figure-results-review

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Figure Results Review

图表结果审核

Audit figures, tables, plots, captions, and result narratives before they become paper evidence or meeting material.

Use this skill when:

the user has a figure, table, plot, result screenshot, caption, result section, or slide with experimental evidence
a paper claim needs to be checked against the actual displayed evidence
a plot may be missing baselines, error bars, seeds, labels, units, or fairness context
a table layout hides the main comparison or makes the result look weaker than it is
paper figures need a consistent visual style: color palette, markers, symbols, line widths, fonts, sizing, and notation
new results require deciding whether to update writing, rerun experiments, diagnose failures, or narrow claims
a rebuttal needs a clean result table or concise visual answer
an advisor meeting needs figures that make the decision obvious

Do not use this skill to design experiments from scratch. Use

experiment-design-planner

before results exist. Use

result-diagnosis

when the primary issue is why a result is surprising or broken. Use

conference-writing-adapter

when the main task is prose style after the evidence is already accepted.

Pair this skill with:

```
paper-evidence-board
```
when figures/tables must be linked to paper claims, sections, reviewer risks, and actions
```
result-diagnosis
```
when a plotted result is suspicious, unstable, negative, or contradictory
```
baseline-selection-audit
```
when the visual exposes missing, weak, or unfair baselines
```
experiment-design-planner
```
when the fix requires new experiments, ablations, controls, or metrics
```
experiment-report-writer
```
when raw results need a structured report before figure review
```
conference-writing-adapter
```
when the final figure narrative or visual style must be adapted to a target venue
```
research-project-memory
```
when claim/evidence/risk/action updates should persist across sessions

在实验图表、表格、绘图、标题及结果说明成为论文证据或会议材料之前，对其进行审核。

适用场景：

用户持有包含实验证据的图表、表格、绘图、结果截图、标题、结果章节或演示文稿
需要对照实际展示的证据检查论文观点
绘图可能缺少基线、误差棒、随机种子、标签、单位或公平性相关背景信息
表格布局隐藏了核心对比，或使结果看起来比实际更弱
论文图表需要统一的视觉风格：调色板、标记、符号、线宽、字体、尺寸及符号规范
新结果需要决定是否更新文稿、重新运行实验、诊断失败原因或缩小观点范围
反驳材料需要清晰的结果表格或简洁的可视化答复
导师会议需要能让决策一目了然的图表

不适用场景：

从头设计实验。在获得结果前请使用
```
experiment-design-planner
```
。
主要问题是结果为何令人惊讶或出现异常时，请使用
```
result-diagnosis
```
。
证据已被认可后主要任务是调整 prose 风格时，请使用
```
conference-writing-adapter
```
。

可搭配使用的技能：

当图表/表格必须与论文观点、章节、审稿人质疑及行动项关联时，搭配
```
paper-evidence-board
```
当绘图结果存在可疑、不稳定、负面或矛盾情况时，搭配
```
result-diagnosis
```
当可视化内容暴露出缺失、薄弱或不公平的基线时，搭配
```
baseline-selection-audit
```
当修复方案需要新实验、消融实验、控制变量或新指标时，搭配
```
experiment-design-planner
```
当原始结果需要先整理成结构化报告再进行图表审核时，搭配
```
experiment-report-writer
```
当最终的图表说明或视觉风格需要适配目标会议/期刊时，搭配
```
conference-writing-adapter
```
当观点/证据/风险/行动项的更新需要跨会话持久保存时，搭配
```
research-project-memory
```

Skill Directory Layout

技能目录结构

text

<installed-skill-dir>/
├── SKILL.md
└── references/
    ├── caption-and-narrative.md
    ├── claim-support.md
    ├── memory-writeback.md
    ├── paper-visual-style.md
    ├── report-template.md
    ├── statistical-evidence.md
    └── visual-integrity.md

text

<installed-skill-dir>/
├── SKILL.md
└── references/
    ├── caption-and-narrative.md
    ├── claim-support.md
    ├── memory-writeback.md
    ├── paper-visual-style.md
    ├── report-template.md
    ├── statistical-evidence.md
    └── visual-integrity.md

