Back to Details

scientific-writing

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Scientific Writing

科学写作

Overview

概述

This is the core journal-writing skill in this repository. Use it to turn a stable scientific story into clear, well-structured manuscript prose while keeping citations, figures, and reporting standards aligned.
Scientific writing is a process for communicating research with precision and clarity. Write manuscripts using IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA). Apply this skill for research papers and journal submissions.
Critical Principle: Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript. Use a two-stage process: first create section outlines with key points from verified notes, literature, and results, then convert those outlines into complete paragraphs.
For revision-heavy journal manuscripts, do not jump from stale prose directly to polishing. First stabilize the section with a reverse outline and a claim-evidence map, then rewrite the paragraphs.
这是本仓库中的核心期刊写作技能。使用它可将成熟的科学研究内容转化为清晰、结构合理的手稿行文，同时确保引用、图表和报告标准保持一致。
科学写作是一种精准、清晰地传达研究内容的过程。撰写手稿时需采用IMRAD结构、指定格式的引用（APA/AMA/Vancouver）、图表以及报告规范（CONSORT/STROBE/PRISMA）。该技能适用于研究论文撰写与期刊投稿场景。
关键原则：始终使用完整段落的流畅行文。最终手稿中绝不能提交项目符号列表。 采用两阶段流程：首先利用已验证的笔记、文献和研究结果创建包含要点的章节大纲，然后将这些大纲转化为完整段落。
对于需要大量修改的期刊手稿，不要直接从陈旧的行文开始润色。首先通过反向大纲和主张-证据图稳定章节内容，再重写段落。

When to Use This Skill

何时使用此技能

This skill should be used when:
  • Writing or revising any section of a scientific manuscript (abstract, introduction, methods, results, discussion)
  • Structuring a research paper using IMRAD or other standard formats
  • Formatting citations and references in specific styles (APA, AMA, Vancouver, Chicago, IEEE)
  • Creating, formatting, or improving figures, tables, and data visualizations
  • Applying study-specific reporting guidelines (CONSORT for trials, STROBE for observational studies, PRISMA for reviews)
  • Drafting abstracts that meet journal requirements (structured or unstructured)
  • Preparing manuscripts for submission to specific journals
  • Improving writing clarity, conciseness, and precision
  • Ensuring proper use of field-specific terminology and nomenclature
  • Addressing reviewer comments and revising manuscripts
For title, abstract, cover-letter, or top-level logic decisions, read 
references/editor-first-impression.md
.
当你遇到以下场景时，应使用此技能：
  • 撰写或修改科学手稿的任意章节（摘要、引言、方法、结果、讨论）
  • 采用IMRAD或其他标准格式构建研究论文结构
  • 按照特定格式（APA、AMA、Vancouver、Chicago、IEEE）格式化引用和参考文献
  • 创建、格式化或优化图表、表格和数据可视化内容
  • 应用特定研究类型的报告规范（试验研究用CONSORT、观察性研究用STROBE、综述用PRISMA）
  • 撰写符合期刊要求的摘要（结构化或非结构化）
  • 为特定期刊准备投稿手稿
  • 提升写作的清晰度、简洁性和精准度
  • 确保正确使用领域特定术语和命名法
  • 处理审稿意见并修改手稿
如需标题、摘要、求职信或顶层逻辑决策相关指导，请阅读
references/editor-first-impression.md
。

Visual Enhancement with Scientific Figures

利用科学图表提升视觉效果

When a manuscript would benefit from a schematic, workflow diagram, or conceptual figure, use an installed figure-generation skill if one is available, such as 
inno-figure-gen
. This repository does not ship that optional skill in the default install set.
Before finalizing any document:
  1. Add at least one figure when it materially improves comprehension.
  2. Prefer 2-3 figures for longer papers (methods flowchart, results visualization, conceptual diagram).
How to generate figures:
  • Use an installed figure-generation skill such as 
    inno-figure-gen
    to generate publication-style diagrams.
  • Write prompts that specify academic style, white background, clean labels, colorblind-friendly colors, and high contrast.
  • Save outputs under a local 
    figures/
    directory in the current project.
Example command when 
inno-figure-gen
is installed:
bash
uv run ~/.codex/skills/inno-figure-gen/scripts/generate_image.py \
  --prompt "Publication-style scientific schematic of your method; white background; clean labels; colorblind-friendly palette; high contrast" \
  --filename "figures/output.png" \
  --resolution 2K
当手稿需要示意图、工作流程图或概念图时，若已安装图表生成技能（如
inno-figure-gen
），可使用该技能。本仓库默认安装包不包含此可选技能。
在最终确定任何文档前：
  1. 当图表能显著提升内容理解度时，至少添加一张图表。
  2. 对于篇幅较长的论文，建议添加2-3张图表（方法流程图、结果可视化图、概念示意图）。
图表生成方法：
  • 使用已安装的图表生成技能（如
    inno-figure-gen
    ）生成符合出版风格的图表。
  • 编写提示词时需指定学术风格、白色背景、清晰标签、色盲友好配色和高对比度。
  • 将输出文件保存至当前项目的本地
    figures/
    目录下。
安装
inno-figure-gen
后的示例命令：
bash
uv run ~/.codex/skills/inno-figure-gen/scripts/generate_image.py \
  --prompt "Publication-style scientific schematic of your method; white background; clean labels; colorblind-friendly palette; high contrast" \
  --filename "figures/output.png" \
  --resolution 2K

Claude Code (global install): replace ~/.codex/skills with ~/.claude/skills

Claude Code (全局安装): 将~/.codex/skills替换为~/.claude/skills

Claude Code (project-local install): replace ~/.codex/skills with .claude/skills

Claude Code (项目本地安装): 将~/.codex/skills替换为.claude/skills


Requires `GEMINI_API_KEY` or an explicit `--api-key`. Iterate on the prompt until the figure is publication-ready.

**When to add figures:**
- Study design and methodology flowcharts (CONSORT, PRISMA, STROBE)
- Conceptual framework diagrams
- Experimental workflow illustrations
- Data analysis pipeline diagrams
- Biological pathway or mechanism diagrams
- System architecture visualizations
- Any complex concept that benefits from visualization

For detailed guidance on creating figures, refer to the figure-generation skill you have installed.

