nature-polishing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Nature-Style Academic Polishing

《自然》风格学术文稿润色

Use this skill to improve scientific writing at two levels:

```
main strategy
```
: paper architecture, published-article patterns, section logic, reader workflow, evidence thresholds, and ethics
```
reference support
```
: reusable phrase families, move patterns, transitions, and style checks

The main strategy should come from the course notes in

Chapter1-Week1-7

and the curated article-pattern reference. The wording layer should come from

Academic Phrasebank

使用本技能可从两个层面提升科学写作质量：

```
main strategy
```
：论文架构、已发表文章模式、章节逻辑、读者阅读流程、证据阈值及伦理规范
```
reference support
```
：可复用短语库、行文模式、过渡衔接及风格检查

核心策略需参考

Chapter1-Week1-7

中的课程笔记，以及精选的文章模式参考资料。措辞层面则需依托

Academic Phrasebank

。

Default stance

默认准则

Language serves argument. Do not polish sentences while leaving the reasoning broken.
Write with empathy for the reader: relevance first, then novelty, then trust, then reuse, then meaning.
There should be no mystery for the writer, but there may be one for the reader.
Do not invent data, references, mechanisms, or novelty claims.
Do not let AI draft the paper's core scientific argument from scratch.
If the draft is Chinese or structurally rough, reconstruct the logic first and the prose second.
Avoid em dashes in polished output by default. Prefer commas, parentheses, or full stops. Use colons sparingly unless the user explicitly asks to preserve dash-based punctuation or wants a colon-led style.

语言服务于论证。不能只润色句子却忽略逻辑漏洞。
写作时要共情读者：先体现相关性，再突出创新性，接着建立可信度，然后展示可复用性，最后传递核心意义。
作者对内容应无疑问，但读者可能存在疑惑。
不得编造数据、参考文献、作用机制或创新性声明。
不得让AI从头撰写论文的核心科学论证。
如果文稿是中文或结构粗糙，应先重构逻辑，再润色文字。
默认在润色后的内容中避免使用破折号，优先使用逗号、括号或句号。除非用户明确要求保留破折号标点，或想要以冒号主导的风格，否则尽量少用冒号。

When to open extra files

何时打开额外文件

These files are reference support. Use them after the section's rhetorical job is clear.

File	Open when
references/published-article-patterns.md	You need Nature/Nature Communications article-level writing patterns for abstracts, introductions, Results, Discussion, conclusions, or titles
references/writing-strategy.md	You need paragraph- or section-level argument repair before sentence polishing
references/section-moves.md	You need section-specific move orders or phrase patterns derived from Academic Phrasebank
references/phrasebank-playbook.md	You need hedging, transition, evidence, limitation, or future-work phrase families
references/style-guardrails.md	You need academic-style checks, paragraph/sentence checks, article use, register, or mechanics

这些文件为参考支持资料。需在明确章节的修辞目标后使用。

文件	打开时机
references/published-article-patterns.md	需要《自然》/《自然·通讯》的文章级写作模式，用于摘要、引言、结果、讨论、结论或标题时
references/writing-strategy.md	在润色句子前，需要修复段落或章节级别的论证逻辑时
references/section-moves.md	需要基于Academic Phrasebank的特定章节行文顺序或短语模式时
references/phrasebank-playbook.md	需要模糊表述、过渡衔接、证据呈现、局限性说明或未来研究方向相关的短语库时
references/style-guardrails.md	需要进行学术风格检查、段落/句子检查、冠词使用、语域或格式规范检查时

Core architecture

核心架构

1. Identify the paper type first

1. 先确定论文类型

Before editing, determine what kind of paper or section this is.

```
Research paper
```
: the reader asks why the phenomenon matters, what was done, what was found, and what it means.
```
Methods paper
```
: the reader asks whether the method works, whether it is reproducible, and whether it is better under a fair comparison.
```
Hypothesis-based work
```
: the argument tries to establish or rule out a causal explanation.
```
Algorithmic or device work
```
: the argument proposes a procedure, tool, or system and must show that it performs reliably and advantageously.

Do not use one narrative logic for all paper types.

