What kind of output does the analysis provide?

You receive a structured report including concrete SQL queries, hypothesis results (supported/inconclusive), key insights, and a prioritized action plan for implementation.

Is it suitable for complex statistical testing?

Absolutely. It supports statistical significance testing, including p-values, confidence intervals, and sample size validation as part of its hypothesis-testing phase.

Can I use this for sensitive PII data?

The workflow includes a specific 'Privacy/Compliance' checkpoint in Phase 3, allowing you to define anonymization needs and fields to exclude before deep analysis begins.

How does the skill find my data sources?

It uses glob patterns to scan your repository for database schemas, migration files, ORM models, analytics tracking code, and API documentation to build a comprehensive data map.

Does this skill require the Gemini CLI?

Yes, it leverages Gemini's large context window for deep analysis. The skill includes a phase to verify your Gemini CLI installation and guide you if it's missing.

Comprehensive Data Analyst

Name: Comprehensive Data Analyst
Author: Expanly

byExpanly

0•

Data Science & ML

Executes a structured, multi-phase data analysis workflow to transform raw data into actionable business insights and strategic recommendations.

The Comprehensive Data Analyst skill provides a rigorous 7-phase framework for end-to-end data investigation within Claude Code. It automates the discovery of data sources, schemas, and tracking implementations across your codebase, then leverages the Gemini CLI to perform deep analytical reasoning. From initial goal setting and hypothesis formation to generating complex SQL queries and statistical testing, this skill ensures that data analysis is thorough, context-aware, and directly tied to business decision-making. It is particularly useful for debugging metrics, exploring user behavior, and optimizing product roadmaps based on empirical evidence.

Key Features

01Automated data source identification (SQL, ORM models, Analytics logs)

02Hypothesis-driven investigation with statistical rigor checkpoints

03Interactive user checkpoints for data quality and privacy validation

04Gemini-powered deep reasoning for complex query generation

057-phase structured analysis workflow from discovery to action plan

060 GitHub stars

Use Cases

01Generating optimized SQL queries based on existing database schemas

02Investigating user behavior anomalies or performance metric drops

03Validating product hypotheses with evidence-based data reporting

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add expanly/expanly-claude-code-agents comprehensive-data-analysis

For use in Claude.ai and ChatGPT

Download Skill