Scientific Manuscript Review

科研手稿审阅

Purpose

目的

This skill provides systematic review and editing of scientific manuscripts (research articles, reviews, perspectives) to improve clarity, structure, scientific rigor, and reader comprehension. It applies a multi-pass approach covering structure, scientific logic, language, and formatting to transform drafts into publication-ready documents.

此功能为科研手稿（研究论文、综述、观点类文稿）提供系统性审阅与编辑服务，旨在提升文稿的清晰度、结构合理性、科学严谨性及读者可读性。它采用多轮审阅法，涵盖结构、科学逻辑、语言及格式层面，助力草稿转变为可投稿的终稿。

When to Use

适用场景

Use this skill when:

Drafting manuscripts: Research articles, short communications, review papers, perspectives
Pre-submission review: Final polish before journal submission
Revision cycles: Addressing reviewer comments, improving based on feedback
Collaborative editing: Reviewing co-author drafts, mentoring student writing
Self-editing: Systematic review of your own writing for blind spots
Journal transfer: Adapting manuscript for different journal format

Trigger phrases: "manuscript review", "paper draft", "journal article", "research writing", "improve my paper", "reviewer feedback", "submission ready", "scientific writing"

Do NOT use for:

Grant proposals (use
```
grant-proposal-assistant
```
)
Recommendation letters (use
```
academic-letter-architect
```
)
General emails (use
```
scientific-email-polishing
```
)

在以下场景中使用此功能：

手稿撰写阶段：研究论文、短篇通讯、综述、观点类文稿
投稿前审阅：期刊投稿前的最终润色
返修阶段：回应审稿人意见，基于反馈优化文稿
协作编辑：审阅合著者的草稿，指导学生写作
自我编辑：系统性审阅自己的写作内容，排查盲区
期刊转投：调整文稿以适配不同期刊的格式要求

触发短语："manuscript review"、"paper draft"、"journal article"、"research writing"、"improve my paper"、"reviewer feedback"、"submission ready"、"scientific writing"

请勿用于：

基金申请书（请使用
```
grant-proposal-assistant
```
）
推荐信（请使用
```
academic-letter-architect
```
）
通用邮件（请使用
```
scientific-email-polishing
```
）

Core Principles

核心原则

Seven foundational beliefs guiding manuscript review:

Clarity over cleverness: Scientific clarity is more important than stylistic elegance
Narrative shapes comprehension: Structure and story arc determine reader understanding
Audience dictates tone: Expert vs. general audience requires different depth and framing
Format signals credibility: Professional formatting reflects scientific rigor
Claims require evidence: Strong assertions need strong data and appropriate hedging
Each section has a job: Introduction sells the problem, Results show the data, Discussion interprets
Constraints shape structure: Word limits and journal guidelines determine emphasis

指导手稿审阅的七大基础准则：

清晰优先于华丽：科学表达的清晰度比文体优雅更重要
叙事决定理解：结构与叙事脉络影响读者的理解程度
受众决定语气：面向专家与普通受众需采用不同的深度与框架
格式彰显可信度：专业格式体现科学严谨性
观点需有依据：有力的论断需要充分的数据支撑与恰当的措辞
各章节各司其职：引言阐明研究问题，结果呈现数据，讨论解读意义
约束塑造结构：字数限制与期刊准则决定内容的侧重点

Workflow

工作流程

Copy this checklist and track your progress:

Manuscript Review Progress:
- [ ] Step 1: Identify manuscript type and extract core message
- [ ] Step 2: Structural pass - map and evaluate overall organization
- [ ] Step 3: Introduction review - gap statement, focus, hypothesis
- [ ] Step 4: Results review - question, approach, finding, interpretation
- [ ] Step 5: Discussion review - synthesis, context, limitations
- [ ] Step 6: Scientific clarity check - claims, controls, hedging
- [ ] Step 7: Language polish - terminology, voice, jargon
- [ ] Step 8: Formatting check - journal compliance

Step 1: Identify Manuscript Type and Core Message

Determine document type (research article, review, perspective, short communication). Extract the ONE finding or message readers must remember. Ask: "If readers remember only one thing, what should it be?" See resources/methodology.md for extraction techniques.

