data-analysis

Analyze messy multi-format data and generate validated reports with charts.

333|83|Updated Jan 9, 2026

Search Tags:#pdf #analysis #reporting #visualization #pandas #csv #eda

Ready to run

npx skills add https://github.com/SpaceZephyr/myskill --skill data-analysis-spacezephyr

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/SpaceZephyr/myskill/tree/main/data-analysis
Command: npx skills add https://github.com/SpaceZephyr/myskill --skill data-analysis-spacezephyr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you safely analyze messy, multi-format data without loading everything into context, so you can avoid token overflow, detect data quality issues early, and produce reliable findings.

Core Features & Use Cases

Safe data exploration: Inspect metadata and small samples first for CSV, Excel, PDF, DOCX, Markdown, and image-based data.
Quality validation: Check missing values, duplicates, type issues, range errors, consistency problems, and cross-file relationships before analysis.
Analysis and reporting: Perform statistical analysis, pattern discovery, visualization, and Markdown, PDF, or DOCX report generation for EDA and business insight workflows.

Quick Start

Analyze the attached dataset, inspect its structure and quality, then generate a concise Markdown report with key findings and charts.

Frequently Asked Questions about data-analysis

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

FAQPage Schema

How do I perform exploratory data analysis on messy CSV and Excel files?▼

Exploratory data analysis on messy CSV and Excel files is performed by safely sampling data, inspecting metadata, and running quality checks for missing values and duplicates before generating validated insights, charts, and structured Markdown reports.

What is the best way to extract and analyze data from multiple PDF and DOCX sources?▼

Analyzing data across PDF and DOCX sources involves cross-file extraction and safe sampling to avoid token overflow, applying quality validation, and producing consolidated business reporting with visualizations.

Can I use Python and pandas for data quality checks and visualization?▼

Yes, Python and pandas are used for data quality checks and visualization, applying type issue detection, range error identification, and consistency problem checks before delivering validated reports.

Does data visualization and reporting work with image-based data sources?▼

Data visualization and reporting supports image-based data sources alongside CSV, Excel, PDF, DOCX, and Markdown, applying metadata inspection and sampling to handle multi-format messy data safely without loading everything into context.

Why does analyzing large multi-format datasets cause token overflow and how to avoid it?▼

Analyzing large multi-format datasets causes token overflow by loading everything into context, which is avoided by applying safe sampling, metadata inspection, and small data extraction before running Python-based cleaning and analysis.

How do I generate structured business reports from raw data findings?▼

Generating structured business reports from raw data findings is done by performing statistical analysis and pattern discovery, then exporting the validated insights into Markdown, PDF, or DOCX report formats with embedded charts.