---

需要`GEMINI_API_KEY`或显式指定`--api-key`。迭代优化提示词，直到图表达到出版标准。

**添加图表的场景：**
- 研究设计和方法流程图（CONSORT、PRISMA、STROBE）
- 概念框架图
- 实验工作流程示意图
- 数据分析管道图
- 生物通路或机制图
- 系统架构可视化图
- 任何需要可视化辅助理解的复杂概念

如需图表创建的详细指导，请参考你已安装的图表生成技能文档。

---

Core Capabilities

核心能力

1. Manuscript Structure and Organization

1. 手稿结构与组织

IMRAD Format: Guide papers through the standard Introduction, Methods, Results, And Discussion structure used across most scientific disciplines. This includes:
  • Introduction: Establish research context, identify gaps, state objectives
  • Methods: Detail study design, populations, procedures, and analysis approaches
  • Results: Present findings objectively without interpretation
  • Discussion: Interpret results, acknowledge limitations, propose future directions
For detailed guidance on IMRAD structure, refer to 
references/imrad_structure.md
.
Alternative Structures: Support discipline-specific formats including:
  • Review articles (narrative, systematic, scoping)
  • Case reports and case series
  • Meta-analyses and pooled analyses
  • Theoretical/modeling papers
  • Methods papers and protocols
IMRAD格式：指导论文采用大多数科学学科通用的标准引言（Introduction）、方法（Methods）、结果（Results）和讨论（Discussion）结构。包括：
  • 引言：确立研究背景，明确研究缺口，阐述研究目标
  • 方法：详细说明研究设计、研究对象、流程和分析方法
  • 结果：客观呈现研究发现，不添加解读
  • 讨论：解读结果，承认研究局限性，提出未来研究方向
如需IMRAD结构的详细指导，请参考
references/imrad_structure.md
。
替代结构：支持特定学科的格式，包括：
  • 综述文章（叙述性综述、系统性综述、范围综述）
  • 病例报告和病例系列
  • 元分析和合并分析
  • 理论/建模论文
  • 方法学论文和研究方案

2. Section-Specific Writing Guidance

2. 分章节写作指导

Editor-First Front Door: Make the title, abstract, introduction, Results, discussion, and cover letter answer the same four questions in the same order:
  • why did the study need to be done
  • what did you do
  • what did you find
  • how does the study advance the field
If these sections answer different versions of the story, the manuscript will feel fragmented even when the prose is locally strong.
Abstract Composition: Craft concise, standalone summaries (100-250 words) that capture the paper's purpose, methods, results, and conclusions. Support both structured abstracts (with labeled sections) and unstructured single-paragraph formats. Make the abstract state the problem, the aim/method, the key result, and the implication. Do not spend most of the space on generic background or report only that results were significant.
Title and Cover Letter: Make the title a concise summary of the main contribution, ideally about 20 words or fewer. Prefer concrete keywords, avoid question-form titles, avoid unnecessary abbreviations, and avoid making the method the title unless the method itself is the main contribution. Make the cover letter about one page, state significance, journal fit, readership fit, and one or two key findings, and do not turn it into a second abstract or a full result list.
Top-Level Logic: Keep one visible chain across the manuscript:
  • topic
  • published work
  • unresolved problem
  • objective
  • methodology
  • results and figures
  • summary of findings
  • interpretation
  • implication for the field
Introduction Development: Build compelling introductions that:
  • Establish the research problem's importance
  • Review relevant literature systematically
  • Identify knowledge gaps or controversies
  • State clear research questions or hypotheses
  • Explain the study's novelty and significance
Methods Documentation: Ensure reproducibility through:
  • Detailed participant/sample descriptions
  • Clear procedural documentation
  • Statistical methods with justification
  • Equipment and materials specifications
  • Ethical approval and consent statements
Results Presentation: Present findings with:
  • Logical flow from primary to secondary outcomes
  • Integration with figures and tables
  • Statistical significance with effect sizes
  • Objective reporting without interpretation
Discussion Construction: Synthesize findings by:
  • Relating results to research questions
  • Comparing with existing literature
  • Acknowledging limitations honestly
  • Proposing mechanistic explanations
  • Suggesting practical implications and future research
编辑视角的核心逻辑：标题、摘要、引言、结果、讨论和求职信需按相同顺序回答以下四个问题：
  • 为什么需要开展这项研究
  • 你做了什么
  • 你发现了什么
  • 这项研究如何推动领域发展
如果这些章节讲述的内容逻辑不一致，即使局部行文流畅，手稿整体也会显得零散。
摘要撰写：撰写简洁、独立的摘要（100-250词），涵盖论文目的、方法、结果和结论。支持结构化摘要（带标签章节）和非结构化单段落格式。摘要需说明研究问题、目标/方法、关键结果和意义。不要将大部分篇幅用于通用背景描述，也不要仅报告结果具有显著性。
标题与求职信：标题需简洁概括核心贡献，理想长度约为20词以内。优先使用具体关键词，避免疑问句标题，避免不必要的缩写，除非方法本身是核心贡献，否则不要将方法作为标题。求职信篇幅约为一页，说明研究意义、与期刊的契合度、目标读者群体以及一两个关键发现，不要将其写成第二个摘要或完整结果列表。
顶层逻辑：保持手稿逻辑链清晰可见：
  • 研究主题
  • 已发表研究
  • 未解决的问题
  • 研究目标
  • 方法论
  • 结果与图表
  • 发现总结
  • 解读
  • 对领域的意义
引言撰写：构建引人入胜的引言，需：
  • 确立研究问题的重要性
  • 系统综述相关文献
  • 明确知识缺口或争议点
  • 提出清晰的研究问题或假设
  • 说明研究的创新性和意义
方法记录：通过以下方式确保研究可重复性：
  • 详细描述研究对象/样本
  • 清晰记录研究流程
  • 说明统计方法并提供依据
  • 明确设备和材料规格
  • 说明伦理审批和知情同意情况
结果呈现：呈现研究发现时需：
  • 按从主要到次要结果的逻辑顺序展示
  • 与图表内容整合
  • 提供统计显著性和效应量
  • 客观报告，不添加解读
讨论构建：通过以下方式整合研究发现：
  • 将结果与研究问题关联
  • 与现有文献进行比较
  • 坦诚承认研究局限性
  • 提出机制性解释
  • 建议实际应用方向和未来研究方向

