文档与办公格式（Anthropic 官方）
View all →处理 PDF / Word / Excel / PPT 的官方 skill，论文写作流水线最常用。
anthropics/skills
Anthropic 官方的 PDF 处理 skill。围绕 pypdf 等 Python 库展开，覆盖文本与 表格抽取、页面合并拆分、旋转加水印、表单填写、加密解密，扫描件也能 做 OCR 让全文可检索。论文流水线里读文献、整理审稿意见、汇编附录 几乎绕不开。
docx
anthropics/skills
Anthropic 官方的 Word 文档 skill。把 .docx 当作 ZIP+XML 来读写，能新建 带目录、页眉、抬头的正式文档，也能解包后改 XML 再封回去做精细修订。 常见场景包括起草 PRD、改投稿信、把 .doc 转 .docx，以及处理审阅模式 下的修订与批注。
xlsx
anthropics/skills
Anthropic 官方的电子表格 skill，覆盖 .xlsx / .xlsm / .csv / .tsv。重点是 零公式错误、保留既有模板格式、字体统一专业。适合整理实证数据、修 脏表、把多源数据拼成研究用的分析表，或者按既定模板做财务建模。
pptx
anthropics/skills
Anthropic 官方的 PowerPoint skill。读取演示文稿用 markitdown 抽文字， 做缩略图扫一眼版式；新建用 pptxgenjs，改既有模板就解包 XML 再重打包。 适合按学校或会议模板做答辩 deck、把研究结果转成讲稿，或批量改备注页。
doc-coauthoring
anthropics/skills
Anthropic 官方的文档协同写作 skill。把写作过程拆成三步：先收集上下文， 再迭代结构和措辞，最后做读者视角的可读性验证。适合写 PRD、设计文档、 RFC、决策记录这类需要把想法清楚转交给同事的结构化文稿。
设计与图形（Anthropic 官方）
View all →画图、做设计稿、生成主题与品牌素材。
frontend-design
anthropics/skills
Anthropic 官方的前端设计 skill，目标是做出可上线、视觉风格鲜明的界面， 避开常见的"AI 千篇一律"配色和居中堆叠版式。先定调子，再写 React / HTML / CSS，组件、落地页、海报、dashboard 都能用，注重细节和审美决断。
canvas-design
anthropics/skills
Anthropic 官方的视觉设计 skill，专做静态海报和插画类作品，输出 .pdf 或 .png。先用一份 .md 文件把"设计哲学"写清楚——形式、空间、色彩、构图， 再在画布上落地。要求原创，避免临摹在世艺术家的风格造成侵权。
algorithmic-art
anthropics/skills
Anthropic 官方的算法艺术 skill。用 p5.js 写生成式作品，支持种子化随机和 交互式参数调节，常见题材包括 flow field、粒子系统、涌现行为。先定一份 算法美学的"哲学"文档，再用 .html + .js 实现可交互的查看器。
brand-guidelines
anthropics/skills
Anthropic 官方品牌规范 skill。提供官方主色、辅助色与字体搭配，方便把 任意 artifact 套上 Anthropic 的视觉调性。给 Anthropic 内部或合作项目做 slide、海报、网页时直接调用，避免自己临摹品牌色出错。
theme-factory
anthropics/skills
Anthropic 官方的主题工具集 skill。预置 10 套配色 + 字体搭配方案，也能 按需生成新主题，应用到幻灯片、文档、报告、HTML 落地页等任何 artifact 上。 适合在没有强品牌约束时快速给产物套一致的视觉风格。
slack-gif-creator
anthropics/skills
Anthropic 官方的 Slack GIF 制作 skill。封装了 Slack 对动图的尺寸、帧率、 色数、时长这些隐性约束，提供生成与校验工具。emoji 用 128x128、消息用 480x480、控制在三秒内，避免做出来发不上去。
web-artifacts-builder
anthropics/skills
Anthropic 官方的 claude.ai 复杂 artifact 构建 skill。基于 React 18 + TypeScript + Vite + Tailwind + shadcn/ui，初始化、开发、再打包成单 HTML 文件 交给用户。适合做带路由、状态管理、复合组件的交互 demo，简单单文件 artifact 反而用不上。
开发与扩展（Anthropic 官方）
View all →建 MCP、写 skill、写 API、做测试、内部沟通。
claude-api
anthropics/skills
Anthropic 官方的 Claude API skill。用来构建、调试、优化基于 Anthropic SDK 的应用，强调默认开启 prompt caching。还负责模型版本之间的迁移 （Claude 4.5 到 4.6、4.6 到 4.7，以及退役模型替换），并能针对 thinking、 tool use、batch、citations、memory 等特性做调参。
mcp-builder
anthropics/skills
Anthropic 官方的 MCP server 开发指南 skill，支持 Python FastMCP 与 Node TypeScript SDK 两条路径。重点放在工具设计的质量上——既要覆盖 API， 又要提炼面向真实任务的 workflow 工具。适合给现有外部服务封 MCP 接口 给 LLM 调用。
skill-creator
anthropics/skills
Anthropic 官方的 skill 元 skill，用来从零写新 skill、修改已有 skill，并对 skill 触发准确性、表现做 eval。流程是先想清楚 skill 做什么，写初稿，跑 测试提示，做定量与定性评估，再迭代描述以提升触发命中率。
webapp-testing
anthropics/skills
Anthropic 官方的 Web 应用测试 skill。基于 Playwright 写原生 Python 脚本， 能验证前端功能、调试 UI 行为、抓截图、看浏览器日志。配套 `scripts/with_server.py` 管理服务进程，做端到端回归或排查页面问题时 最常用。