Step 2: Structural Pass

Map overall organization against standard IMRaD (Introduction, Methods, Results, Discussion) or review structure. Check logical sequencing - does each section flow into the next? Identify unclear transitions or missing context. See resources/methodology.md for structure evaluation.

Step 3: Introduction Review

Evaluate using the Introduction Arc: Broad context → Narrow focus → Knowledge gap → Hypothesis/Objective. Check that gap statement is explicit and compelling. Verify ending with clear hypothesis or objective. See resources/template.md for template.

Step 4: Results Review

For each figure/table/experiment: Question addressed? → Approach used? → Key finding (with statistics)? → Interpretation (what it means)? Flag data-dump writing that lacks interpretation. Ensure findings build toward core message. See resources/template.md for results structure.

Step 5: Discussion Review

Verify structure: Revisit hypothesis → Interpret findings in field context → Place in broader literature → Acknowledge limitations → Suggest future directions. Check for overclaiming (speculation presented as fact). Ensure clear separation of data interpretation vs. speculation. See resources/methodology.md for discussion framework.

Step 6: Scientific Clarity Check

Run the clarity checklist: Claims supported by data? Quantitative details present (statistics, n values)? Controls adequately described? Interpretations appropriately hedged? Mechanistic explanations where needed? See resources/template.md for full checklist.

Step 7: Language Polish

Ensure terminology consistency throughout. Remove or define jargon on first use. Prefer active voice when it aids clarity. Standardize abbreviations. Check for hedging language ("suggests" vs "proves"). See resources/methodology.md for specific guidance.

Step 8: Formatting Check

Verify compliance with target journal guidelines (word limits, reference format, figure requirements). Check section headings match journal requirements. Ensure abstract follows structured/unstructured requirement. Validate using resources/evaluators/rubric_scientific_manuscript.json. Minimum standard: Average score ≥ 3.5.

复制以下清单并跟踪进度：

Manuscript Review Progress:
- [ ] Step 1: Identify manuscript type and extract core message
- [ ] Step 2: Structural pass - map and evaluate overall organization
- [ ] Step 3: Introduction review - gap statement, focus, hypothesis
- [ ] Step 4: Results review - question, approach, finding, interpretation
- [ ] Step 5: Discussion review - synthesis, context, limitations
- [ ] Step 6: Scientific clarity check - claims, controls, hedging
- [ ] Step 7: Language polish - terminology, voice, jargon
- [ ] Step 8: Formatting check - journal compliance

步骤1：确定手稿类型与核心信息

明确文档类型（研究论文、综述、观点类文稿、短篇通讯）。提炼出读者必须记住的核心发现或信息。思考："如果读者只能记住一件事，那应该是什么？" 提取技巧可参考resources/methodology.md。

步骤2：结构审阅

对照标准IMRaD（引言、方法、结果、讨论）或综述类文稿结构，梳理整体框架。检查逻辑连贯性——各章节是否顺畅衔接？识别模糊的过渡或缺失的背景信息。结构评估方法可参考resources/methodology.md。

步骤3：引言审阅

采用"引言脉络"评估：宽泛背景→聚焦特定领域→研究缺口→假设/目标。检查研究缺口是否明确且有说服力，确认结尾是否包含清晰的假设或目标。模板可参考resources/template.md。

步骤4：结果审阅

针对每个图表/实验：是否明确解决的问题？使用的方法？关键发现（含统计数据）？解读（发现的意义）？标记缺乏解读的"数据堆砌"式写作。确保研究发现围绕核心信息展开。结果部分结构模板可参考resources/template.md。

步骤5：讨论审阅

验证结构是否符合：回顾假设→结合领域背景解读发现→关联已有文献→承认研究局限→提出未来方向。检查是否存在过度论断（将推测当作事实），确保数据解读与推测明确区分。讨论部分框架可参考resources/methodology.md。

步骤6：科学清晰度检查

执行清晰度清单：观点是否有数据支撑？是否包含量化细节（统计数据、样本量n）？对照实验是否描述充分？解读是否采用恰当的措辞？必要时是否提供机制性解释？完整清单可参考resources/template.md。

步骤7：语言润色

确保术语前后一致。首次使用行话时需定义或替换为易懂表达。在有助于提升清晰度时优先使用主动语态。统一缩写形式。检查措辞的严谨性（如"表明" vs "证明"）。具体指导可参考resources/methodology.md。

