Data Visualization Chart Recommender

Pro v1.0.0 1 view

Analyzes your data and goals to recommend the optimal chart type, explains why it works, and generates professional Python visualizations ready for presentations.

What You Get

Transform data into compelling visuals by getting expert chart recommendations tailored to your data structure and analytical goals, then generating publication-ready visualizations instantly.

The Problem

Choosing the right visualization is challenging. With dozens of chart types available, selecting the wrong one can obscure insights, mislead your audience, or make comparisons impossible. Most people default to familiar charts (pie charts, vertical bars) even when better alternatives exist, resulting in ineffective data communication.

The Solution

This skill acts as your data visualization consultant. It analyzes your data structure (numeric, categorical, time series, distributions), clarifies your analytical goal (compare, trend, distribution, composition, relationship), and applies visualization selection rules to recommend the optimal chart type with clear reasoning. The skill generates clean Python code using matplotlib and seaborn with best practices: readable labels, colorblind-friendly colors, sorted data, and no chart junk. Beyond chart generation, it provides data quality assessment and contextual insights about patterns and trends.

How It Works

  1. 1 Load data from files (CSV/Excel) or pasted content and analyze structure
  2. 2 Identify data types (numeric, categorical, temporal) and quality issues
  3. 3 Clarify analytical goal: compare, trend, distribution, composition, or relationship
  4. 4 Apply visualization selection rules to recommend optimal chart type
  5. 5 Explain why recommendation works and why alternatives don't
  6. 6 Generate professional Python code with matplotlib/seaborn best practices
  7. 7 Execute visualization and provide insights on patterns and trends

What You'll Need

  • Data in any format: file path (CSV/Excel), pasted data, or inline values
  • Clear communication goal or willingness to answer clarifying questions
  • Python environment with matplotlib, seaborn, pandas for code execution