3. Citation and Reference Management

3. 引用与参考文献管理

Apply citation styles correctly across disciplines. For comprehensive style guides, refer to 
references/citation_styles.md
.
Major Citation Styles:
  • AMA (American Medical Association): Numbered superscript citations, common in medicine
  • Vancouver: Numbered citations in square brackets, biomedical standard
  • APA (American Psychological Association): Author-date in-text citations, common in social sciences
  • Chicago: Notes-bibliography or author-date, humanities and sciences
  • IEEE: Numbered square brackets, engineering and computer science
Best Practices:
  • Cite primary sources when possible
  • Include recent literature (last 5-10 years for active fields)
  • Balance citation distribution across introduction and discussion
  • Verify all citations against original sources
  • Use reference management software (Zotero, Mendeley, EndNote)
正确应用各学科的引用格式。如需完整格式指南，请参考
references/citation_styles.md
。
主要引用格式：
  • AMA（美国医学协会格式）：上标数字引用，常用于医学领域
  • Vancouver格式：方括号内数字引用，生物医学领域标准格式
  • APA（美国心理协会格式）：文内作者-年份引用，常用于社会科学领域
  • Chicago格式：注释-参考文献或作者-年份格式，适用于人文和科学领域
  • IEEE格式：方括号内数字引用，常用于工程和计算机科学领域
最佳实践：
  • 尽可能引用原始文献
  • 包含近期文献（活跃领域引用过去5-10年的文献）
  • 在引言和讨论部分均衡分布引用
  • 验证所有引用与原始文献一致
  • 使用参考文献管理软件（Zotero、Mendeley、EndNote）

4. Figures and Tables

4. 图表

Create effective data visualizations that enhance comprehension. For detailed best practices, refer to 
references/figures_tables.md
.
When to Use Tables vs. Figures:
  • Tables: Precise numerical data, complex datasets, multiple variables requiring exact values
  • Figures: Trends, patterns, relationships, comparisons best understood visually
Design Principles:
  • Make each table/figure self-explanatory with complete captions
  • Use consistent formatting and terminology across all display items
  • Label all axes, columns, and rows with units
  • Include sample sizes (n) and statistical annotations
  • Follow the "one table/figure per 1000 words" guideline
  • Avoid duplicating information between text, tables, and figures
Common Figure Types:
  • Bar graphs: Comparing discrete categories
  • Line graphs: Showing trends over time
  • Scatterplots: Displaying correlations
  • Box plots: Showing distributions and outliers
  • Heatmaps: Visualizing matrices and patterns
创建能提升内容理解度的有效数据可视化内容。如需详细最佳实践，请参考
references/figures_tables.md
。
表格与图表的适用场景：
  • 表格：精确的数值数据、复杂数据集、需要精确值的多变量数据
  • 图表：趋势、模式、关系、适合可视化比较的内容
设计原则：
  • 每个表格/图表需配有完整说明，确保可独立理解
  • 所有展示内容使用一致的格式和术语
  • 为所有坐标轴、列和行标注单位
  • 包含样本量（n）和统计注释
  • 遵循“每1000词配一个表格/图表”的原则
  • 避免在文本、表格和图表之间重复信息
常见图表类型：
  • 柱状图：比较离散类别
  • 折线图：展示随时间变化的趋势
  • 散点图：展示相关性
  • 箱线图：展示分布和异常值
  • 热图：可视化矩阵和模式

5. Reporting Guidelines by Study Type

5. 按研究类型分类的报告规范

Ensure completeness and transparency by following established reporting standards. For comprehensive guideline details, refer to 
references/reporting_guidelines.md
.
Key Guidelines:
  • CONSORT: Randomized controlled trials
  • STROBE: Observational studies (cohort, case-control, cross-sectional)
  • PRISMA: Systematic reviews and meta-analyses
  • STARD: Diagnostic accuracy studies
  • TRIPOD: Prediction model studies
  • ARRIVE: Animal research
  • CARE: Case reports
  • SQUIRE: Quality improvement studies
  • SPIRIT: Study protocols for clinical trials
  • CHEERS: Economic evaluations
Each guideline provides checklists ensuring all critical methodological elements are reported.
遵循既定报告标准，确保内容完整且透明。如需完整规范细节，请参考
references/reporting_guidelines.md
。
核心规范：
  • CONSORT：随机对照试验
  • STROBE：观察性研究（队列研究、病例对照研究、横断面研究）
  • PRISMA：系统性综述和元分析
  • STARD：诊断准确性研究
  • TRIPOD：预测模型研究
  • ARRIVE：动物研究
  • CARE：病例报告
  • SQUIRE：质量改进研究
  • SPIRIT：临床试验研究方案
  • CHEERS：经济评估研究
每个规范都提供检查清单，确保报告所有关键方法要素。

6. Writing Principles and Style

6. 写作原则与风格

Apply fundamental scientific writing principles. For detailed guidance, refer to 
references/writing_principles.md
.
Clarity:
  • Use precise, unambiguous language
  • Define technical terms and abbreviations at first use
  • Maintain logical flow within and between paragraphs
  • Use active voice when appropriate for clarity
Conciseness:
  • Eliminate redundant words and phrases
  • Favor shorter sentences (15-20 words average)
  • Remove unnecessary qualifiers
  • Respect word limits strictly
Accuracy:
  • Report exact values with appropriate precision
  • Use consistent terminology throughout
  • Distinguish between observations and interpretations
  • Acknowledge uncertainty appropriately
Objectivity:
  • Present results without bias
  • Avoid overstating findings or implications
  • Acknowledge conflicting evidence
  • Maintain professional, neutral tone
应用基础科学写作原则。如需详细指导，请参考
references/writing_principles.md
。
清晰度：
  • 使用精确、无歧义的语言
  • 在首次使用时定义技术术语和缩写
  • 保持段落内部和段落之间的逻辑连贯
  • 适当使用主动语态提升清晰度
简洁性：
  • 删除冗余词汇和短语
  • 偏好短句（平均15-20词）
  • 移除不必要的限定词
  • 严格遵守字数限制
准确性：
  • 报告精确值并采用适当精度
  • 全文使用一致的术语
  • 区分观察结果和解读内容
  • 适当承认不确定性
客观性：
  • 无偏呈现结果
  • 避免夸大研究发现或意义
  • 承认相互矛盾的证据
  • 保持专业、中立的语气

