home / skills / meleantonio / awesome-econ-ai-stuff / econ-visualization

econ-visualization skill

/_skills/communication/econ-visualization

This skill helps economists create publication-quality figures with consistent styling, labeled axes, and export-ready formats for papers and presentations.

npx playbooks add skill meleantonio/awesome-econ-ai-stuff --skill econ-visualization

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

Files (2)

SKILL.md

2.9 KB

---
name: econ-visualization
description: Create publication-quality charts and graphs for economics papers.
workflow_stage: communication
compatibility:
  - claude-code
  - cursor
  - codex
  - gemini-cli
author: Awesome Econ AI Community
version: 1.0.0
tags:
  - visualization
  - ggplot2
  - charts
  - publication
---

# Econ Visualization

## Purpose

This skill creates publication-quality figures for economics papers, using clean styling, consistent scales, and export-ready formats.

## When to Use

- Building figures for empirical results and descriptive analysis
- Standardizing chart style across a paper or presentation
- Exporting figures to PDF or PNG at journal quality

## Instructions

Follow these steps to complete the task:

### Step 1: Understand the Context

Before generating any code, ask the user:

- What is the dataset and key variables?
- What chart type is needed (line, bar, scatter, event study)?
- What output format and size are required?

### Step 2: Generate the Output

Based on the context, generate code that:

1. **Uses a consistent theme** for academic styling
2. **Labels axes and legends clearly**
3. **Exports figures** at high resolution
4. **Includes reproducible steps** for data preparation

### Step 3: Verify and Explain

After generating output:

- Explain how to regenerate or update the plot
- Suggest alternatives (log scales, faceting, smoothing)
- Note any data transformations used

## Example Prompts

- "Create an event study plot with confidence intervals"
- "Plot GDP per capita over time for three countries"
- "Build a scatter plot with fitted regression line"

## Example Output

```r
# ============================================
# Publication-Quality Figure in R
# ============================================
library(tidyverse)

df <- read_csv("data.csv")

ggplot(df, aes(x = year, y = gdp_per_capita, color = country)) +
  geom_line(size = 1) +
  scale_y_continuous(labels = scales::comma) +
  labs(
    title = "GDP per Capita Over Time",
    x = "Year",
    y = "GDP per Capita (USD)",
    color = "Country"
  ) +
  theme_minimal(base_size = 12) +
  theme(
    legend.position = "bottom",
    panel.grid.minor = element_blank()
  )

ggsave("figures/gdp_per_capita.pdf", width = 7, height = 4, dpi = 300)
```

## Requirements

### Software

- R 4.0+ or Python 3.10+

### Packages

- For R: `ggplot2`, `scales`, `dplyr`
- For Python: `matplotlib`, `seaborn` (optional alternative)

## Best Practices

1. **Use vector formats** (PDF, SVG) for publication
2. **Keep labels concise** and readable
3. **Document data filters** used in the figure

## Common Pitfalls

- Overcrowded plots without clear labeling
- Inconsistent scales across figures
- Exporting low-resolution images

## References

- [ggplot2 documentation](https://ggplot2.tidyverse.org/)
- [Tufte (2001) The Visual Display of Quantitative Information](https://www.edwardtufte.com/tufte/books_vdqi)

## Changelog

### v1.0.0

- Initial release

Overview

This skill creates publication-quality charts and graphs tailored to economics papers, with clean academic styling, consistent scales, and export-ready formats. It produces reproducible code (R or Python) and clear instructions so figures can be regenerated or adjusted. The focus is on readable labels, correct units, and journal-friendly vector exports.

How this skill works

I first ask about the dataset, key variables, desired chart type, and output size/format. Based on those answers I generate code that applies a consistent theme, labels axes and legends clearly, documents data preparation steps, and exports the figure at high resolution or as a vector file. I also provide verification steps, alternatives (log scales, faceting, smoothing), and notes on any data transformations used.

When to use it

Preparing figures for empirical results or descriptive tables
Standardizing visual style across a paper or presentation
Exporting figures to PDF, SVG, or high-resolution PNG for submission
Creating event-study plots, time series, scatter plots with fitted lines
Reproducing figures from supplementary code or replication packages

Best practices

Prefer vector formats (PDF or SVG) for line art and journal submission
Keep labels concise, use readable font sizes and sensible tick marks
Document every data filter and transformation used to generate the plot
Use a consistent theme and color palette across all figures
Avoid overcrowding: consider faceting, small multiples, or inset zooms

Example use cases

Event-study plot with shaded confidence intervals and baseline normalization
Line plot of GDP per capita over time for multiple countries with consistent scales
Scatter plot of earnings vs. education with fitted regression line and annotation
Bar charts of treatment/control means with error bars and balanced axis limits
Export-ready figure pipeline: data cleaning, plotting code, and ggsave/plt.savefig commands

FAQ

Which language should I use, R or Python?

Use R (ggplot2) if you prefer grammar-of-graphics syntax and easy PDF export; use Python (matplotlib/seaborn) if your workflow is Python-based. I can provide code for either.

How do you ensure journal-quality output?

I recommend vector formats, set base font sizes for readability, choose publication-safe color palettes, and export at appropriate dimensions and DPI. I include ggsave or plt.savefig settings to match journal requirements.