data-analyst

Analyze datasets from CSV, Excel, JSON, or databases with EDA and visualizations.

2|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/k1lgor/virtual-company --skill data-analyst-k1lgor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analyst
Source: https://github.com/k1lgor/virtual-company/tree/main/skills/16-data-analyst
Command: npx skills add https://github.com/k1lgor/virtual-company --skill data-analyst-k1lgor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps data teams turn raw data into actionable insights, clear visualizations, and business intelligence through guided EDA, cleaning, and interpretation.

Core Features & Use Cases

  • Data loading & cleaning: load CSV, Excel, JSON, or database sources; identify missing values and duplicates; propose cleaning steps.
  • Exploratory Analysis & Visualization: generate summary statistics, check data types and distributions, and create charts with Matplotlib, Seaborn, or Plotly.
  • Insight generation & reporting: translate findings into actionable recommendations and dashboards for stakeholders.

Quick Start

Provide the dataset path and request an exploratory analysis to generate a summary of insights and visuals.

Frequently Asked Questions about data-analyst

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?

Exploratory data analysis on a CSV file involves loading the dataset, identifying missing values and duplicates, and generating summary statistics to understand data distributions before creating visualizations. The process translates raw data into actionable insights through guided cleaning and plotting.

Can I generate data visualizations using Matplotlib and Seaborn for Excel datasets?

Yes, you can generate data visualizations using Matplotlib, Seaborn, or Plotly for Excel datasets. The workflow supports loading Excel files, checking data types and distributions, and creating charts directly from the cleaned data to visualize trends and summary statistics.

What is the best way to clean missing values and duplicates in a JSON dataset?

The best way to clean missing values and duplicates in a JSON dataset is to load the source data, identify structural anomalies, and propose targeted cleaning steps. This ensures data quality before generating summary statistics and exploratory visualizations.

Does this EDA process work with database sources and SQL?

Yes, the EDA process works directly with database sources and SQL. It supports loading data from databases, handling missing values, checking data types, and producing summary statistics to derive actionable insights and visualizations from your structured queries.

How do I translate data insights into business intelligence reports?

To translate data insights into business intelligence reports, you perform EDA and visualization to detect trends, then interpret the findings into actionable recommendations. This generates dashboards and reports that communicate clear insights to stakeholders.