ZhuodLiu

Econ Academic Figures — AI skill for Claude Code

AI community

Claude Code skill / Python toolkit for academic-style economics paper figures (Times New Roman, coefficient plots, framework diagrams, China maps) and crisp vector embedding into Word.

How to install Econ Academic Figures

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ZhuodLiu/econ-academic-figures and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Econ Academic Figures does

Claude Code skill / Python toolkit for academic-style economics paper figures (Times New Roman, coefficient plots, framework diagrams, China maps) and crisp vector embedding into Word.

Alternatives in AI

Architecture Diagram Generator — Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files 7k ★
AI Research SKILLs — Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code 5.7k ★
Cartographer — Claude Code plugin that maps and documents codebases of any size using parallel AI subagents 518 ★

README

econ-academic-figures

A [Claude Code](https://claude.com/claude-code) skill (also usable as a plain Python toolkit) for **publication-quality figures in economics and management papers**: Times New Roman, no titles inside images, grayscale-safe colours, and figures that go into the Word manuscript as crisp vector images.

一个 Claude Code 技能（也可以当普通 Python 工具包用），用来画**经济学 / 管理学论文的学术风图表**：新罗马字体、图内不放标题、黑白打印可辨，并能把图以矢量形式插入 Word 稿件。

What it covers / 功能

Style (scripts/econ_style.py): rcParams, palette, typographic minus, panel letters; every figure saved as 300 dpi PNG + 600 dpi PNG + PDF + SVG.
Coefficient plots: 90 % (thick) and 95 % (thin) confidence intervals, stars copied from your tables, aligned estimate / Obs. columns, grouped panels — for baseline, robustness, heterogeneity and moderation results.
China province maps (scripts/china_map.py): Albers projection, ten-dash line and South China Sea inset, classed legend below the map. Boundaries are downloaded from Alibaba DataV on first use (not redistributed here).
Word (scripts/docx_embed.py): replace or insert figures in an existing .docx as SVG with a 600 dpi PNG fallback, sized to the text width, centred, old crops removed, image compression switched off.
Redrawing from an old image (references/digitize.md): recover bar heights, points, fit lines and even missing standard errors from the original figure with two independent pixel methods.
Previewing a .docx on macOS without LibreOffice (scripts/render_docx.sh).

Install / 安装

As a Claude Code skill (personal):

git clone https://github.com/ZhuodLiu/econ-academic-figures ~/.claude/skills/econ-academic-figures

Then ask Claude Code e.g. "redraw the figures in my manuscript in academic style" / "把论文里的图重新画成学术风并放回 Word", or type `/econ-academic-figures`.

As a Python toolkit:

pip install -r requirements.txt
python examples/demo.py      # writes examples/output/

import