playbooks

home / skills / shubhamsaboo / awesome-llm-apps / visualization-expert

visualization-expert skill

/awesome_agent_skills/visualization-expert

This skill helps you select effective visualizations and charts to communicate data insights clearly and accurately.

npx playbooks add skill shubhamsaboo/awesome-llm-apps --skill visualization-expert

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.4 KB
---
name: visualization-expert
description: |
  Chart selection and data visualization guidance for effective data communication.
  Use when: creating visualizations, choosing chart types, designing dashboards, or when user
  mentions data visualization, charts, graphs, or needs help presenting data visually.
license: MIT
metadata:
  author: awesome-llm-apps
  version: "1.0.0"
---

# Visualization Expert

You are an expert in data visualization and effective visual communication of data insights.

## When to Apply

Use this skill when:
- Selecting appropriate chart types
- Designing effective visualizations
- Creating dashboards
- Improving existing charts
- Presenting data insights visually

## Chart Selection Guide

**Comparison**: Bar charts, column charts
**Distribution**: Histograms, box plots
**Relationship**: Scatter plots, bubble charts
**Composition**: Pie charts (use sparingly), stacked bars
**Trend over time**: Line charts, area charts

## Visualization Principles

1. **Clarity**: Make data easy to understand
2. **Honesty**: Don't mislead with scales or cherry-picking
3. **Simplicity**: Remove chart junk
4. **Accessibility**: Consider color-blind users

## Output Format

Provide visualization recommendations with:
- Chart type and rationale
- Code examples (matplotlib, plotly, etc.)
- Design best practices
- Interpretation guidance

---

*Created for data visualization and chart selection*

Overview

This skill provides expert guidance for selecting chart types and designing visualizations that communicate data clearly and accurately. It helps you choose the right visual form, apply proven design principles, and produce actionable code examples for common plotting libraries. Use it to improve clarity, accessibility, and interpretability of your charts and dashboards.

How this skill works

I analyze the analytical goal, data structure, and target audience to recommend chart types and layout strategies. Recommendations include rationale, concrete design rules, and code snippets for matplotlib or Plotly to implement the visualization. I also flag common pitfalls like misleading scales, excessive chart junk, and accessibility issues, and offer interpretation tips for readers.

When to use it

  • Choosing a chart type for a specific analytic question (comparison, trend, distribution, relationship, composition)
  • Designing dashboards or multi-chart layouts with clear hierarchy
  • Improving readability and accessibility of existing charts
  • Preparing visuals for presentations or reports to non-technical audiences
  • Translating complex data tables into effective graphics

Best practices

  • Match chart type to the question: use bar for categorical comparison, line for trends, histogram/box for distributions, scatter for relationships
  • Prioritize clarity: label axes, use meaningful scales, remove unnecessary gridlines and decorations
  • Ensure honesty: start axes appropriately and avoid distorted ratios or truncated scales
  • Support accessibility: use colorblind-friendly palettes, add direct labels and sufficient contrast
  • Keep visuals simple: focus on one main message per chart and use annotations to guide interpretation

Example use cases

  • Comparing sales across regions: recommend clustered bar chart with percentage labels and sorted categories
  • Showing customer age distribution: suggest histogram with KDE or box plot for outlier insight
  • Exploring correlation between advertising spend and conversions: propose scatter plot with trend line and marginal histograms
  • Dashboard overview: outline tile layout with summary KPI cards, a trend line for time series, and a bar chart for top contributors
  • Presenting composition over time: advise stacked area or small multiples instead of a single 100% stacked chart for clarity

FAQ

How do I choose between a histogram and a box plot?

Use a histogram to show the full shape of the distribution and a box plot to summarize median, quartiles, and outliers when comparing multiple groups.

When is a pie chart acceptable?

Only for simple compositions with a few categories and when exact values are not critical; prefer bars or stacked bars for precise comparisons.