Data Analysis

This is a structured workflow for turning messy revenue data into defensible insights. It walks you through a seven-phase process from ingestion to output, with mandatory decision logging at every step (why this filter, why this metric, what assumptions you made). The bias checklist and data quality validator are the real value here: they force you to document survivorship bias, test weighting sensitivity, and add confidence intervals before you ship anything. Built for financial and RevOps contexts where stakeholders will actually question your methodology. Outputs range from exec slide decks to full Marimo notebooks with audit trails. If you've ever had an analysis questioned three months later and couldn't remember why you excluded certain records, this prevents that.

skills.sh installs: 333
GitHub stars: 15
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add casper-studios/casper-marketplace --skill data-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Analysis

Overview

A comprehensive data analysis and storytelling skill optimized for financial, SaaS, and RevOps contexts. This skill provides structured workflows for turning raw data into actionable insights with full transparency on analytical decisions, bias awareness, and progressive disclosure reporting.

Workflow Overview

Every analysis follows a 7-phase process:

1. SETUP    → Initialize Marimo notebook (run init_marimo_notebook.py)
2. INGEST   → Load data, document sources and assumptions
3. EXPLORE  → EDA with logged decisions (why this viz, why this filter)
4. MODEL    → If needed, with interpretable-first approach
5. INTERPRET → Apply bias checklist, hedge appropriately
6. WISHLIST → Document data gaps and proxies used
7. OUTPUT   → Generate appropriate tier (slides/report/notebook)