7. Writing Process: From Outline to Full Paragraphs

7. 写作流程：从大纲到完整段落

CRITICAL: Always write in full paragraphs, never submit bullet points in scientific papers.
Scientific papers must be written in complete, flowing prose. Use this two-stage approach for effective writing:
Stage 1: Create Section Outlines with Key Points
When starting a new section:
  1. Gather the relevant literature and data from verified local notes, trusted web sources, or an installed literature-search skill
  2. Create a structured outline with bullet points marking:
    • Main arguments or findings to present
    • Key studies to cite
    • Data points and statistics to include
    • Logical flow and organization
  3. These bullet points serve as scaffolding—they are NOT the final manuscript
Example outline (Introduction section):
- Background: AI in drug discovery gaining traction
  * Cite recent reviews (Smith 2023, Jones 2024)
  * Traditional methods are slow and expensive
- Gap: Limited application to rare diseases
  * Only 2 prior studies (Lee 2022, Chen 2023)
  * Small datasets remain a challenge
- Our approach: Transfer learning from common diseases
  * Novel architecture combining X and Y
- Study objectives: Validate on 3 rare disease datasets
Stage 2: Convert Key Points to Full Paragraphs
Once the outline is complete, expand each bullet point into proper prose:
  1. Transform bullet points into complete sentences with subjects, verbs, and objects
  2. Add transitions between sentences and ideas (however, moreover, in contrast, subsequently)
  3. Integrate citations naturally within sentences, not as lists
  4. Expand with context and explanation that bullet points omit
  5. Ensure logical flow from one sentence to the next within each paragraph
  6. Vary sentence structure to maintain reader engagement
Example conversion to prose:
Artificial intelligence approaches have gained significant traction in drug discovery 
pipelines over the past decade (Smith, 2023; Jones, 2024). While these computational 
methods show promise for accelerating the identification of therapeutic candidates, 
traditional experimental approaches remain slow and resource-intensive, often requiring 
years of laboratory work and substantial financial investment. However, the application 
of AI to rare diseases has been limited, with only two prior studies demonstrating 
proof-of-concept results (Lee, 2022; Chen, 2023). The primary obstacle has been the 
scarcity of training data for conditions affecting small patient populations. 

To address this challenge, we developed a transfer learning approach that leverages 
knowledge from well-characterized common diseases to predict therapeutic targets for 
rare conditions. Our novel neural architecture combines convolutional layers for 
molecular feature extraction with attention mechanisms for protein-ligand interaction 
modeling. The objective of this study was to validate our approach across three 
independent rare disease datasets, assessing both predictive accuracy and biological 
interpretability of the results.
Key Differences Between Outlines and Final Text:
Outline (Planning Stage)Final Manuscript
Bullet points and fragmentsComplete sentences and paragraphs
Telegraphic notesFull explanations with context
List of citationsCitations integrated into prose
Abbreviated ideasDeveloped arguments with transitions
For your eyes onlyFor publication and peer review
Common Mistakes to Avoid:
  • ❌ Never leave bullet points in the final manuscript
  • ❌ Never submit lists where paragraphs should be
  • ❌ Don't use numbered or bulleted lists in Results or Discussion sections (except for specific cases like study hypotheses or inclusion criteria)
  • ❌ Don't write sentence fragments or incomplete thoughts
  • ✅ Do use occasional lists only in Methods (e.g., inclusion/exclusion criteria, materials lists)
  • ✅ Do ensure every section flows as connected prose
  • ✅ Do read paragraphs aloud to check for natural flow
When Lists ARE Acceptable (Limited Cases):
Lists may appear in scientific papers only in specific contexts:
  • Methods: Inclusion/exclusion criteria, materials and reagents, participant characteristics
  • Supplementary Materials: Extended protocols, equipment lists, detailed parameters
  • Never in: Abstract, Introduction, Results, Discussion, Conclusions
Integration with Literature Search:
Verified literature gathering is essential for Stage 1 (creating outlines):
  1. Search for relevant papers using trusted sources or an installed literature-search skill
  2. Extract key findings, methods, and data
  3. Organize findings as bullet points in your outline
  4. Then convert the outline to full paragraphs in Stage 2
This two-stage process ensures you:
  • Gather and organize information systematically
  • Create logical structure before writing
  • Produce polished, publication-ready prose
  • Maintain focus on the narrative flow
重要提示：始终使用完整段落写作，科学论文中绝不能提交项目符号列表。
科学论文必须使用完整、流畅的行文。采用以下两阶段方法进行有效写作：
阶段1：创建包含要点的章节大纲
开始新章节时：
  1. 从已验证的本地笔记、可信网络来源或已安装的文献搜索技能中收集相关文献和数据
  2. 创建结构化大纲，使用项目符号标记：
    • 要呈现的主要论点或发现
    • 要引用的关键研究
    • 要包含的数据点和统计信息
    • 逻辑流程和组织结构
  3. 这些项目符号仅作为框架——并非最终手稿内容
示例大纲（引言章节）：
- Background: AI in drug discovery gaining traction
  * Cite recent reviews (Smith 2023, Jones 2024)
  * Traditional methods are slow and expensive
- Gap: Limited application to rare diseases
  * Only 2 prior studies (Lee 2022, Chen 2023)
  * Small datasets remain a challenge
- Our approach: Transfer learning from common diseases
  * Novel architecture combining X and Y
- Study objectives: Validate on 3 rare disease datasets
阶段2：将要点转化为完整段落
大纲完成后，将每个项目符号扩展为规范行文：
  1. 将项目符号转化为完整句子，包含主语、谓语和宾语
  2. 添加过渡词连接句子和观点（however, moreover, in contrast, subsequently等）
  3. 自然整合引用到句子中，而非以列表形式呈现
  4. 补充上下文和解释，这些内容是项目符号中省略的
  5. 确保段落内句子间逻辑连贯
  6. 变换句子结构以保持读者兴趣
示例转化为行文：
Artificial intelligence approaches have gained significant traction in drug discovery 
pipelines over the past decade (Smith, 2023; Jones, 2024). While these computational 
methods show promise for accelerating the identification of therapeutic candidates, 
traditional experimental approaches remain slow and resource-intensive, often requiring 
years of laboratory work and substantial financial investment. However, the application 
of AI to rare diseases has been limited, with only two prior studies demonstrating 
proof-of-concept results (Lee, 2022; Chen, 2023). The primary obstacle has been the 
scarcity of training data for conditions affecting small patient populations. 