步骤8：格式检查

验证是否符合目标期刊的准则（字数限制、参考文献格式、图表要求）。检查章节标题是否匹配期刊要求。确认摘要符合结构化/非结构化要求。可使用resources/evaluators/rubric_scientific_manuscript.json进行评估。最低标准：平均得分≥3.5。

Section-by-Section Review

逐节审阅指南

Introduction Structure

引言结构

Goal: Convince readers the problem matters and your approach is sound

The Funnel Structure:

[Broad context - establish field importance, 1-2 sentences]
        ↓
[Narrow to specific area - what's been done]
        ↓
[Knowledge gap - what's missing, why it matters]
        ↓
[Your hypothesis/objective - what you will address]

Common problems:

Gap statement buried or implicit (make it explicit: "However, X remains unknown")
Too broad opening (readers don't need history of the universe)
No clear hypothesis at end (readers don't know what to expect)
Overlong literature review (move details to Discussion)

目标： 让读者相信研究问题的重要性及你的方法的合理性

漏斗式结构：

[宽泛背景 - 阐述领域重要性，1-2句话]
        ↓
[聚焦特定领域 - 已有研究成果]
        ↓
[研究缺口 - 尚未解决的问题及重要性]
        ↓
[你的假设/目标 - 拟解决的问题]

常见问题：

研究缺口表述模糊或隐含（需明确："然而，X仍未明确"）
开篇过于宽泛（读者无需了解整个领域的发展历史）
结尾无清晰假设（读者无法预知研究方向）
文献综述过长（可将细节移至讨论部分）

Results Structure

结果结构

Goal: Present data clearly with interpretation, not just numbers

Per-paragraph/figure structure:

[Question this experiment addresses]
[Approach/method used]
[Key finding - with quantification]
[Brief interpretation - what this means]

Common problems:

Data dump (listing results without interpretation)
Missing statistics (p-values, n values, confidence intervals)
Vague descriptions ("we found differences" vs "we found 3-fold increase")
Figures not referenced in logical order
Key findings buried in text (highlight important results)

目标： 清晰呈现数据并附带解读，而非仅罗列数字

每段落/图表的结构：

[本实验解决的问题]
[使用的方法/途径]
[关键发现 - 含量化数据]
[简要解读 - 发现的意义]

常见问题：

数据堆砌（仅罗列结果而无解读）
缺失统计数据（p值、样本量n、置信区间）
描述模糊（"我们发现差异" vs "我们发现3倍增长"）
图表引用顺序混乱
关键发现被埋没在文本中（需突出重要结果）

Discussion Structure

讨论结构

Goal: Interpret findings and place in broader context

Standard flow:

[Restate main finding and hypothesis status]
        ↓
[Interpret key results in field context]
        ↓
[Compare to prior literature - agreements/disagreements]
        ↓
[Mechanistic implications (if applicable)]
        ↓
[Limitations - honest acknowledgment]
        ↓
[Future directions - what comes next]
        ↓
[Concluding statement - big picture significance]

Common problems:

Overclaiming (data doesn't support conclusions)
Repeating Results section (discuss, don't recapitulate)
Missing limitations (reviewers will note them anyway)
Speculation unmarked (clearly label "we speculate that...")
No connection to field (discuss in isolation)

目标： 解读研究发现并置于更广泛的背景中

标准流程：

[重申主要发现及假设验证情况]
        ↓
[结合领域背景解读关键结果]
        ↓
[与已有文献对比 - 共识/分歧]
        ↓
[机制性启示（如适用）]
        ↓
[研究局限 - 坦诚承认]
        ↓
[未来方向 - 后续研究建议]
        ↓
[结论性陈述 - 宏观意义]

常见问题：

过度论断（数据无法支撑结论）
重复结果部分内容（需解读而非复述）
未提及研究局限（审稿人必然会注意到）
推测未标记（需明确标注"我们推测..."）
未结合领域背景（孤立讨论研究结果）

Language Guidelines

语言规范

Active vs. Passive Voice:

Use active for clarity: "We measured" not "Measurements were made"
Use passive when agent is obvious or unimportant: "Samples were incubated at 37°C"
Avoid dangling modifiers: Not "Having analyzed the data, the conclusion was..." but "Having analyzed the data, we concluded..."

