data-analysis

Analyze CSV, JSON, and SQL datasets with Python pandas workflows.

40|9|Updated Jan 4, 2026
One-click install
npx skills add https://github.com/akillness/oh-my-skills --skill data-analysis-akillness
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/akillness/oh-my-skills/tree/main/.agent-skills/data-analysis
Command: npx skills add https://github.com/akillness/oh-my-skills --skill data-analysis-akillness

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Data professionals spend excessive time exploring datasets, identifying patterns, and producing reports; this skill accelerates analysis by providing structured workflows for common data formats and tools.

Core Features & Use Cases

  • Data loading and cleaning: ingest data from CSV, JSON, and relational sources, with basic cleaning steps.
  • Statistical analysis & summarization: compute descriptive stats, correlations, group-by aggregations.
  • Visualization & reporting: generate visuals and summary reports to inform decisions.
  • Use Case: Example: analyze a sales dataset to surface trends, segment customers, and produce an executive summary.

Quick Start

Load your dataset (CSV/JSON) and run an initial exploratory report to surface key insights.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I analyze a CSV dataset to generate summary reports and insights?

To analyze a CSV dataset, you load the data using Python pandas workflows to compute descriptive statistics and identify patterns. This generates visual summary reports with reproducible code for data cleaning and analysis.

Can I use Python pandas and SQL queries for JSON data analysis?

Yes, Python pandas and SQL queries support JSON data analysis by ingesting JSON files alongside CSV and relational sources. This applies data cleaning, statistical analysis, and generates reproducible queries to extract actionable insights.

What is the best way to clean and visualize data for business intelligence?

The best way to clean and visualize data for business intelligence is through structured step-by-step workflows. These ingest data from multiple formats, apply basic cleaning steps, compute group-by aggregations, and generate visuals to inform decisions.

Does this data analysis approach work with relational sources and SQL workflows?

Yes, this data analysis approach works with relational sources and SQL workflows. It provides structured steps to ingest relational data, execute SQL queries, and perform statistical analysis and summarization to surface insights and trends.

How do I compute correlations and group-by aggregations on a sales dataset?

To compute correlations and group-by aggregations on a sales dataset, apply statistical analysis and summarization workflows. These calculate descriptive statistics, segment customers, and surface trends to produce an executive summary report.