internal-comms
anthropics/skills
Anthropic 官方的内部沟通写作 skill。针对 3P 更新（Progress / Plans / Problems）、公司内部 newsletter、FAQ、状态报告、领导汇报、事故复盘等 常见格式，提供模板与示例。把日常内部文档对齐到组织偏好的格式与口吻。
流程纪律（obra/superpowers）
View all →Brainstorm → 写计划 → TDD → 验证 → 代码评审一整套工程纪律。
using-superpowers
obra/superpowers
obra/superpowers 体系的入口 skill。规则是：只要任务有 1% 可能命中某个 skill，就必须先 invoke 那个 skill 再回答，包括澄清问题之前。整套 superpowers 把流程纪律作为硬约束，本 skill 是建立这种纪律的起点。
brainstorming
obra/superpowers
obra/superpowers 的创意头脑风暴 skill。任何"做新功能、加新组件、改行为" 类的工作都要先走它：通过逐条提问澄清意图、需求和设计，把模糊想法 推演成完整方案。设计未经用户拍板前不能写代码、不能搭项目。
writing-plans
obra/superpowers
obra/superpowers 的实施计划撰写 skill。假定执行者对项目一无所知，把 多步任务拆成"动哪些文件、写什么代码、怎么测、要看哪些文档"的细颗粒 清单。强调 DRY、YAGNI、TDD、勤提交，方便后续交给子 agent 或新 session 执行。
executing-plans
obra/superpowers
obra/superpowers 的计划执行 skill。在新 session 里加载已经写好的实施 计划，先做一轮批判性 review，再按顺序执行每个任务，完成后报告。如果 平台支持 subagent，会推荐改用 subagent-driven-development 提高质量。
test-driven-development
obra/superpowers
obra/superpowers 的 TDD skill。先写测试、看它失败、再写最少代码让它过。 适用于新功能、bug 修复、重构、行为变更——抛弃式原型、生成代码、 配置文件这类情况要先和人确认。铁律是没有失败的测试，就不写实现代码。
systematic-debugging
obra/superpowers
obra/superpowers 的系统化调试 skill。铁律是没找到根因不能动手修，杜绝 随便贴补丁掩盖问题。覆盖测试失败、生产 bug、构建报错、性能问题、集成 问题等各种技术故障，强制走完根因调查阶段才允许提出修复方案。
verification-before-completion
obra/superpowers
obra/superpowers 的完工前验证 skill。在声称"做完了 / 修好了 / 通过了" 之前，必须本轮对话里跑一遍验证命令并贴出输出。证据先于结论，提交、 开 PR 前都要走一道。专治"先喊完成再被打脸"的常见漏洞。
requesting-code-review
obra/superpowers
obra/superpowers 的代码评审请求 skill。派一个独立 subagent 做评审，给它 精心构造的上下文，而不会继承当前 session 的历史。这样评审视角聚焦在 产物本身，主 session 也保留自己的上下文继续干活。完成大功能或合并 主分支前都该走一次。
receiving-code-review
obra/superpowers
obra/superpowers 的接收评审 skill。强调技术严谨而非情绪化回应：先完整 读完反馈，再用自己的话复述需求，对照代码事实做核验，技术上站不住 就有理有据地反驳。一次实现一项，逐条测试，避免盲目接受或形式上 应付。
writing-skills
obra/superpowers
obra/superpowers 的 skill 写作 skill。把写 skill 类比成对流程文档做 TDD： 先用 subagent 跑压力场景看 baseline 表现，再写 skill，再验证 agent 是否 遵守，最后封堵漏洞。个人 skill 放在 `~/.claude/skills` 或 `~/.agents/skills/`。
subagent-driven-development
obra/superpowers
obra/superpowers 的子 agent 驱动开发 skill。一项任务起一个新 subagent， 完成后走两阶段评审——先核 spec 合规，再看代码质量。子 agent 拿到的 是精心拼好的上下文，不继承主 session 历史，既让它专注，又保护主线的 上下文预算。
dispatching-parallel-agents
obra/superpowers
obra/superpowers 的并行 agent 派发 skill。面对两个以上互不依赖、无共享 状态的任务时，串行调查浪费时间，改成并行派 agent 同时跑。每个 agent 拿到隔离的上下文与精确指令，主 session 只负责协调。典型场景：多个 不相关的测试失败同时排查。
using-git-worktrees
obra/superpowers
obra/superpowers 的 git worktree skill。在动新功能或执行计划前，确保自己 在一个隔离工作区里。优先用平台原生 worktree 工具，没得用时再退到手工 git worktree。先检测是否已在隔离环境，避免和 harness 打架，也避免污染 主分支。
finishing-a-development-branch
obra/superpowers
obra/superpowers 的开发分支收尾 skill。验证测试通过 → 探测当前环境 → 给出合并、开 PR、清理等结构化选项 → 按选择执行 → 收尾清理。测试没过 必须先修，避免半成品被 merge 进主线。
Obsidian 笔记（kepano/obsidian-skills）
View all →Obsidian Markdown 方言、Canvas、Bases、命令行集成，配合 obsidian 笔记仓使用。
obsidian-markdown
kepano/obsidian-skills
