This is a structured workflow for handling CSV, Excel, PDF, and image data without blowing your token budget. It enforces a safety-first approach: always probe with metadata and small samples before processing, run quality checks for missing values and duplicates, then execute Python analysis with Pandas and Matplotlib. The source includes detailed checklists for data integrity (completeness, uniqueness, consistency) and generates reports in markdown, PDF, or DOCX. It's opinionated about avoiding full data dumps and requires verification before delivery. Use this when you need repeatable exploratory analysis with guardrails, especially if you're dealing with multiple files that need cross-referencing or messy real-world data that needs cleaning first.
npx skills add https://github.com/excelsioryy/data-analysis-skill --skill data-analysis