To address this challenge, we developed a transfer learning approach that leverages 
knowledge from well-characterized common diseases to predict therapeutic targets for 
rare conditions. Our novel neural architecture combines convolutional layers for 
molecular feature extraction with attention mechanisms for protein-ligand interaction 
modeling. The objective of this study was to validate our approach across three 
independent rare disease datasets, assessing both predictive accuracy and biological 
interpretability of the results.
大纲与最终文本的关键差异：
大纲（规划阶段）最终手稿
项目符号和片段内容完整句子和段落
简洁笔记带上下文的完整解释
引用列表引用自然整合到行文
简化观点带过渡词的完整论点
仅供个人参考用于出版和同行评审
需避免的常见错误：
  • ❌ 绝不要在最终手稿中保留项目符号
  • ❌ 绝不要在应使用段落的地方提交列表
  • ❌ 不要在结果或讨论部分使用编号或项目符号列表（研究假设或纳入标准等特定情况除外）
  • ❌ 不要写句子片段或不完整的想法
  • ✅ 可以仅在方法部分偶尔使用列表（如纳入/排除标准、材料列表）
  • ✅ 务必确保每个章节以连贯行文呈现
  • ✅ 务必大声朗读段落，检查自然流畅度
可使用列表的场景（有限情况）：
科学论文中仅在特定场景可使用列表：
  • 方法部分：纳入/排除标准、材料和试剂、研究对象特征
  • 补充材料：扩展方案、设备列表、详细参数
  • 禁止使用场景：摘要、引言、结果、讨论、结论
与文献搜索的整合：
已验证的文献收集对阶段1（创建大纲）至关重要：
  1. 使用可信来源或已安装的文献搜索技能搜索相关论文
  2. 提取关键发现、方法和数据
  3. 将发现整理为大纲中的项目符号
  4. 然后在阶段2将大纲转化为完整段落
这种两阶段流程可确保：
  • 系统收集和组织信息
  • 在写作前创建逻辑结构
  • 生成 polished、符合出版标准的行文
  • 保持叙事流程的聚焦

7A. Reverse Outline And Claim-Evidence Pass For Revisions

7A. 修订时的反向大纲和主张-证据检查

When revising an existing manuscript section rather than drafting from scratch:
  1. Reverse-outline the current text:
    • section thesis
    • one-line message for each paragraph
    • the evidence, citation, or reasoning each paragraph carries
  2. For all major claims in the Abstract, Introduction, Results topic sentences, and Discussion, write: 
    • Claim: ... | Evidence: ... | Status: supported / partial / missing
  3. If a claim is marked 
    partial
    or 
    missing
    , do one of three things only:
    • weaken it
    • add the missing evidence
    • move it into motivation, interpretation, or future work
  4. Only after this pass, rewrite into full journal prose.
Use this especially when:
  • the section has been revised many times
  • the front half may now be stronger than the Results
  • paragraph flow feels smooth but the logic still feels unstable
当修改现有手稿章节而非从头起草时：
  1. 对当前文本进行反向大纲梳理：
    • 章节主旨
    • 每个段落的核心信息（一句话概括）
    • 每个段落承载的证据、引用或推理
  2. 针对摘要、引言、结果主题句和讨论中的所有主要主张，记录： 
    • 主张: ... | 证据: ... | 状态: 已支持 / 部分支持 / 缺失
  3. 如果主张标记为
    部分支持
    或
    缺失
    ，仅可采取以下三种措施之一：
    • 弱化主张
    • 添加缺失的证据
    • 将其移至动机、解读或未来工作部分
  4. 完成此检查后，再重写为符合期刊要求的完整行文。
以下场景尤其适合使用此方法：
  • 章节已多次修改
  • 前半部分内容可能比结果部分更完善
  • 段落流畅度尚可，但逻辑仍不稳定

7B. Skeptical Self-Review Before Finalizing

7B. 最终定稿前的批判性自我审查

Before treating a section as finished, ask:
  • Is the contribution actually clear?
  • Is every major claim readable and self-contained?
  • Does the empirical evidence directly support the claim I am making?
  • Is an important baseline, ablation, or caveat missing?
  • Would a skeptical reviewer call the method, framework, or resource insufficiently justified?
If the answer is not clearly defensible from the manuscript itself, revise the section before polishing style.
在将章节视为定稿前，自问：
  • 研究贡献是否清晰明确？
  • 每个主要主张是否易于理解且独立完整？
  • 实证证据是否直接支持我提出的主张？
  • 是否遗漏了重要的基线、消融实验或注意事项？
  • 持批判态度的审稿人是否会认为方法、框架或资源的合理性不足？
如果手稿本身无法明确证明答案是肯定的，请在润色风格前先修订章节。

8. Journal-Specific Formatting

8. 期刊特定格式要求

Adapt manuscripts to journal requirements:
  • Follow author guidelines for structure, length, and format
  • Apply journal-specific citation styles
  • Meet figure/table specifications (resolution, file formats, dimensions)
  • Include required statements (funding, conflicts of interest, data availability, ethical approval)
  • Adhere to word limits for each section
  • Format according to template requirements when provided
根据期刊要求调整手稿：
  • 遵循作者指南中的结构、篇幅和格式要求
  • 应用期刊特定的引用格式
  • 满足图表规格要求（分辨率、文件格式、尺寸）
  • 包含所需声明（资助信息、利益冲突、数据可用性、伦理审批）
  • 遵守各章节的字数限制
  • 提供模板时，按照模板要求格式化