Progressive Loading

渐进式加载规则

Always read

references/claim-support.md

references/visual-integrity.md

, and

references/statistical-evidence.md

Read
```
references/paper-visual-style.md
```
when figures/tables are intended for a paper, slide deck, rebuttal, camera-ready, or venue-specific rewrite.
Read
```
references/caption-and-narrative.md
```
when revising captions, result prose, slide text, or paper figure callouts.
Read
```
references/report-template.md
```
before writing the final review.
Read
```
references/memory-writeback.md
```
when the project has
```
memory/
```
, component
```
.agent/
```
folders, or the user asks for persistent project memory.
If the expected plotting or table conventions depend on a target venue, benchmark, or recent paper style, verify with current accepted papers, official benchmark protocols, or user-provided exemplars.
If the actual image/table cannot be inspected, audit the provided data/caption/prose and clearly mark visual-layout judgments as unverified.

务必阅读

references/claim-support.md

、

references/visual-integrity.md

和

references/statistical-evidence.md

。

当图表/表格用于论文、演示文稿、反驳材料、终稿或特定会议/期刊改写时，阅读
```
references/paper-visual-style.md
```
。
当修订标题、结果文本、演示文稿文字或论文图表标注时，阅读
```
references/caption-and-narrative.md
```
。
在撰写最终审核报告前，阅读
```
references/report-template.md
```
。
当项目包含
```
memory/
```
目录、组件
```
.agent/
```
文件夹，或用户要求持久化项目记忆时，阅读
```
references/memory-writeback.md
```
。
如果绘图或表格的预期规范依赖于目标会议/期刊、基准测试或近期论文风格，请参考当前已发表的论文、官方基准测试协议或用户提供的示例进行验证。
如果无法检查实际图像/表格，请审核提供的数据/标题/文本，并明确标记视觉布局判断为“未验证”。

Core Principles

核心原则

A figure is evidence for a specific claim, not decoration.
Every plot/table should answer one reviewer question.
The main comparison should be visually and numerically easy to find.
Captions must state enough setup for the result to be interpreted without searching the paper.
Statistical uncertainty, seeds, and variance matter when the claim depends on small differences.
Compute, data, baseline, and protocol fairness must be visible when they affect interpretation.
Paper figures should share a deliberate visual language. Style choices are part of writing because they control what reviewers notice first.
A beautiful plot that does not support the claim should be revised or cut.
New results must update claims, writing, reviewer risks, and next actions.

图表是特定观点的证据，而非装饰。
每个绘图/表格都应回答一个审稿人的问题。
核心对比应在视觉和数值上易于识别。
标题必须包含足够的实验设置信息，无需查阅论文即可解读结果。
当观点依赖于微小差异时，统计不确定性、随机种子和方差至关重要。
当计算、数据、基线和实验协议会影响结果解读时，必须清晰展示其公平性。
论文图表应采用统一的视觉语言。风格选择是写作的一部分，因为它们决定了审稿人首先注意到的内容。
无法支持观点的精美绘图应被修订或删除。
新结果必须更新观点、文稿、审稿人质疑点和后续行动项。

Step 1 - Recover Evidence Context

步骤1 - 还原证据背景

Collect:

figure/table file path, screenshot, raw data, caption, or result prose
paper claim or section the result is meant to support
experiment setup: dataset, model, baseline, metric, seed, split, hyperparameters, protocol
target audience: paper, advisor meeting, slide, rebuttal, internal report, or appendix
target venue or benchmark expectations
current paper location, if any

linked project memory IDs such as

CLM-###

EVD-###

FIG-###

TAB-###

RSK-###

, or

ACT-###

Rewrite the intended evidence relation:

text

This figure/table is supposed to show that [claim] because [metric/comparison/trend] under [setup].

If that sentence cannot be written, route to

paper-evidence-board

before polishing the visual.

