data-analyst

Automate missing-value analysis, imputation, and Plotly Dash dashboard generation for CSV datasets.

6|1|Updated Nov 12, 2025

Search Tags:#data visualization #data analysis #EDA #Plotly Dash #CSV #imputation

Ready to run

npx skills add https://github.com/auldsyababua/instructor-workflow --skill data-analyst

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-analyst
Source: https://github.com/auldsyababua/instructor-workflow/tree/main/skills/data-analyst
Command: npx skills add https://github.com/auldsyababua/instructor-workflow --skill data-analyst

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scikit-learn, plotly, dash, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates end-to-end data analysis workflows for CSV datasets, including missing value assessment, intelligent imputation, and interactive dashboards to explore trends and patterns.

Core Features & Use Cases

Missing Value Analysis: detect patterns and guide imputation strategies
Intelligent Imputation: apply robust methods (mean/median/mode/knn/forward-fill)
Interactive Dashboard Creation: Plotly Dash dashboards for exploration
End-to-end Exploratory Data Analysis (EDA) workflow with recommended visualizations

Quick Start

Run the workflow on a CSV to generate a imputed dataset and an interactive dashboard.

Frequently Asked Questions about data-analyst

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

FAQPage Schema

How do I handle missing values in CSV data before analysis?▼

Missing-value analysis detects patterns across your dataset and applies intelligent imputation strategies—mean/median for numeric columns, mode for categorical, forward-fill for time series—then drops rows or columns if needed. This Skill automates detection, strategy selection, and application end-to-end.

Can I create an interactive dashboard from CSV data automatically?▼

Yes. After imputation, this Skill generates a Plotly Dash dashboard that lets you explore trends, patterns, and data quality visually without manual dashboard coding.

What imputation methods does this workflow support?▼

Imputation methods include mean and median for numeric data, mode for categorical, k-nearest neighbors, forward-fill for temporal sequences, and constant-value replacement. Strategy selection is automated by column type and missing-value pattern.

Do I need to prepare my CSV in a specific format?▼

No. The Skill handles datasets with varying data types (numeric, categorical, temporal), missing-value patterns, and structures. It detects column types automatically and applies appropriate imputation and visualization.

What output does the exploratory data analysis workflow produce?▼

The workflow produces an imputed CSV dataset, a JSON analysis report with data-quality metrics and imputation details, and an interactive Plotly Dash dashboard for exploration.

When should I use KNN imputation instead of mean or mode?▼

KNN imputation works best when missing values depend on patterns in neighboring rows and relationships across columns matter. Mean/median suit simpler numeric columns; mode suits categorical data. This Skill recommends strategies by column type automatically.