data-analyst

Load CSV, JSON, or Excel data in memory for cleaning, statistics, and visualization.

171|4|Updated Feb 27, 2026

Search Tags:#json #visualization #pandas #excel #data-analysis #csv #in-memory

Ready to run

npx skills add https://github.com/ntygod/ZhiWei --skill data-analyst-ntygod

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-analyst
Source: https://github.com/ntygod/ZhiWei/tree/main/src/main/resources/skills/data-analyst
Command: npx skills add https://github.com/ntygod/ZhiWei --skill data-analyst-ntygod

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill enables in-memory data analysis by loading CSV, JSON, or Excel data, performing clean-up and quality checks, executing descriptive statistics, hypothesis testing, and generating visualizations without repeatedly reading from disk or external services.

Core Features & Use Cases

In-memory data loading for CSV/JSON/Excel with shared kernel state to maintain context across steps.
Data cleaning, including missing value handling, type conversion, and deduplication.
Statistical analysis and visualization workflows, including describe, corr, t-tests, and charts.
Use Case: Given a dataset of sales records, quickly obtain a summary, assess relationships, test hypotheses, and produce a chart for reporting.

Quick Start

Upload a CSV, JSON, or Excel file and tell me the analysis you want, and I will load it in memory, clean it, analyze, and visualize it.

Frequently Asked Questions about data-analyst

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

FAQPage Schema

How do I analyze CSV data in memory without repeatedly reading from disk?▼

To analyze CSV data in memory, load your file into a shared kernel session. This maintains context across steps, allowing you to clean data, run statistics, and generate visualizations without repeated disk reads.

Can I perform data cleaning and hypothesis testing on Excel files in one session?▼

Yes, you can load Excel files into the in-memory session to perform data cleaning like missing value handling and type conversion, followed by descriptive statistics and hypothesis testing such as t-tests within the same workflow.

What is the best way to run descriptive statistics and generate visualizations from JSON data?▼

The best way to run descriptive statistics on JSON data is to load it in memory first. You can then apply describe and correlation functions, and generate charts directly within the kernel-enabled session for immediate reporting.

Does this in-memory data analysis approach work with large files and handle input validation?▼

Yes, this in-memory data analysis approach ensures robust handling of large files. It includes input validation and graceful error reporting to manage exceptions during loading, cleaning, and statistical analysis.

How do I clean up a dataset by handling missing values and deduplication before analysis?▼

To clean up a dataset before analysis, load it in memory and apply the built-in cleaning functions. This includes missing value handling, type conversion, and deduplication to ensure data quality prior to running statistics.

Why use an in-memory kernel session for data analysis instead of reading from external services?▼

Using an in-memory kernel session for data analysis eliminates the latency of repeatedly reading from disk or external services. It maintains shared state across your cleaning, statistical testing, and visualization steps for faster workflows.