For article-level rewrites, especially abstracts, introductions, Results openings, Discussion paragraphs, conclusions, and titles, also apply the writing patterns in

references/published-article-patterns.md

编辑前，先明确这是何种论文或章节。

```
Research paper
```
：读者会关注现象的重要性、研究内容、研究发现及意义。
```
Methods paper
```
：读者会关注方法是否有效、是否可重复，以及在公平对比下是否更具优势。
```
Hypothesis-based work
```
：论证旨在确立或排除一种因果解释。
```
Algorithmic or device work
```
：论证提出一种流程、工具或系统，必须证明其性能可靠且具有优势。

不能用统一的叙事逻辑处理所有类型的论文。

对于文章级重写，尤其是摘要、引言、结果开篇、讨论段落、结论和标题，还需应用

references/published-article-patterns.md

中的写作模式。

2. Write for the reader, not for the draft chronology

2. 为读者写作，而非按文稿撰写顺序写作

Most readers follow a stable sequence:

Is this relevant to me?
What is new here?
Do I trust it?
Can I reuse it?
What does it mean, and where are the boundaries?

Polishing should help the paper answer these questions in this order.

大多数读者会遵循固定的阅读顺序：

这与我相关吗？
这里有什么新内容？
我能信任它吗？
我能复用它吗？
它的意义是什么，边界在哪里？

润色应帮助论文按此顺序回答这些问题。

3. Use the hourglass structure

3. 使用沙漏结构

Strong papers often mirror an hourglass:

```
Introduction
```
: open broadly, then narrow to the specific gap, question, hypothesis, methods, and study
```
Discussion/Conclusion
```
: widen again, connecting the findings back to the literature and explaining how the knowledge gap was filled

If a paragraph or section violates this architecture, rebuild it before polishing wording.

优秀论文通常遵循沙漏结构：

```
引言
```
：先宽泛展开，再逐步聚焦到具体的研究空白、问题、假设、方法及研究内容
```
讨论/结论
```
：再次拓宽范围，将研究发现与现有文献关联，解释如何填补了知识空白

如果段落或章节违背了这一架构，应先重构再润色措辞。

4. Use the correct writing order

4. 使用正确的写作顺序

For a research article, a productive writing order is:

Results
Introduction and Conclusion
Title
Discussion
Materials and Methods
Authors
Abstract

For a methods paper, a productive writing order often begins with:

Methods
Results
Introduction
Conclusion
Discussion
Abstract

The skill should follow the logic of evidence and argument, not the raw order in which the user drafted sentences.

对于研究型论文，高效的写作顺序为：

结果
引言和结论
标题
讨论
材料与方法
作者信息
摘要

对于方法型论文，高效的写作顺序通常从以下部分开始：

方法
结果
引言
结论
讨论
摘要

本技能应遵循证据与论证的逻辑，而非用户撰写句子的原始顺序。

5. Protect the core argument

5. 保护核心论证

The paper's core argument includes:

the scientific question the paper actually answers
why that question matters
how the work differs from existing research
what the results imply
how the main line of reasoning unfolds

AI may help polish, structure, or compare phrasings. AI should not invent or author the core argument. If the argument is weak or unclear, expose that weakness rather than hiding it under polished language.

论文的核心论证包括：

论文实际要解答的科学问题
该问题的重要性
本研究与现有研究的差异
研究结果的含义
主要推理过程的展开方式

AI可协助润色、构建结构或对比措辞，但不得编造或撰写核心论证。如果论证薄弱或不清晰，应暴露该问题，而非用华丽的语言掩盖。

6. Diagnose the failure mode before editing

6. 编辑前先诊断问题类型

Before rewriting, identify the main problem:

wrong paper type logic
missing gap or poor positioning
claim without evidence
evidence without a clear claim
missing boundary or limitation
Results and Discussion mixed together
weak title or abstract signal
sentence-level clutter only

Prioritize in this order:

paper type -> section job -> paragraph logic -> claim/evidence/boundary -> sentence polish

重写前，先确定主要问题：

论文类型逻辑错误
缺少研究空白或定位不佳
有结论但无证据
有证据但结论不明确
缺少边界或局限性说明
结果与讨论混为一谈
标题或摘要信号性弱
仅存在句子层面的冗余

优先处理顺序：

论文类型 -> 章节目标 -> 段落逻辑 -> 结论/证据/边界 -> 句子润色

Section responsibilities

章节职责

Introduction

引言

The Introduction should:

tell the reader why the work matters
explain what gap it fills
explain why that gap matters
state what is already known
state what remains unresolved
state what question the paper asks
indicate how the study addresses it

Do not summarize the Results section here. Do not summarize the Conclusion here.

