes and normalized input formats, with results returned exclusively as structured JSON outputs for tabular data processing.