9. Field-Specific Language and Terminology

9. 领域特定语言与术语

Adapt language, terminology, and conventions to match the specific scientific discipline. Each field has established vocabulary, preferred phrasings, and domain-specific conventions that signal expertise and ensure clarity for the target audience.
Identify Field-Specific Linguistic Conventions:
  • Review terminology used in recent high-impact papers in the target journal
  • Note field-specific abbreviations, units, and notation systems
  • Identify preferred terms (e.g., "participants" vs. "subjects," "compound" vs. "drug," "specimens" vs. "samples")
  • Observe how methods, organisms, or techniques are typically described
Biomedical and Clinical Sciences:
  • Use precise anatomical and clinical terminology (e.g., "myocardial infarction" not "heart attack" in formal writing)
  • Follow standardized disease nomenclature (ICD, DSM, SNOMED-CT)
  • Specify drug names using generic names first, brand names in parentheses if needed
  • Use "patients" for clinical studies, "participants" for community-based research
  • Follow Human Genome Variation Society (HGVS) nomenclature for genetic variants
  • Report lab values with standard units (SI units in most international journals)
Molecular Biology and Genetics:
  • Use italics for gene symbols (e.g., TP53), regular font for proteins (e.g., p53)
  • Follow species-specific gene nomenclature (uppercase for human: BRCA1; sentence case for mouse: Brca1)
  • Specify organism names in full at first mention, then use accepted abbreviations (e.g., Escherichia coli, then E. coli)
  • Use standard genetic notation (e.g., +/+, +/-, -/- for genotypes)
  • Employ established terminology for molecular techniques (e.g., "quantitative PCR" or "qPCR," not "real-time PCR")
Chemistry and Pharmaceutical Sciences:
  • Follow IUPAC nomenclature for chemical compounds
  • Use systematic names for novel compounds, common names for well-known substances
  • Specify chemical structures using standard notation (e.g., SMILES, InChI for databases)
  • Report concentrations with appropriate units (mM, μM, nM, or % w/v, v/v)
  • Describe synthesis routes using accepted reaction nomenclature
  • Use terms like "bioavailability," "pharmacokinetics," "IC50" consistently with field definitions
Ecology and Environmental Sciences:
  • Use binomial nomenclature for species (italicized: Homo sapiens)
  • Specify taxonomic authorities at first species mention when relevant
  • Employ standardized habitat and ecosystem classifications
  • Use consistent terminology for ecological metrics (e.g., "species richness," "Shannon diversity index")
  • Describe sampling methods with field-standard terms (e.g., "transect," "quadrat," "mark-recapture")
Physics and Engineering:
  • Follow SI units consistently unless field conventions dictate otherwise
  • Use standard notation for physical quantities (scalars vs. vectors, tensors)
  • Employ established terminology for phenomena (e.g., "quantum entanglement," "laminar flow")
  • Specify equipment with model numbers and manufacturers when relevant
  • Use mathematical notation consistent with field standards (e.g., ℏ for reduced Planck constant)
Neuroscience:
  • Use standardized brain region nomenclature (e.g., refer to atlases like Allen Brain Atlas)
  • Specify coordinates for brain regions using established stereotaxic systems
  • Follow conventions for neural terminology (e.g., "action potential" not "spike" in formal writing)
  • Use "neural activity," "neuronal firing," "brain activation" appropriately based on measurement method
  • Describe recording techniques with proper specificity (e.g., "whole-cell patch clamp," "extracellular recording")
Social and Behavioral Sciences:
  • Use person-first language when appropriate (e.g., "people with schizophrenia" not "schizophrenics")
  • Employ standardized psychological constructs and validated assessment names
  • Follow APA guidelines for reducing bias in language
  • Specify theoretical frameworks using established terminology
  • Use "participants" rather than "subjects" for human research
General Principles:
Match Audience Expertise:
  • For specialized journals: Use field-specific terminology freely, define only highly specialized or novel terms
  • For broad-impact journals (e.g., Nature, Science): Define more technical terms, provide context for specialized concepts
  • For interdisciplinary audiences: Balance precision with accessibility, define terms at first use
Define Technical Terms Strategically:
  • Define abbreviations at first use: "messenger RNA (mRNA)"
  • Provide brief explanations for specialized techniques when writing for broader audiences
  • Avoid over-defining terms well-known to the target audience (signals unfamiliarity with field)
  • Create a glossary if numerous specialized terms are unavoidable
Maintain Consistency:
  • Use the same term for the same concept throughout (don't alternate between "medication," "drug," and "pharmaceutical")
  • Follow a consistent system for abbreviations (decide on "PCR" or "polymerase chain reaction" after first definition)
  • Apply the same nomenclature system throughout (especially for genes, species, chemicals)
Avoid Field Mixing Errors:
  • Don't use clinical terminology for basic science (e.g., don't call mice "patients")
  • Avoid colloquialisms or overly general terms in place of precise field terminology
  • Don't import terminology from adjacent fields without ensuring proper usage
Verify Terminology Usage:
  • Consult field-specific style guides and nomenclature resources
  • Check how terms are used in recent papers from the target journal
  • Use domain-specific databases and ontologies (e.g., Gene Ontology, MeSH terms)
  • When uncertain, cite a key reference that establishes terminology
调整语言、术语和惯例以匹配特定科学学科。每个领域都有既定词汇、偏好表达方式和特定领域惯例，这些可体现专业性并确保目标读者清晰理解。
识别领域特定语言惯例：
  • 查阅目标期刊近期高影响力论文中使用的术语
  • 记录领域特定缩写、单位和符号系统
  • 确定偏好术语（如“研究对象”vs“受试者”、“化合物”vs“药物”、“标本”vs“样本”）
  • 观察方法、生物体或技术的典型描述方式
生物医学与临床医学：
  • 使用精确的解剖学和临床医学术语（如正式写作中使用“心肌梗死”而非“心脏病发作”）
  • 遵循标准化疾病命名法（ICD、DSM、SNOMED-CT）
  • 药物名称先使用通用名，必要时在括号内添加品牌名
  • 临床研究使用“患者”，社区研究使用“研究对象”
  • 遵循人类基因组变异协会（HGVS）的基因变异命名法
  • 使用标准单位报告实验室数值（大多数国际期刊使用SI单位）
分子生物学与遗传学：
  • 基因符号使用斜体（如TP53），蛋白质使用常规字体（如p53）
  • 遵循物种特定的基因命名法（人类基因大写：BRCA1；小鼠基因首字母大写：Brca1）
  • 首次提及生物体时使用全名，之后使用公认缩写（如Escherichia coli，之后使用E. coli）
  • 使用标准遗传符号（如+/+、+/-、-/-表示基因型）
  • 使用分子技术的既定术语（如“定量PCR”或“qPCR”，而非“实时PCR”）
化学与制药科学：
  • 遵循IUPAC化合物命名法
  • 新型化合物使用系统名，知名物质使用通用名
  • 使用标准符号指定化学结构（如SMILES、InChI用于数据库）
  • 使用适当单位报告浓度（mM、μM、nM或% w/v、v/v）
  • 使用公认反应命名法描述合成路线
  • 与领域定义一致地使用“生物利用度”、“药代动力学”、“IC50”等术语
生态学与环境科学：
  • 物种使用双名法（斜体：Homo sapiens）
  • 相关情况下，首次提及物种时注明分类学权威
  • 使用标准化栖息地和生态系统分类
  • 生态指标使用一致术语（如“物种丰富度”、“香农多样性指数”）
  • 使用领域标准术语描述采样方法（如“样带”、“样方”、“标记重捕法”）
物理学与工程学：
  • 除非领域惯例另有规定，否则一致使用SI单位
  • 物理量使用标准符号（标量vs矢量、张量）
  • 现象使用既定术语（如“量子纠缠”、“层流”）
  • 相关情况下，指定设备型号和制造商
  • 使用符合领域标准的数学符号（如ℏ表示约化普朗克常数）
神经科学：
  • 使用标准化脑区命名法（如参考Allen Brain Atlas等图谱）
  • 使用既定立体定位系统指定脑区坐标
  • 遵循神经术语惯例（如正式写作中使用“动作电位”而非“尖峰信号”）
  • 根据测量方法适当使用“神经活动”、“神经元放电”、“脑激活”等术语
  • 详细描述记录技术（如“全细胞膜片钳”、“细胞外记录”）
社会与行为科学：
  • 适当使用以人为本的语言（如“精神分裂症患者”而非“精神分裂症病人”）
  • 使用标准化心理构念和经过验证的评估工具名称
  • 遵循APA减少语言偏见的指南
  • 使用既定术语指定理论框架
  • 人类研究使用“研究对象”而非“受试者”
通用原则：
匹配读者专业水平：
  • 专业期刊：自由使用领域特定术语，仅定义高度专业或新颖术语
  • 高影响力综合期刊（如Nature、Science）：定义更多技术术语，为专业概念提供背景
  • 跨学科读者：平衡精准性与易读性，首次使用时定义术语
战略性定义技术术语：
  • 首次使用时定义缩写：“信使RNA（mRNA）”
  • 面向更广泛读者写作时，为专业技术提供简要解释
  • 避免过度定义目标读者熟知的术语（会显得对领域不熟悉）
  • 若有大量专业术语不可避免，创建术语表
保持一致性：
  • 同一概念使用同一术语（不要交替使用“药物”、“药剂”和“制药”）
  • 缩写使用一致体系（首次定义后，决定使用“PCR”还是“聚合酶链式反应”）
  • 全文使用同一命名体系（尤其是基因、物种、化合物）
避免领域混淆错误：
  • 不要将临床术语用于基础科学（如不要将小鼠称为“患者”）
  • 避免用口语化或过于笼统的术语替代精准的领域术语
  • 不要未经确认正确用法就引入相邻领域的术语
验证术语用法：
  • 查阅领域特定风格指南和命名资源
  • 查看目标期刊近期论文中术语的使用方式
  • 使用领域特定数据库和本体（如基因本体、MeSH术语）
  • 不确定时，引用确立术语用法的关键参考文献

