figure
Econometrics skill for generating publication-quality figures for top economics journals. Activates when the user asks about: "econometric figure", "publication figure", "journal figure", "AER figure", "QJE figure", "event study plot", "coefficient plot", "coefplot", "binned scatter", "binscatter", "RDD plot", "parallel trends plot", "kernel density", "distribution plot", "time series plot", "map", "figure formatting", "academic plot", "论文图表", "学术图", "系数图", "事件研究图", "散点图", "分布图", "趋势图", "回归可视化"
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill figure --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates figure code that follows journal-style formatting for top economics journals. It supports a wide range of econometric figure types and provides concrete defaults for fonts, sizes, colors, and export formats to produce publication-ready visuals.
How it works
The skill includes concrete code templates in Python, R, and Stata:
- Python (matplotlib) and R (ggplot2) examples show how to set journal-style defaults (fonts, sizes, grayscale-safe palettes) and provide export routines (PDF, vector formats).
- It documents specific figure types with full code blocks, including: Event Study / Dynamic Treatment Effects; Coefficient Plot; Binned Scatter (binscatter); RDD Visualization; Kernel Density / Distribution; Time Series / Trend plots; and more.
- For each type, it provides plotting routines (e.g., event study: plotting CIs, treatment reference line; coefplot: multiple models with offsets; binscatter: bin means and linear fit; rdd: binning and local fits) and includes notes about formatting and export.
- It enumerates journal requirements (PDF/EPS vector formats, DPI, width/height, font choices, grayscale readability, line widths, legend placement, notes formatting, and caption numbering).
When to use it
Use when generating figures intended for AER, QJE, ReStud, Econometrica, or JPE-style publication figures. It activates when you request econometric figures, publication figures, or specific figure types such as event study plots, coefplots, binscatter, RDD plots, density plots, and time series plots.
What it can touch
The skill references and uses tools labeled under declared tools: "claude-code". The code samples show interactions with Python, R, and Stata environments to produce figures and export PDFs. It touches the plotting libraries and export mechanisms described in the code blocks (matplotlib in Python, ggplot2 in R, and Stata graph export). Note: The statements here reflect the code examples and defaults provided within the skill.
Caveats
The skill provides example code templates and defaults; actual data wiring, model outputs, and file paths must be supplied by the user. Licensing is NOASSERTION. It does not claim automatic publication acceptance or integration with any external plotting pipelines beyond the included templates.
# Publication-Quality Figures Skill This skill generates figure code that meets the formatting standards of top economics journals (AER, QJE, ReStud, Econometrica, JPE). It covers the most common econometric figure types with precise control over fonts, colors, dimensions, and export formats. ## Journal Requirements Summary | Requirement | AER / QJE / ReStud Standard | |-------------|-------------
What does the figure skill do?
Econometrics skill for generating publication-quality figures for top economics journals. Activates when the user asks about: "econometric figure", "publication figure", "journal figure", "AER figure", "QJE figure", "event study plot", "coefficient plot", "coefplot", "binned scatter", "binscatter", "RDD plot", "parallel trends plot", "kernel density", "distribution plot", "time series plot", "map", "figure formatting", "academic plot", "论文图表", "学术图", "系数图", "事件研究图", "散点图", "分布图", "趋势图", "回归可视化"
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill figure --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.