收集以下信息：

图表/表格的文件路径、截图、原始数据、标题或结果文本
该结果旨在支持的论文观点或章节
实验设置：数据集、模型、基线、指标、随机种子、数据划分、超参数、实验协议
目标受众：论文、导师会议、演示文稿、反驳材料、内部报告或附录
目标会议/期刊或基准测试的预期要求
当前在论文中的位置（如有）
关联的项目记忆ID，如
```
CLM-###
```
、
```
EVD-###
```
、
```
FIG-###
```
、
```
TAB-###
```
、
```
RSK-###
```
或
```
ACT-###
```

重写预期的证据关联关系：

text

此图表/表格旨在通过[设置]下的[指标/对比/趋势]证明[观点]。

如果无法写出上述句子，请先使用

paper-evidence-board

工具，再优化可视化内容。

Step 2 - Audit Claim Support

步骤2 - 审核观点支持性

Read

references/claim-support.md

For each figure or table, answer:

what exact claim does it support?
is the displayed evidence sufficient for that claim?
is the claim too broad for the measured setup?
are baselines, ablations, controls, or diagnostics missing?
does the result contradict another figure, table, or section?
is the result main-paper material, appendix material, diagnostic material, or not ready?

Assign one status:

```
supports-claim
```
```
supports-narrower-claim
```
```
ambiguous
```
```
contradicts-claim
```
```
diagnostic-only
```
```
not-ready
```

阅读

references/claim-support.md

。

针对每个图表或表格，回答以下问题：

它具体支持哪个观点？
展示的证据是否足以支持该观点？
观点是否超出了实测设置的范围？
是否缺少基线、消融实验、控制变量或诊断信息？
该结果是否与其他图表、表格或章节矛盾？
该结果属于主论文内容、附录内容、诊断内容还是尚未准备好？

分配以下状态之一：

```
supports-claim
```
（支持观点）
```
supports-narrower-claim
```
（支持更窄的观点）
```
ambiguous
```
（模糊不清）
```
contradicts-claim
```
（与观点矛盾）
```
diagnostic-only
```
（仅用于诊断）
```
not-ready
```
（尚未准备好）

Step 3 - Audit Visual and Table Integrity

步骤3 - 审核可视化与表格完整性

Read

references/visual-integrity.md

Check:

axes, labels, units, scales, and transformations
legend readability and method names
ordering of methods, datasets, metrics, and ablations
whether the main result is visually salient
table grouping, bolding, decimals, missing values, and footnotes
whether color, markers, line styles, or hatching remain readable in grayscale
whether figure size works for one-column, two-column, slide, or appendix usage
whether captions and labels match the actual plotted data

Flag any issue that could cause a reviewer to misread the result.

阅读

references/visual-integrity.md

。

检查以下内容：

坐标轴、标签、单位、刻度和变换方式
图例可读性及方法名称
方法、数据集、指标和消融实验的排序
核心结果是否在视觉上突出
表格分组、加粗、小数位数、缺失值和脚注
颜色、标记、线条样式或阴影在灰度模式下是否仍可读
图表尺寸是否适用于单栏、双栏、演示文稿或附录场景
标题和标签是否与实际绘制的数据一致

标记任何可能导致审稿人误读结果的问题。

Step 4 - Audit Paper Visual Style

步骤4 - 审核论文视觉风格

Read

references/paper-visual-style.md

when the output is paper-facing.

Check:

color palette and colorblind/grayscale robustness
stable method-to-color and method-to-marker mapping across all figures
line width, marker size, hatch, symbol, and notation consistency
font size, tick density, label length, and final-column readability
figure dimensions for one-column, two-column, appendix, or slide use
whether visual emphasis matches the paper's claim hierarchy
whether the main method is recognizable without relying only on color
whether theorem/method symbols in plots match the paper notation

If the paper has no visual style policy, propose one and record it in

paper/.agent/

.agent/conference-writing/project-style.md

when appropriate.