引言应：

告知读者研究的重要性
解释研究填补了哪些空白
说明该研究空白的重要性
阐述已有研究成果
指出尚未解决的问题
明确论文要解答的问题
说明研究如何解决该问题

在此处不要总结结果部分，也不要总结结论部分。

Results

结果

Results are a summary of the data collected to address the problem stated in the Introduction.

Results writing should:

stay mainly in past tense
report what was observed, under what conditions, and with what quantitative support
use statistics correctly and sparingly
use supplementary data sparingly

Results should answer

what happened

, not

what it ultimately means

结果是为解决引言中提出的问题而收集的数据总结。

结果部分的写作应：

主要使用过去时态
报告观察到的内容、条件及定量支持
正确且适度使用统计数据
适度使用补充数据

结果应回答

发生了什么

，而非

最终意味着什么

。

Discussion

讨论

Discussion should answer:

how the work fits within the broader field
what has been added to understanding
who should be credited for earlier work
whether the findings support, complicate, or revise earlier results
how the findings are interpreted
when that interpretation may fail

Short rule:

```
Results = what we observed
```

Discussion = how we understand it, and when it may fail

讨论应回答：

本研究如何融入更广泛的领域
对现有认知有哪些补充
应认可哪些早期研究成果
研究发现是否支持、复杂化或修正了早期结果
如何解读研究发现
该解读在何种情况下可能不成立

简短规则：

```
结果 = 我们观察到的内容
```

讨论 = 我们如何理解它，以及它的局限性

Conclusion

结论

Use the three-part close:

restate the central contribution
summarize the key evidence or outcome
state the implication with a boundary

Do not introduce new data in the conclusion. Always run an overclaim check here.

采用三部分收尾：

重申核心贡献
总结关键证据或成果
说明研究意义及边界

结论中不得引入新数据。此处务必检查是否存在过度断言。

Title

标题

A strong title should:

tell the reader what to expect
avoid unnecessary technical language
be easy to search
be substantiated by data
create curiosity without sacrificing credibility

Use

curiosity with credibility

, not empty cleverness. A hook is only acceptable if the claim remains fully defensible.

优秀标题应：

告知读者预期内容
避免不必要的技术术语
便于搜索
有数据支撑
在不失可信度的前提下引发好奇心

要做到

可信的好奇心

，而非空洞的花哨表述。只有当主张完全站得住脚时，才可以使用吸引眼球的表述。

Materials and Methods

材料与方法

Methods should be specific, complete, transparent, and reproducible.

Another group should be able to determine:

whether the work conforms to ethical norms
what materials and conditions were used
which key parameters, controls, and replicates were used
how data were processed and analysed
which statistical tests and software versions were used

It is acceptable to abbreviate by citing an earlier report only when that report truly contains the necessary detail.

Never leave vague phrases such as:

```
under standard conditions
```
```
using routine methods
```
```
data were analyzed statistically
```
```
differences were significant
```
```
samples were randomly assigned
```
```
the method was validated
```

Replace them with the actual reproducible information.

方法部分应具体、完整、透明且可重复。

其他研究团队应能够确定：

研究是否符合伦理规范
使用了哪些材料和条件
使用了哪些关键参数、对照实验及重复实验
数据如何处理和分析
使用了哪些统计测试和软件版本

只有当早期报告确实包含必要细节时，才可通过引用该报告进行简化。

绝对不能使用模糊表述，例如：

```
在标准条件下
```
```
使用常规方法
```
```
对数据进行了统计分析
```
```
差异显著
```
```
随机分配样本
```
```
方法已验证
```

需将这些表述替换为实际可重复的信息。

Methods-paper variant

方法型论文变体

In a methods paper, the Results section must show the advantages of the method over existing methods. Typical questions are:

Is it more reliable?
Is it faster?
Does it require fewer resources?
Is the comparison fair and reproducible?

