ai-data-analyst

Name: ai-data-analyst
Availability: InStock
Author: grupous

Write and execute Python scripts for data analysis, modeling, and visualization.

1|1|Updated May 23, 2025

Search Tags:#python #data analysis #visualization #statistics #reproducibility #analyze

Ready to run

npx skills add https://github.com/GrupoUS/aegiswallet --skill ai-data-analyst

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ai-data-analyst
Source: https://github.com/GrupoUS/aegiswallet/tree/main/.factory/skills/ai-data-analyst
Command: npx skills add https://github.com/GrupoUS/aegiswallet --skill ai-data-analyst

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables comprehensive data analysis, statistical modeling, and visualization by writing and executing self-contained Python scripts. It helps you derive insights from data with reproducible workflows.

Core Features & Use Cases

Data loading and cleaning from CSV, Excel, JSON, Parquet, or databases.
Exploratory data analysis (EDA), hypothesis testing, and predictive modeling.
Publication-quality visualizations for reports and dashboards.
Use Case: Analyze a CSV data dump to identify key drivers and generate a report with charts and a model summary.

Quick Start

Create a Python virtual environment and install required libraries (pandas, numpy, scikit-learn, statsmodels, matplotlib, seaborn, plotly).
Place your data file (e.g., data.csv) in the working directory and run analysis.py to generate results and visuals.
Review outputs in the outputs/ directory and the generated report.md.

Frequently Asked Questions about ai-data-analyst

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

FAQPage Schema

How do I perform exploratory data analysis and generate visualizations from a CSV file using Python?▼

Exploratory data analysis from a CSV is performed by running self-contained Python scripts that use pandas, matplotlib, and seaborn to clean data, compute statistics, and generate publication-quality visual outputs. The workflow produces reproducible charts and summaries in an outputs directory.

Can I load JSON or Parquet files for statistical modeling in Python?▼

Yes, JSON and Parquet files can be loaded for statistical modeling. The Python scripts utilize pandas and statsmodels to ingest these formats directly, enabling hypothesis testing, predictive modeling, and reproducible data workflows without requiring prior format conversion.

What Python libraries do I need to run reproducible data analysis scripts?▼

Reproducible data analysis scripts require a Python virtual environment with pandas, numpy, scikit-learn, statsmodels, matplotlib, seaborn, and plotly installed. Setting up this environment ensures all data loading, modeling, and visualization dependencies are satisfied for the workflow.

Does Python data analysis support pulling data directly from databases for EDA?▼

Yes, Python data analysis supports pulling data directly from databases for EDA. The workflow uses self-contained scripts to connect to databases, perform data cleaning, and execute statistical modeling, yielding reproducible insights and visualizations without manual data extraction.

What is the best way to generate publication-quality charts from Excel data in Python?▼

The best way to generate publication-quality charts from Excel data in Python is by executing scripts that leverage seaborn, matplotlib, and plotly. This approach ingests Excel files, performs statistical modeling, and outputs reproducible visualizations suitable for reports and dashboards.

Why use Python scripts for reproducible data workflows instead of manual analysis?▼

Python scripts ensure reproducible data workflows by encapsulating data loading, cleaning, EDA, and modeling in self-contained code. This eliminates manual analysis errors, provides publication-quality visuals, and generates a markdown report for consistent, verifiable insights.