当输出内容面向论文时，阅读

references/paper-visual-style.md

。

检查以下内容：

调色板及色盲/灰度模式下的鲁棒性
所有图表中方法与颜色、方法与标记的映射是否稳定统一
线宽、标记大小、阴影、符号和符号规范的一致性
字体大小、刻度密度、标签长度和末栏可读性
适用于单栏、双栏、附录或演示文稿的图表尺寸
视觉重点是否与论文的观点层级匹配
核心方法是否无需仅依赖颜色即可识别
绘图中的定理/方法符号是否与论文中的符号一致

如果论文没有视觉风格规范，可提出一个规范，并在合适时记录在

paper/.agent/

或

.agent/conference-writing/project-style.md

中。

Step 5 - Audit Statistical and Experimental Evidence

步骤5 - 审核统计与实验证据

Read

references/statistical-evidence.md

Check:

number of seeds or repeated runs
variance, confidence intervals, standard deviation, or standard error
significance or effect-size interpretation when differences are small
data split and leakage risk
metric definition and averaging
baseline fairness and tuning budget
compute or speed reporting when efficiency is part of the claim
failure cases or negative results that should be shown

If the plot lacks necessary uncertainty, decide whether to rerun, add error bars, weaken the claim, or move the result to appendix/diagnostic status.

阅读

references/statistical-evidence.md

。

检查以下内容：

随机种子数量或重复运行次数
方差、置信区间、标准差或标准误
当差异较小时的显著性或效应量解读
数据划分和信息泄露风险
指标定义和平均方式
基线公平性和调参预算
当效率是观点一部分时的计算或速度报告
应展示的失败案例或负面结果

如果绘图缺少必要的不确定性信息，决定是否重新运行实验、添加误差棒、弱化观点，或将结果移至附录/诊断内容。

Step 6 - Review Caption and Result Narrative

步骤6 - 审核标题与结果说明

Read

references/caption-and-narrative.md

when output text needs revision.

For each figure/table, produce:

caption diagnosis
revised caption or caption outline
one-sentence paper callout
claims to avoid in nearby prose
reviewer question answered
missing setup details to add

Captions should not oversell. They should state the setup, comparison, metric, and takeaway.

当需要修订输出文本时，阅读

references/caption-and-narrative.md

。

针对每个图表/表格，生成以下内容：

标题诊断
修订后的标题或标题大纲
一句话式的论文标注
附近文本中应避免的观点表述
回答的审稿人问题
需要补充的实验设置细节

标题不应夸大其词，应说明实验设置、对比、指标和结论。

Step 7 - Route Fixes

步骤7 - 确定修复路径

For every issue, route to one or more actions:

```
edit-figure
```
: labels, ordering, scale, legend, layout, or visual emphasis
```
edit-table
```
: grouping, decimals, bolding, footnotes, missing values, or row/column order
```
rewrite-caption
```
: setup, metric, takeaway, caveat, or claim alignment
```
rewrite-results-text
```
: nearby paper prose overclaims or misses the takeaway
```
define-visual-style
```
: missing or inconsistent paper visual style policy
```
restyle-figure
```
: color, marker, line width, font size, symbol, panel layout, or emphasis
```
rerun
```
: missing seeds, variance, baseline, metric, or protocol
```
diagnose-result
```
: suspicious, negative, unstable, or contradictory pattern
```
baseline-audit
```
: missing or unfair baseline
```
narrow-claim
```
: evidence only supports a smaller statement
```
move-to-appendix
```
: useful but not central enough for main paper
```
cut
```
: visual does not support a paper need

Name the next skill when appropriate.

针对每个问题，指定一个或多个行动项：

```
edit-figure
```
（编辑图表）：标签、排序、刻度、图例、布局或视觉重点
```
edit-table
```
（编辑表格）：分组、小数位数、加粗、脚注、缺失值或行列顺序
```
rewrite-caption
```
（重写标题）：实验设置、指标、结论、注意事项或观点对齐
```
rewrite-results-text
```
（重写结果文本）：附近论文文本存在夸大或未突出结论的问题
```
define-visual-style
```
（定义视觉风格）：缺少或不一致的论文视觉风格规范
```
restyle-figure
```
（重新设置图表样式）：颜色、标记、线宽、字体大小、符号、面板布局或重点
```
rerun
```
（重新运行实验）：缺少随机种子、方差、基线、指标或实验协议
```
diagnose-result
```
（诊断结果）：可疑、负面、不稳定或矛盾的模式
```
baseline-audit
```
（基线审核）：缺失或不公平的基线
```
narrow-claim
```
（缩小观点）：证据仅支持更具体的表述
```
move-to-appendix
```
（移至附录）：有用但不足以成为主论文核心内容
```
cut
```
（删除）：可视化内容无法满足论文需求