10. Common Pitfalls to Avoid

10. 需避免的常见陷阱

Top Rejection Reasons:
  1. Inappropriate, incomplete, or insufficiently described statistics
  2. Over-interpretation of results or unsupported conclusions
  3. Poorly described methods affecting reproducibility
  4. Small, biased, or inappropriate samples
  5. Poor writing quality or difficult-to-follow text
  6. Inadequate literature review or context
  7. Figures and tables that are unclear or poorly designed
  8. Failure to follow reporting guidelines
Writing Quality Issues:
  • Mixing tenses inappropriately (use past tense for methods/results, present for established facts)
  • Excessive jargon or undefined acronyms
  • Paragraph breaks that disrupt logical flow
  • Missing transitions between sections
  • Inconsistent notation or terminology
主要拒稿原因：
  1. 统计方法不当、不完整或描述不足
  2. 过度解读结果或结论缺乏依据
  3. 方法描述不佳影响可重复性
  4. 样本量小、有偏或不合适
  5. 写作质量差或文本难以理解
  6. 文献综述不充分或背景描述不足
  7. 图表不清晰或设计不佳
  8. 未遵循报告规范
写作质量问题：
  • 时态使用不当（方法/结果使用过去时，既定事实使用现在时）
  • 过度使用行话或未定义缩写
  • 段落划分破坏逻辑连贯
  • 章节间缺少过渡
  • 符号或术语不一致

