skills.rest
truongnat
truongnatCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

data-analysis-pro

Analyze tabular data with pandas, producing statistics, visualizations, and Excel-ready outputs.

1|Updated Jul 3, 2026
Search Tags:#sqlite#visualization#pandas#csv#EDA#parquet#data-cleaning
One-click install
npx skills add https://github.com/truongnat/skills --skill data-analysis-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-analysis-pro
Source: https://github.com/truongnat/skills/tree/main/skills/data-analysis-pro
Command: npx skills add https://github.com/truongnat/skills --skill data-analysis-pro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Professional data analysis in Python: exploratory data analysis (EDA), cleaning, descriptive statistics, pandas workflows, Parquet/CSV/SQLite IO, visualization (matplotlib/seaborn-style), pivot-style summaries, and spreadsheet deliverables (openpyxl charts, freeze panes, validation).

Core Features & Use Cases

  • EDA, data cleaning, descriptive statistics, and pivot-style summaries using pandas.
  • Visualization with matplotlib/seaborn-style plots; export to Excel via openpyxl charts, with freeze panes and data-validation patterns.
  • Use cases include profiling a dataset, comparing distributions, generating pivot tables, and delivering Excel-ready reports.

Quick Start

Analyze a sample CSV with pandas to produce a quick descriptive summary and a basic visualization, then export results to an Excel workbook.

Frequently Asked Questions about data-analysis-pro

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

FAQPage Schema
How do I perform exploratory data analysis on a CSV file using pandas?▼

Exploratory data analysis on a CSV file uses pandas to compute descriptive statistics, clean records, and generate visualizations. The workflow outputs structured summaries and Excel-ready reports for immediate KPI tracking and reproducible review.

Can I generate pivot tables and Excel reports with openpyxl charts from Parquet data?▼

Yes, you can generate pivot tables and Excel reports from Parquet data using pandas for pivoting and openpyxl for export. The output includes formatted charts, freeze panes, and data-validation patterns for professional reporting.

What is the best way to visualize SQLite exports using Python?▼

The best way to visualize SQLite exports is reading data with pandas and applying matplotlib or seaborn-style plots. This generates clear visual representations for comparing distributions and profiling datasets efficiently.

Does this Python data analysis workflow support dtype-aware processing for reproducible results?▼

Yes, this Python data analysis workflow supports dtype-aware processing to ensure reproducible results. It strictly manages data types during cleaning and summarization to maintain consistent analytical outputs across CSV and Parquet files.

How do I clean tabular data and handle missing values before generating descriptive statistics?▼

To clean tabular data before generating descriptive statistics, the workflow applies pandas data-cleaning operations to handle missing values and correct types. This prepares the dataset for accurate pivot-style summaries and visualization.

Related Skills

Explore More Data & Analytics Skills→
rocklambrosrocklambros
2

auditing-data-quality

Audit tabular datasets for data quality issues before modeling.

Community
Advanced
Wesley1600Wesley1600

excel-pivot-charts

Create pivot tables and charts in Excel with pandas and openpyxl.

Community
Advanced
sanand0sanand0
8

seaborn

Generate statistical visualizations from pandas DataFrames using seaborn.

Community
Intermediate
cas-bigdatalabcas-bigdatalab
541

ray_document_deduplicator

Remove duplicate documents from large-scale datasets using MD5 hashing and Ray distributed computing.

Official
Advanced