figure-designer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Figure Designer

图表设计助手

Overview

概述

A top-venue paper typically carries six to eight figures, with three carrying almost all the storytelling weight: the Motivated Example (Figure 1, on page 1 or the top of page 2), the Solution Overview (inside the Methodology section), and the Experimental Results figures (inside the Experiments section). Reviewers scan these three in under a minute to decide whether the paper is worth reading in detail; weak figures sink otherwise-strong papers.

This skill takes the user's intent (what they want to communicate) plus context (research area, method name, target venue) and returns the recommended paradigm, a layout sketch, labelling guidance, tool suggestion, and a quality-control audit against a universal rule set (vector format, font size, colour-blind-safe encoding, self-contained caption, honest axis ranges).

一篇顶会论文通常包含6到8个图表，其中三个是叙事核心：Motivated Example（图1，位于第1页或第2页顶部）、Solution Overview（方法论章节内）和实验结果图表（实验章节内）。审稿人会在一分钟内快速浏览这三个图表，判断论文是否值得细读；图表质量不佳会直接拖累内容优秀的论文。

本技能结合用户的意图（想要传达的内容）和上下文（研究领域、方法名称、目标会议/期刊），返回推荐的设计范式、布局草图、标注指南、工具建议，并基于通用规则集（矢量格式、字体大小、色弱友好编码、独立说明性标题、真实坐标轴范围）进行质量控制审核。

When to use this skill

适用场景

Before drawing any figure in a paper.
The user asks to 'design a figure', 'draw Figure 1', 'plot experiment results', 'choose the right chart type'.
The user has drawn a figure and wants a design audit.
The user is unsure which figure type or paradigm to choose.
Preparing camera-ready figures before submission.

绘制论文中的任何图表之前
用户提出“设计图表”“绘制图1”“绘制实验结果图”“选择合适的图表类型”等需求
用户已绘制好图表，需要设计审核
用户不确定应选择哪种图表类型或范式
提交前准备终稿图表

When NOT to use this skill

不适用场景

The user only wants generic plotting help (bar chart, line chart) outside a paper. Regular assistance suffices.
The paper is not yet structured; use
```
intro-drafter
```
or
```
tech-paper-template
```
first to decide what figures the paper needs.
The user wants a review of an already-finished paper. Use
```
pre-submission-reviewer
```
.

用户仅需要论文外的通用绘图帮助（柱状图、折线图），常规协助即可满足
论文结构尚未确定，应先使用
```
intro-drafter
```
或
```
tech-paper-template
```
确定论文需要的图表
用户想要对已完成的整篇论文进行评审，应使用
```
pre-submission-reviewer
```

Core procedure

核心流程

Step 1: Figure-type identification

步骤1：图表类型识别

Decide which of the three core types the figure is. If the user's request does not match any, either it is a supporting figure (use the experimental-results guidance as a base) or it does not belong in the paper.

If the mode is

figure-audit

and the user has provided an image path, load the image with the Read tool before proceeding to Step 2. Vision-based inspection enables the universal rule audit in Step 6 to check font legibility, colour palette, raster-vs- vector tells, and chartjunk directly rather than relying on user description. If no image is provided, continue in text-only mode and mark vision-only rules (font size, raster detection, colour palette) as "user must verify" in the final audit report.

判断该图表属于三种核心类型中的哪一种。如果用户的需求与任一类型都不匹配，则它要么是辅助图表（以实验结果图表的指导规则为基础），要么不属于该论文。

如果处于

figure-audit

模式且用户提供了图片路径，在进入步骤2前先用Read工具加载图片。基于视觉的检查能让步骤6中的通用规则审核直接检查字体可读性、调色板、栅格/矢量特征和图表冗余元素，而非依赖用户描述。如果未提供图片，则继续使用纯文本模式，并在最终审核报告中将仅能通过视觉检查的规则（字体大小、栅格检测、调色板）标记为“需用户自行验证”。

Step 2: Paradigm recommendation

步骤2：范式推荐

See: references/motivated-example.md, references/solution-overview.md, or references/experimental-results.md depending on figure type.

Each figure type has two to three canonical paradigms. Pick the one that fits the user's storytelling need, and explain why the other paradigms fit less well.

参考：references/motivated-example.md、references/solution-overview.md或references/experimental-results.md，具体取决于图表类型。

每种图表类型有2到3种标准范式。选择最符合用户叙事需求的范式，并解释其他范式为何不太合适。

Step 3: Layout sketch

步骤3：布局草图

Produce a text description of the layout: panel positions, element placement, arrows, colour assignments. The goal is that the user could draw the first draft from the sketch alone.

生成布局的文字描述：面板位置、元素摆放、箭头、颜色分配。目标是用户仅通过草图就能绘制出初稿。

Step 4: Labelling and annotation guidance

步骤4：标注与注释指南

Name every visible element concretely (no "Module A", "X", "Y").
Annotate critical points (failure highlight, success highlight, comparison emphasis).
Specify font sizes and colour palette. Default colour palette: ColorBrewer Qualitative or Viridis for sequential.

为每个可见元素赋予具体名称（避免使用“模块A”“X”“Y”这类占位符）
标注关键点（失败高亮、成功高亮、对比重点）
指定字体大小和调色板。默认调色板：ColorBrewer定性调色板或Viridis连续调色板

Step 5: Tool suggestion

步骤5：工具建议

See: references/tools.md for the tool matrix and the decision heuristic.

Default recommendations:

Motivated Example and Solution Overview: PowerPoint (draft), Figma (polish).
Experimental Results: Matplotlib or Seaborn in a reusable
```
plot_utils.py
```
script.
LaTeX-integrated figures: TikZ or PGFPlots.