Workflow for Manuscript Development

手稿开发工作流程

Stage 1: Planning
  1. Identify target journal and review author guidelines
  2. Determine applicable reporting guideline (CONSORT, STROBE, etc.)
  3. Outline manuscript structure (usually IMRAD)
  4. Plan figures and tables as the backbone of the paper
Stage 2: Drafting (Use two-stage writing process for each section)
  1. Start with figures and tables (the core data story)
  2. For each section below, follow the two-stage process:
    • First: Create outline with bullet points from verified literature, notes, and results
    • Second: Convert bullet points to full paragraphs with flowing prose
  3. Write Methods (often easiest to draft first)
  4. Draft Results (describing figures/tables objectively)
  5. Compose Discussion (interpreting findings)
  6. Write Introduction (setting up the research question)
  7. Craft Abstract (synthesizing the complete story)
  8. Create Title (concise and descriptive)
Remember: Bullet points are for planning only—the final manuscript must be in complete paragraphs.
Stage 3: Revision
  1. Check logical flow and "red thread" throughout
  2. Verify consistency in terminology and notation
  3. Ensure figures/tables are self-explanatory
  4. Confirm adherence to reporting guidelines
  5. Verify all citations are accurate and properly formatted
  6. Check word counts for each section
  7. Proofread for grammar, spelling, and clarity
Stage 4: Final Preparation
  1. Format according to journal requirements
  2. Prepare supplementary materials
  3. Write cover letter highlighting significance
  4. Complete submission checklists
  5. Gather all required statements and forms
阶段1：规划
  1. 确定目标期刊并查阅作者指南
  2. 确定适用的报告规范（CONSORT、STROBE等）
  3. 勾勒手稿结构（通常为IMRAD）
  4. 将图表规划为论文的核心框架
阶段2：起草（每个章节采用两阶段写作流程）
  1. 从图表开始（核心数据故事）
  2. 对以下每个章节，遵循两阶段流程：
    • 第一步：利用已验证的文献、笔记和结果创建带项目符号的大纲
    • 第二步：将项目符号转化为流畅的完整段落
  3. 撰写方法部分（通常最容易起草）
  4. 起草结果部分（客观描述图表内容）
  5. 撰写讨论部分（解读研究发现）
  6. 撰写引言部分（提出研究问题）
  7. 撰写摘要部分（整合完整研究故事）
  8. 创建标题（简洁且具描述性）
注意：项目符号仅用于规划——最终手稿必须使用完整段落。
阶段3：修订
  1. 检查全文逻辑连贯和核心主线
  2. 验证术语和符号的一致性
  3. 确保图表可独立理解
  4. 确认符合报告规范
  5. 验证所有引用准确且格式正确
  6. 检查各章节字数
  7. 校对语法、拼写和清晰度
阶段4：最终准备
  1. 按照期刊要求格式化
  2. 准备补充材料
  3. 撰写突出研究意义的求职信
  4. 完成投稿检查清单
  5. 收集所有所需声明和表格

Integration with Other Scientific Skills

与其他科学技能的整合

This skill works effectively with:
  • Data analysis skills: For generating results to report
  • Statistical analysis: For determining appropriate statistical presentations
  • Literature review skills: For contextualizing research
  • Figure creation tools: For developing publication-quality visualizations
此技能可与以下技能有效配合：
  • 数据分析技能：生成需报告的结果
  • 统计分析：确定合适的统计呈现方式
  • 文献综述技能：为研究提供背景
  • 图表创建工具：生成符合出版标准的可视化内容

References

参考文献

This skill includes comprehensive reference files covering specific aspects of scientific writing:
  • references/imrad_structure.md
    : Detailed guide to IMRAD format and section-specific content
  • references/citation_styles.md
    : Complete citation style guides (APA, AMA, Vancouver, Chicago, IEEE)
  • references/figures_tables.md
    : Best practices for creating effective data visualizations
  • references/reporting_guidelines.md
    : Study-specific reporting standards and checklists
  • references/writing_principles.md
    : Core principles of effective scientific communication
Load these references as needed when working on specific aspects of scientific writing.
此技能包含涵盖科学写作特定方面的完整参考文件：
  • references/imrad_structure.md
    ：IMRAD格式和分章节内容的详细指南
  • references/citation_styles.md
    ：完整引用格式指南（APA、AMA、Vancouver、Chicago、IEEE）
  • references/figures_tables.md
    ：创建有效数据可视化内容的最佳实践
  • references/reporting_guidelines.md
    ：特定研究类型的报告标准和检查清单
  • references/writing_principles.md
    ：有效科学沟通的核心原则
处理科学写作的特定方面时，可按需加载这些参考文件。

Nature-Style Academic Polishing

《自然》风格学术润色

Sentence Length Control

句子长度控制

Rule: Every sentence in the polished output must be ≤30 words and span no more than 2 lines at standard formatting.
Cohesion strategies:
StrategyExample
Restate the subject"The resulting serial sections exhibit inherent spatial asymmetry. Such asymmetry makes pixel-level alignment unattainable."
Adverbial connective"PAS captures only one dimension of the pathology. Therefore, special stains are essential."
Pronoun reference"Pathologists employ a panel of histochemical stains. Each targets a distinct feature."
Definite article + noun"The renal biopsy specimen is small. The limited tissue complicates multi-modal analysis."
Demonstrative + noun"This heterogeneity makes IgAN an ideal test case."
规则：润色后的输出中，每个句子必须≤30词，且标准格式下不超过2行。
连贯策略：
策略示例
重述主语"The resulting serial sections exhibit inherent spatial asymmetry. Such asymmetry makes pixel-level alignment unattainable."
状语连接词"PAS captures only one dimension of the pathology. Therefore, special stains are essential."
代词指代"Pathologists employ a panel of histochemical stains. Each targets a distinct feature."
定冠词+名词"The renal biopsy specimen is small. The limited tissue complicates multi-modal analysis."
指示词+名词"This heterogeneity makes IgAN an ideal test case."

Practical Heuristics

实用启发法

  • Each English sentence should carry ONE subject + ONE verb as its core.
  • Avoid overloading sentences with participial phrases, lists, or multiple propositions.
  • Split long sentences to improve clarity and flow.
  • 每个英文句子的核心应包含一个主语+一个谓语。
  • 避免用分词短语、列表或多个命题使句子过载。
  • 拆分长句以提升清晰度和流畅度。

Example

示例

Before: To characterise phenotypic evolution and spatial reorganisation within this microenvironment during kidney injury, pathologists employ a panel of histochemical stains. PAS, Masson's trichrome, PAM and H&E each interrogate distinct pathological dimensions, including basement membrane lesions, collagen deposition and cellular infiltration, enabling a composite assessment of tissue damage. (38 words)
After: To characterise phenotypic evolution and spatial reorganisation within this microenvironment during kidney injury, pathologists employ a panel of histochemical stains. PAS, Masson's trichrome, PAM and H&E each interrogate distinct pathological dimensions. These include basement membrane lesions, collagen deposition and cellular infiltration. Together, they enable a composite assessment of tissue damage.
润色前： To characterise phenotypic evolution and spatial reorganisation within this microenvironment during kidney injury, pathologists employ a panel of histochemical stains. PAS, Masson's trichrome, PAM and H&E each interrogate distinct pathological dimensions, including basement membrane lesions, collagen deposition and cellular infiltration, enabling a composite assessment of tissue damage. (38 words)
润色后： To characterise phenotypic evolution and spatial reorganisation within this microenvironment during kidney injury, pathologists employ a panel of histochemical stains. PAS, Masson's trichrome, PAM and H&E each interrogate distinct pathological dimensions. These include basement membrane lesions, collagen deposition and cellular infiltration. Together, they enable a composite assessment of tissue damage.