claude-code-paper-writing

Use when designing, restructuring, or auditing manuscript figures and you need to define one main claim per figure, assign panel roles, align legends with the text, or decide what belongs in main figures versus supplement.

Use when checking manuscript citations, bibliography hygiene, DOI or PMID completeness, placeholder references, or BibTeX consistency before submission or revision.

Use when acting as a journal or grant reviewer and writing formal reviewer-side evaluations focused on methodology, statistics, reporting standards, reproducibility, and constructive feedback.

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → figure-spec/paper-illustration/mermaid-diagram → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished PDF. At `— effort: max | beast` (or explicit `— assurance: submission`), Phase 6 gates the Final Report on `tools/verify_paper_audits.sh`; the PDF is labelled `submission-ready` only when the external verifier is green. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

Polish, restructure, or translate academic prose into Nature-leaning English using the paper-architecture and writing-strategy principles from Scientific English Writing & Communication, with phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English.

Use when writing or revising scientific manuscripts, abstracts, figures, or references for journal submission and you need full-paragraph prose, scientific structure, citation-style guidance, or reporting-guideline support.

当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词，多源检索→去重→AI 逐篇阅读并评分（1–10分语义相关性与子主题分组）→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作（固定摘要/引言/子主题/讨论/展望/结论），保留正文字数与参考文献数硬校验，强制导出 PDF 与 Word。支持多语言翻译与智能编译（en/zh/ja/de/fr/es）。

Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

General-purpose diagramming tool using drawio XML format with 8900+ stencils. Best for custom diagrams requiring pixel-perfect positioning, diagrams with vendor-specific icons (AWS, Azure, Cisco), or any diagram not covered by specialized skills. Use network skill for network topology, uml skill for UML diagrams, architecture skill for layered system views. NOT for simple flowcharts (use mermaid) or data-driven charts (use vega).

Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

在编辑任何 .docx / Word 文件之前，必须先用 cp 创建带时间戳的备份副本， 并优先评估"用 markitdown 转 LaTeX 后再改"是否更安全； 只有在确认必须直接编辑 .docx 时才动手，且改完后必须提醒用户先打开 Word 验证完整性。 Use when 用户请求修改、润色、改写、重排任何 .docx 文件、 或调用 /docx skill、或 Edit/Write 操作目标是 .docx 文件时。

开始任何新的论文写作项目时（新建项目目录、第一次开会话、还没有 CLAUDE.md 文件）， 在写任何论文内容、改任何文件之前，必须先帮用户建一份项目级 CLAUDE.md， 把研究主题、投稿目标、术语保护清单、文件结构、写作风格、导师偏好这六项写清楚。 Use when 用户说"开始写新论文"、"新开一个项目"、"帮我写第 X 章"且项目目录里没有 CLAUDE.md 时。

论文写作中遇到任何模糊指令（改、整理、润色、重写、找出、统一、清理、看看、处理一下…）， 在调用任何写文件 / 编辑文件 / 批量操作工具之前，必须先用一段话向用户陈述 「我打算怎么做、改哪里、不改哪里」，并明确等待用户确认后再动手。 Use when 用户对论文 / 章节 / 段落 / 文献 / 图表 / 参考文献给出宽泛指令、 未指定具体范围或方法、未限定「只改 X 不改 Y」等边界。

当用户改动论文里的核心声明（研究问题、核心论点、因果关系、边界条件、假设、关键结论、对已有研究的态度）时， 必须先扫描该声明在全文其他章节的出现位置，列出来让用户核对哪些需要联动修改，再开始动手。 本 Skill 抓的是「论证一致性」（语义级），不是「术语一致性」（机械级）——两者互不替代。 Use when 用户改了核心论点、研究问题、主要结论、方法边界、假设； 或要求重写涉及核心声明的段落；或在交付前要求"检查一下逻辑"。

当用户在一次对话里同时提出多个论文写作任务（"顺便也帮我..."、"另外..."、"还有..."）， 必须先把这些任务列出来让用户挑一个，拒绝在同一个会话里串行做完所有事。 Use when 用户的一条请求里出现两个以上独立的写作 / 修改 / 核查任务， 或在已经在做 A 任务时临时追加 B 任务。