必要时指定下一步使用的技能。

Step 8 - Write the Review Report

步骤8 - 撰写审核报告

Read

references/report-template.md

If saving to a project and no path is given, use:

text

docs/results/figure_results_review_YYYY-MM-DD_<short-name>.md

The report must include:

figure/table inventory
claim-support status
visual/table integrity issues
visual style policy and consistency issues
statistical evidence issues
caption and narrative fixes
reviewer-risk forecast
routed actions and next skills
memory update section

阅读

references/report-template.md

。

如果要保存到项目且未指定路径，请使用：

text

docs/results/figure_results_review_YYYY-MM-DD_<short-name>.md

报告必须包含：

图表/表格清单
观点支持状态
可视化/表格完整性问题
视觉风格规范及一致性问题
统计证据问题
标题与说明的修复方案
审稿人风险预测
指定的行动项及下一步技能
记忆更新部分

Step 9 - Write Back to Project Memory

步骤9 - 写入项目记忆

Read

references/memory-writeback.md

when memory exists.

Update the smallest useful set of entries:

```
memory/evidence-board.md
```
: figure/table evidence status, setup, and linked claims
```
memory/claim-board.md
```
: claims supported, narrowed, contradicted, or not ready
```
memory/risk-board.md
```
: reviewer risks from visual ambiguity, missing uncertainty, weak baselines, or overclaiming
```
memory/action-board.md
```
: figure edits, reruns, caption fixes, result diagnosis, or claim revisions
```
paper/.agent/
```
: figure/table map, paper locations, caption state, and stale visual warnings
```
.agent/conference-writing/project-style.md
```
: venue-facing figure style decisions when conference adaptation is active
worktree
```
.agent/worktree-status.md
```
: result-generation or plotting tasks and exit conditions

Use certainty labels:

```
verified
```
for values checked against raw data, logs, or source figures
```
user-stated
```
for user-supplied context
```
inferred
```
for reviewer-risk and narrative judgments
```
unverified
```
for visual or statistical claims that could not be inspected

当项目存在记忆功能时，阅读

references/memory-writeback.md

。

更新最小必要的条目集：

```
memory/evidence-board.md
```
：图表/表格的证据状态、设置及关联观点
```
memory/claim-board.md
```
：被支持、缩小、矛盾或未准备好的观点
```
memory/risk-board.md
```
：因视觉模糊、缺失不确定性信息、薄弱基线或夸大表述导致的审稿人风险
```
memory/action-board.md
```
：图表编辑、重新运行实验、标题修复、结果诊断或观点修订
```
paper/.agent/
```
：图表/表格映射、论文位置、标题状态及过时视觉警告
```
.agent/conference-writing/project-style.md
```
：当适配会议功能激活时，面向会议的图表风格决策
工作树
```
.agent/worktree-status.md
```
：结果生成或绘图任务及退出条件

使用确定性标签：

```
verified
```
（已验证）：对照原始数据、日志或源图表检查过的值
```
user-stated
```
（用户提供）：用户给出的背景信息
```
inferred
```
（推断）：关于审稿人风险和文本表述的判断
```
unverified
```
（未验证）：无法检查的视觉或统计观点

Final Sanity Check

最终合理性检查

Before finalizing:

every figure/table has a linked claim and reviewer question
main comparison is easy to find
axes, units, legends, captions, and table labels are unambiguous
colors, markers, fonts, symbols, and figure sizes are consistent across the paper
uncertainty is present or the lack of uncertainty is justified
baseline and compute fairness are visible when relevant
overclaims are narrowed
fixes are routed to concrete next actions or skills
project memory is updated when present

定稿前需确认：

每个图表/表格都关联了观点和审稿人问题
核心对比易于识别
坐标轴、单位、图例、标题和表格标签清晰明确
论文中所有图表的颜色、标记、字体、符号和尺寸保持一致
存在不确定性信息，或缺少不确定性信息的原因合理
相关时基线和计算公平性清晰可见
夸大的观点已被缩小
修复方案已指定为具体的下一步行动或技能
项目记忆已更新（如有）