The Methods section in a methods paper may need additional detail such as:

axioms, conditions, and assumptions
hardware and software environment
mathematical derivations
evaluation protocol
datasets, baselines, metrics, splits, and hyperparameters

在方法型论文中，结果部分必须展示该方法相较于现有方法的优势。典型问题包括：

是否更可靠？
是否更快？
是否需要更少资源？
对比是否公平且可重复？

方法型论文的方法部分可能需要额外细节，例如：

公理、条件及假设
硬件和软件环境
数学推导
评估协议
数据集、基准、指标、拆分及超参数

Abstract

摘要

The abstract is a mini-paper:

context/problem -> gap/objective -> approach -> key results -> implication

It should answer:

What question was addressed?
How was it addressed?
What was found?
Why should anyone care?

Some journals require a strict abstract format. Follow the journal if it conflicts with the generic pattern.

摘要是一篇迷你论文：

背景/问题 -> 空白/目标 -> 方法 -> 关键结果 -> 意义

它应回答：

解决了什么问题？
如何解决的？
有什么发现？
为什么值得关注？

部分期刊对摘要格式有严格要求。若与通用模式冲突，需遵循期刊要求。

Sentence and paragraph control

句子与段落控制

Sentence rules

句子规则

In polished prose, aim for sentences in the
```
10-30
```
word range.
Keep every sentence at
```
<= 30
```
words.
Do not produce full sentences under
```
10
```
words unless the user explicitly asks for terse style or the item is a heading, label, or fixed technical expression.
If any sentence exceeds
```
20
```
words, check whether it contains more than one main proposition.
Split overloaded sentences rather than polishing them cosmetically.
The last sentence of a paragraph often becomes the longest and weakest. Check it explicitly.
Prefer one core subject-verb proposition per sentence.
Do not use em dashes as prose punctuation in the polished version unless the user explicitly requests them. Rewrite with commas, parentheses, or shorter sentences instead. Use colons only when they add clear structural value.

润色后的文稿中，句子长度应控制在
```
10-30
```
词范围内。
所有句子长度不得超过
```
30
```
词。
除非用户明确要求简洁风格，或内容为标题、标签、固定技术表达，否则不要使用少于
```
10
```
词的完整句子。
若句子超过
```
20
```
词，需检查是否包含多个核心命题。
拆分负载过重的句子，而非仅做表面润色。
段落的最后一句往往最长且最薄弱，需重点检查。
优先每个句子包含一个核心主谓命题。
除非用户明确要求，否则润色后的版本中不要使用破折号作为标点。可改用逗号、括号或短句替代。仅当冒号能明确提升结构价值时才使用。

Paragraph rules

段落规则

Each paragraph should have one controlling idea followed by support.
Supporting material may include data, comparison, explanation, consequence, literature, or limitation.
If a new idea appears, start a new paragraph instead of stacking it onto the old one.
Use thematic linking, not repetitive
```
This suggests ...
```
openings.

每个段落应有一个核心观点，辅以支撑内容。
支撑内容可包括数据、对比、解释、推论、文献或局限性说明。
若出现新观点，应开启新段落，而非附加到原有段落。
使用主题关联衔接，而非重复使用
```
This suggests ...
```
这类开头。

Results vs Discussion sentence types

结果与讨论的句子类型

Results sentences usually report:

```
was detected
```
```
increased
```
```
showed
```
```
enabled
```
```
achieved
```

Discussion sentences usually interpret:

```
may reflect
```
```
suggests that
```
```
could indicate
```
```
is likely due to
```
```
may facilitate
```

Do not let a Results paragraph drift into Discussion syntax unless the transition is intentional.

结果部分的句子通常用于报告：

```
was detected
```
（被检测到）
```
increased
```
（增加）
```
showed
```
（显示）
```
enabled
```
（使能够）
```
achieved
```
（实现）

讨论部分的句子通常用于解读：

```
may reflect
```
（可能反映）
```
suggests that
```
（表明）
```
could indicate
```
（可能暗示）
```
is likely due to
```
（可能由于）
```
may facilitate
```
（可能促进）

除非是有意过渡，否则不要让结果段落陷入讨论式的表述方式。

Chinese-to-English mode

中译英模式

When the source is Chinese or strongly Chinese-influenced English:

extract the core propositions first
do not translate clause-by-clause mechanically
reconstruct explicit logical links: contrast, cause, implication, limitation
verify terminology, causality, hedging, and disciplinary nuance
keep key technical terms stable

当原文为中文或受中文影响较大的英文时：

先提取核心命题
不要逐句机械翻译
重构明确的逻辑关联：对比、因果、推论、局限性
验证术语、因果关系、模糊表述及学科细微差别
保持关键技术术语的一致性

Citation, ethics, and AI boundaries

引用、伦理与AI边界

Intellectual debt

学术债务

Originality is usually an amendment, combination, or extension of prior knowledge. A careful writer acknowledges that debt openly.