Hedging Language:

Strong data: "demonstrates", "shows", "establishes"
Moderate confidence: "suggests", "indicates", "supports"
Speculation: "may", "might", "could potentially"
Match hedge strength to evidence strength

Jargon Management:

Define on first use: "polymerase chain reaction (PCR)"
Avoid unnecessary jargon when plain language works
Field-standard terms don't need definition (DNA, protein, cell)
Reader-appropriate: more definition for broad audience journals

Terminology Consistency:

Pick one term and stick with it (don't alternate between "subjects", "participants", "patients")
Create terminology table for complex manuscripts
Check abbreviations defined before use

主动语态vs被动语态：

为提升清晰度使用主动语态："我们测量了" 而非 "进行了测量"
当动作主体明显或不重要时使用被动语态："样本在37℃下孵育"
避免悬垂修饰语：不要写"分析数据后，得出结论..."，而应写"分析数据后，我们得出结论..."

严谨措辞：

数据充分时："demonstrates"、"shows"、"establishes"
中等置信度时："suggests"、"indicates"、"supports"
推测时："may"、"might"、"could potentially"
措辞严谨性需与证据强度匹配

行话管理：

首次使用时定义："聚合酶链式反应（PCR）"
能用通俗语言表达时避免使用行话
领域通用术语无需定义（如DNA、蛋白质、细胞）
根据读者调整：面向广泛受众的期刊需增加定义

术语一致性：

同一概念使用同一术语（不要交替使用"受试者"、"参与者"、"患者"）
复杂手稿可创建术语表
缩写需在首次使用时定义

Guardrails

注意事项

Critical requirements:

Preserve author voice: Edit for clarity, don't rewrite. Never invent claims or change meaning. Mark suggestions clearly when proposing new content.
Claims match data: Every conclusion must be supported by presented results. Flag overclaiming immediately. Speculation must be labeled.
Quantitative rigor: Statistics required for comparisons. N values for all experiments. Significance thresholds stated. Variability measures included.
Logical flow: Each section should flow naturally to the next. Transitions explicit. Conclusions follow from premises.
Appropriate hedging: Strong claims need strong evidence. Use hedging language proportional to certainty.
Consistent terminology: Same concept = same term throughout. Abbreviations defined before use.

Common pitfalls:

❌ Overclaiming: "This proves X" when data only suggests
❌ Missing context: Results without interpretation
❌ Buried lede: Important finding hidden in paragraph
❌ Inconsistent terms: Alternating between synonyms
❌ Dense paragraphs: Walls of text without breaks
❌ Vague descriptions: "Some increase" instead of "3-fold increase"

关键要求：

保留作者风格：编辑以提升清晰度为目标，不要重写全文。切勿编造观点或改变原意。提出新内容建议时需明确标记。
观点与数据匹配：每个结论必须有呈现的结果支撑。立即标记过度论断的内容。推测必须明确标注。
量化严谨性：对比分析需包含统计数据。所有实验需标注样本量n。明确显著性阈值。包含变异度指标。
逻辑连贯：各章节需自然衔接。过渡表述明确。结论需基于前提推导。
措辞恰当：有力的观点需要充分的证据支撑。使用与确定性匹配的严谨措辞。
术语一致：同一概念全程使用同一术语。缩写需在首次使用时定义。

常见误区：

❌ 过度论断：当数据仅能表明时，使用"这证明了X"
❌ 缺失背景：仅呈现结果而无解读
❌ 核心信息埋没：重要发现隐藏在段落中
❌ 术语不一致：交替使用同义词
❌ 段落冗长：大段无分段的文本
❌ 描述模糊："有所增加" 而非 "3倍增长"

scientific-manuscript-review

Original

Translation

Scientific Manuscript Review

科研手稿审阅

Table of Contents

目录

Purpose

目的

When to Use

适用场景

Core Principles

核心原则

Workflow

工作流程

Section-by-Section Review

逐节审阅指南

Introduction Structure

引言结构

Results Structure

结果结构

Discussion Structure

讨论结构

Language Guidelines

语言规范

Guardrails

注意事项

Quick Reference

快速参考