figure-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Scientific Figure Generation

科研图表生成

Generate publication-quality figures for research papers.

为研究论文生成达到出版级别的图表。

Input

输入

```
$0
```
— Description of the desired figure
```
$1
```
— (Optional) Path to data file (CSV, JSON, NPY, PKL) or results directory

```
$0
```
— 所需图表的描述
```
$1
```
—（可选）数据文件路径（CSV、JSON、NPY、PKL格式）或结果目录

Scripts

脚本

Generate figure template

生成图表模板

bash

python ~/.claude/skills/figure-generation/scripts/figure_template.py --type bar --output figure_script.py --name comparison
python ~/.claude/skills/figure-generation/scripts/figure_template.py --list-types

Available types:

bar

training-curve

heatmap

ablation

line

scatter

radar

violin

tsne

attention

bash

python ~/.claude/skills/figure-generation/scripts/figure_template.py --type bar --output figure_script.py --name comparison
python ~/.claude/skills/figure-generation/scripts/figure_template.py --list-types

支持的类型：

bar

、

training-curve

、

heatmap

、

ablation

、

line

、

scatter

、

radar

、

violin

、

tsne

、

attention

Three-Phase Pipeline (from MatPlotAgent)

三阶段流程（来自MatPlotAgent）

Phase 1: Query Expansion

阶段1：查询扩展

Expand the user's figure description into step-by-step coding specifications using the prompts in

references/figure-prompts.md

. Determine: figure type, data mapping (x/y/color/hue), style requirements, paper conventions.

使用

references/figure-prompts.md

中的提示词，将用户的图表描述扩展为分步编码规范。确定：图表类型、数据映射（x/y/颜色/色调）、样式要求、论文格式规范。

Phase 2: Code Generation with Execution Loop (up to 4 retries)

阶段2：带执行循环的代码生成（最多4次重试）

Generate a self-contained Python script using the template from
```
scripts/figure_template.py
```
as a starting point
Write script to a temp file and execute:
```
python figure_script.py
```
If error: capture traceback, feed back, regenerate (see ERROR_PROMPT in references)
If no
```
.png
```
produced: add explicit save instruction, retry
On success: report the generated figure path

以
```
scripts/figure_template.py
```
中的模板为基础，生成一个独立的Python脚本
将脚本写入临时文件并执行：
```
python figure_script.py
```
若出现错误：捕获回溯信息，反馈后重新生成（参考references中的ERROR_PROMPT）
若未生成
```
.png
```
文件：添加显式保存指令，重试
执行成功：报告生成的图表路径

Phase 3: Visual Refinement

阶段3：视觉优化

Read the generated PNG file and visually inspect using the VLM feedback prompts from

references/figure-prompts.md

Does the figure type match the request?
Are labels, titles, and legends correct?
Is the color scheme appropriate and consistent?
Are axis scales sensible? Is text readable at publication size?

If improvements needed: generate corrective instructions and re-execute.

读取生成的PNG文件，使用

references/figure-prompts.md

中的VLM反馈提示词进行视觉检查：

图表类型是否符合需求？
标签、标题和图例是否正确？
配色方案是否合适且一致？
坐标轴刻度是否合理？在出版尺寸下文本是否清晰可读？

若需要改进：生成修正指令并重新执行。

References

参考资料

All MatPlotAgent prompts:

~/.claude/skills/figure-generation/references/figure-prompts.md

Figure templates:

~/.claude/skills/figure-generation/scripts/figure_template.py

所有MatPlotAgent提示词：

~/.claude/skills/figure-generation/references/figure-prompts.md

图表模板：

~/.claude/skills/figure-generation/scripts/figure_template.py

Output

输出

Both PNG (preview, 300 DPI) and PDF (vector, for paper) formats. Plus the LaTeX include code:

latex

\begin{figure}[t]
    \centering
    \includegraphics[width=\linewidth]{figures/figure_name.pdf}
    \caption{Description. Best viewed in color.}
    \label{fig:figure_name}
\end{figure}

同时提供PNG（预览用，300 DPI）和PDF（矢量格式，用于论文）两种格式。此外还包含LaTeX引用代码：