参考：references/tools.md中的工具矩阵和决策规则。

默认推荐：

Motivated Example和Solution Overview：PowerPoint（初稿）、Figma（精修）
实验结果：使用可复用的
```
plot_utils.py
```
脚本搭配Matplotlib或Seaborn
LaTeX集成图表：TikZ或PGFPlots

Step 6: Universal rule audit

步骤6：通用规则审核

See: references/design-rules.md for the full universal rule set.

Verify every proposed or existing figure against:

Vector format (PDF, EPS, SVG) for export.
Font size at least 8pt post-scaling.
Small canvas (not large canvas with small fonts).
Colour-blind-safe palette; no colour-only encoding.
Self-contained caption whose first sentence states the core finding.
Honest axis ranges.
No 3D effects, no chartjunk.

Flag every violation with severity.

参考：references/design-rules.md中的完整通用规则集。

针对所有拟设计或已存在的图表，验证以下规则：

导出格式为矢量格式（PDF、EPS、SVG）
缩放后的字体大小至少为8pt
画布尺寸适中（避免大画布配小字体）
色弱友好调色板；不依赖单一颜色编码信息
标题具备独立性，首句点明核心结论
坐标轴范围真实准确
无3D效果、无冗余图表元素

标记所有违规项并注明严重程度。

Step 7: Integrity gate

步骤7：完整性校验

Run the checks in the Integrity gate section below.

执行下方完整性校验部分的检查项。

Step 8: Output

步骤8：输出

Emit the full design in the Output format below.

按照下方输出格式生成完整设计方案。

Integrity gate

完整性校验

Bullets tagged [inspection] are checked by the LLM from its own output. Bullets tagged [user-verify] require the user to confirm because the check depends on either the drawn figure or knowledge the skill does not have (paper context, prior Introduction).

Before returning the design:

[inspection] Paradigm matches figure type (motivated example is not a pipeline; overview is not a bar chart).
[inspection] Layout sketch is concrete enough that the user could draw from it.
[inspection] Labels are real entity names, not placeholders.
[inspection] Tool suggestion matches the figure's complexity (not Matplotlib for a multi-icon motivated example, not PowerPoint for a 20-method bar chart).
[inspection] when image provided, [user-verify] text-only Universal rule audit has been run; no CRITICAL violation is left unaddressed. Vision-only rules (raster-vs-vector, font size, colour palette) are only checkable when the user supplies an image.
[user-verify] For motivated examples, the example is the same running example referenced by the Introduction (no new example introduced in Figure 1). The skill does not see the Introduction; the user confirms.
[inspection] For experimental results, the chart type matches the data type (time-series uses line, multi-method comparison uses grouped bar, trade-off uses scatter).

If any [inspection] check fails, mark the design as "needs user attention". For [user-verify] items, surface them to the user as items they must confirm before submission.

标记[inspection]的项目由LLM自行检查输出内容。标记[user-verify]的项目需要用户确认，因为检查依赖已绘制的图表或本技能不具备的知识（论文上下文、引言内容）。

返回设计方案前：

[inspection] 范式与图表类型匹配（Motivated Example不应是流程图；Solution Overview不应是柱状图）
[inspection] 布局草图足够具体，用户可据此绘制图表
[inspection] 标签为真实实体名称，而非占位符
[inspection] 工具建议与图表复杂度匹配（多图标Motivated Example不推荐Matplotlib；20种方法对比的柱状图不推荐PowerPoint）
[inspection（提供图片时），user-verify（纯文本模式时）] 已完成通用规则审核；无未解决的CRITICAL级违规。仅能通过视觉检查的规则（栅格/矢量、字体大小、调色板）仅在用户提供图片时可验证
[user-verify] 对于Motivated Example，该示例需与引言中提及的贯穿示例一致（图1中不得引入新示例）。本技能无法查看引言内容，需用户确认
[inspection] 对于实验结果，图表类型与数据类型匹配（时间序列用折线图、多方法对比用分组柱状图、权衡关系用散点图）

若任一[inspection]检查项未通过，标记设计方案为“需用户关注”。对于[user-verify]项，需向用户明确指出这些是提交前必须确认的内容。

Output format

输出格式

1. Figure type

1. 图表类型

Type: <motivated-example or solution-overview or experimental-results>
Reason: <one sentence>

类型：<motivated-example / solution-overview / experimental-results>
原因：<一句话说明>

2. Paradigm recommendation

2. 范式推荐

Paradigm: <name>
Why this paradigm: <rationale>
Alternatives considered and rejected: <list>

范式：<名称>
推荐理由：<合理性说明>
已考虑并排除的替代方案：<列表>

3. Layout sketch

3. 布局草图

Canvas: <size>
Panels: <list with positions and contents>
Arrows and connections: <list>
Colour assignment: <mapping>

画布：<尺寸>
面板：<含位置和内容的列表>
箭头与连接：<列表>
颜色分配：<映射关系>

4. Labelling and annotations

4. 标注与注释

Element names: <list>
Critical highlights: <list>
Font sizes: <target>
Colour palette: <name>

元素名称：<列表>
重点高亮：<列表>
字体大小：<目标值>
调色板：<名称>

5. Tool suggestion

5. 工具建议

Primary: <tool>
Alternative: <tool>
Reason: <rationale>

首选：<工具>
备选：<工具>
理由：<合理性说明>

6. Universal rule audit

6. 通用规则审核

7. Integrity gate result

7. 完整性校验结果

Gate 1-7: <pass or fail>

校验项1-7：<通过 / 不通过>

8. Severity summary

8. 严重程度汇总

<n> CRITICAL, <m> MAJOR, <k> MINOR
Top three actions first: ...

<n> 严重问题，<m> 主要问题，<k> 次要问题
优先处理的三项行动：...