在执行 ≥ 30 条目的批量核查 / 批量修改任务（引用核查、术语一致性检查、格式统一、文献元数据补齐）时， 必须采用"派多个 Agent 并行 + 每个 Agent 输出 JSON + 主进程汇总落盘 + 分批断点续跑"的标准模式， 不得在主会话里串行单线程跑全量。 Use when 任务规模 ≥ 30，涉及对独立条目的同质操作（每个条目处理逻辑相同、之间无依赖）。

在执行任何 ≥ 30 条目的批量任务（批量改文件、批量核查引用、批量重命名、批量格式统一）之前， 必须先在 3–5 个样本上跑一遍，把样本结果给用户看，确认逻辑正确后再推全量。 Use when 用户请求处理"全部"、"所有"、"批量"、"逐个"某类对象， 且对象数量 ≥ 30，或数量未知（"把整个目录的..."）。

在跨多文件批改、术语统一、整篇论文润色、章节重写等可能改动专业术语 / 缩写 / 人名 / 概念命名的操作之前， 必须先显式列出"保护术语清单"，让用户确认哪些词不得被同义替换或改写，再开始执行。 Use when 用户要求跨章节修改、批量替换、整篇润色、术语统一、规范化、 或对出现专业术语 / 缩写 / 模型名 / 算法名 / 自定义概念的段落做改写。

当用户拿来导师的录音转写、便条、口头反馈、批注、邮件意见时， 禁止直接喂 AI 改文章；必须先把口语化 / 模糊 / 隐含的反馈翻译为 「位置 + 改什么 + 改成什么 + 标准 + 不动哪里」的可执行指令清单，让用户确认后再开始改。 Use when 用户提供导师反馈（录音、批注、便条、邮件、聊天截图、口述）， 并要求"按导师意见改一下"。

《Claude Code 科研手记》论文写作纪律 skill 集的入口与强制触发器。 建立"1% 可能适用就必须调用"的硬规则，列出本系列各核心纪律 skill 的触发条件， 防止用户在赶论文 / 紧张 / 熟练之后跳过该有的检查动作。 Use when 开始任何科研写作场景：写论文、改论文、整理参考文献、 画图、整理导师反馈、跑批量任务、改 Word、提交前检查 等。

在把任何成果交付给用户（"改完了"、"已完成"、"可以发给导师"、"可以提交"）之前， 必须运行一份硬检查清单：术语一致性、引用完整性、数据正确性、图表编号、 内部交叉引用、字数 / 格式合规、未完成 todo 残留、AIGC pattern（涉及文段改写时跑 chinese-de-aigc 五维自评）、 论证一致性（涉及核心声明改动时跑 paper-logical-consistency 复核）、 改动概要——任意一项 fail 都不能宣告完成。 Use when 你即将说「改完了 / 完成了 / 可以提交了 / 可以发给导师了」、 或用户问「是不是可以了」「还有什么要检查的吗」。

当用户在科研写作过程中踩到一个本系列 paper-* skill 没覆盖的新坑、 并表示"以后...我都要这样做"、"下次记得..."、"这种情况要先..."、"加一条新规则"时， 帮用户把这条新规则按 4 个判断题筛过，合格则按本 skill 提供的模板提炼成一个新的 paper-* skill 落盘。 Use when 用户说"以后...都要..."、"下次记得..."、"这种情况要先..."、 "帮我把这个习惯固化下来"、"加一条新规则"。

Generate LaTeX Beamer presentations from academic papers. Use this skill whenever the user wants to create a Beamer/LaTeX presentation, academic slides, seminar talk slides, or paper reading slides from a research paper. Also trigger when the user mentions: 论文汇报PPT, 论文报告幻灯片, paper presentation, beamer slides, 做一个论文的PPT, 论文解读演示文稿, conference talk slides, or any request to turn a paper into slides. This skill handles the full pipeline: reading the paper, extracting figures, structuring slides, generating compilable LaTeX, and validating the output. Even if the user just says 'help me present this paper' or 'make slides for my lab meeting', this skill applies.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

Systematic top-down workflow for polishing academic papers. Structure to logic to expression with user confirmation at each step.