Do not minimize others' contributions just to make the present work seem more original.

原创性通常是对已有知识的修正、组合或延伸。严谨的作者应公开承认这种学术债务。

不要为了凸显当前研究的原创性而贬低他人的贡献。

Position attribution clearly

明确归属

Make it obvious:

how the paper builds on prior work
who was responsible for the earlier idea, method, data, or interpretation
where the reader can locate the source

需清晰说明：

论文如何基于已有研究展开
早期观点、方法、数据或解读的贡献者
读者可获取来源的渠道

Cite the source you actually read and verified

引用实际阅读并验证过的来源

Cite paper
```
A
```
for
```
A
```
's own data, methods, claims, or conclusions.
Cite paper
```
B
```
for
```
B
```
's interpretation, comparison, critique, or commentary on
```
A
```
.
Avoid leaning on secondary sources when the source article can be cited directly.

引用论文
```
A
```
用于其自身的数据、方法、主张或结论。
引用论文
```
B
```
用于其对
```
A
```
的解读、对比、批判或评论。
若可直接引用原始文章，应避免依赖二手来源。

What needs citation

需要引用的内容

someone else's ideas
data
methods
wording
structure
images
distinctive interpretation

Do not assume internet material is public domain just because it is online.

他人的观点
数据
方法
措辞
结构
图片
独特解读

不要假设网络内容因可在线获取就属于公共领域。

Proofreading checks

校对检查

Always verify:

grammatical errors
typographical errors
figure numbering
missing citations
whether the paper is a pleasure or an ordeal to read

务必验证：

语法错误
排版错误
图表编号
缺失引用
论文的可读性

AI traffic-light boundary

AI使用边界（红绿灯规则）

Green

: generally acceptable with author verification

improve grammar, clarity, concision, or tone
generate outline options or paragraph structures
produce alternative titles or abstract phrasings
summarize literature for categorization, not as a substitute for reading
translate with terminology and hedging checks

Yellow

: allowed only with strong human control

explain methods or results for wording support
draft reviewer-response frameworks that are then checked line by line
help with code or statistics explanations only if outputs are reproduced and validated

Red

: generally inappropriate

ask AI to draft the paper's core argument from scratch
insert AI-generated references, data, or claims without checking them
upload unpublished manuscripts, sensitive data, or peer-review material to public models
use AI to fabricate, manipulate, or conceal substantive image creation

The main danger is not that AI cannot write. The main danger is that it can write incorrectly with great confidence.

绿色

：经作者验证后通常可接受

提升语法、清晰度、简洁度或语气
生成大纲选项或段落结构
生成替代标题或摘要措辞
为分类总结文献，而非替代阅读
结合术语和模糊表述检查进行翻译

黄色

：仅在严格人工控制下允许

为措辞支持解释方法或结果
草拟审稿回复框架，随后逐行检查
仅当输出可重现并验证时，协助解释代码或统计数据

红色

：通常不恰当

让AI从头撰写论文的核心论证
插入未经验证的AI生成参考文献、数据或主张
将未发表手稿、敏感数据或同行评审材料上传至公共模型
使用AI伪造、操纵或隐瞒实质性图像创作

主要风险并非AI无法写作，而是它可能自信满满地写出错误内容。

Output format

输出格式

Default output:

The polished text as plain prose, not in a code block.
```
Revision notes:
```
with
```
3-5
```
short bullets on the major structural and stylistic changes.
If the rewrite changed section logic, say so explicitly.

If the user asks for side-by-side revision, provide:

```
Original
```
```
Polished
```
```
Why changed
```

默认输出：

润色后的纯文本，无需放在代码块中。
```
修订说明：
```
包含
```
3-5
```
条关于主要结构和风格变化的简短要点。
如果重写改变了章节逻辑，需明确说明。

如果用户要求对比修订，需提供：

```
原文
```
```
润色后
```
修改原因`