kepano/obsidian-skills 里的 Obsidian Markdown 写作 skill。专门处理 Obsidian 对 CommonMark 和 GFM 的扩展语法：wikilinks、embeds、callouts、properties frontmatter、tags、注释。把笔记结构、属性、双向链接和嵌入这些 Obsidian-特有的写法理顺，新建或编辑 .md 时不踩坑。
obsidian-bases
kepano/obsidian-skills
kepano/obsidian-skills 里的 Obsidian Bases skill，用于编辑 .base 文件。 通过 YAML 描述 filters、formulas 和 table / cards / list / map 四种视图， 把笔记库当数据库查询。适合给研究项目做文献追踪表、任务面板、属性 汇总等动态视图。
obsidian-cli
kepano/obsidian-skills
kepano/obsidian-skills 里的 Obsidian CLI skill，通过 `obsidian` 命令行操作 正在运行的 vault：读写笔记、检索内容、管理任务和属性。还支持插件与 主题开发场景——reload 插件、跑 JS、抓错误、截图、看 DOM，方便在 终端里批量维护笔记或调试插件。
json-canvas
kepano/obsidian-skills
Obsidian Canvas 文件（.canvas）的读写规范 skill。Canvas 本质是带 nodes 和 edges 两个数组的 JSON，按 JSON Canvas Spec 1.0 组织。skill 给出 新建画布、追加节点、连线、修改属性的操作步骤，以及节点 id 用 16 位 hex、文本节点用 \n 换行等容易踩坑的细节。适合让 agent 帮你批量生成 思维导图或流程图。
defuddle
kepano/obsidian-skills
用 Defuddle CLI 把网页正文抽成干净 markdown 的 skill。相比 WebFetch 直接抓 HTML，它会去掉导航栏、广告、侧边推荐这些噪声，省 token。 典型用法是 defuddle parse <url> --md，也能单独取标题、描述、域名 等字段。URL 已经是 .md 结尾就不需要它，直接走 WebFetch 即可。
找 skill / 装 skill
View all →通过 npx 命令搜索全网公开 skill 并一键安装。
UI / 设计（社区高分）
View all →67 种 UI 风格、161 套配色、57 组字体配对，覆盖 15+ 技术栈的设计 skill。
论文 · 数据分析
View all →实验规划、消融研究、结果分析、统计与表格整理。
ablation-planner
Chanw-research/claude-code-paper-writing
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.
analyze-results
Chanw-research/claude-code-paper-writing
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
experiment-plan
Chanw-research/claude-code-paper-writing
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
results-analysis
Chanw-research/claude-code-paper-writing
Use when analyzing experimental results, validating comparisons, generating paper-ready results text, or turning model-evaluation outputs into figures, tables, and defensible claims.
run-experiment
Chanw-research/claude-code-paper-writing
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
statistical-analysis
Chanw-research/claude-code-paper-writing
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.
xlsx
Chanw-research/claude-code-paper-writing
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.
论文 · 文档处理
View all →docx / pdf / formula / proof reading 等论文素材处理。
docx
Chanw-research/claude-code-paper-writing
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.
formula-derivation
Chanw-research/claude-code-paper-writing
Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.
markitdown
Chanw-research/claude-code-paper-writing
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.
Chanw-research/claude-code-paper-writing
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
proof-checker
Chanw-research/claude-code-paper-writing
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
proof-writer
Chanw-research/claude-code-paper-writing
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
论文 · 图表绘制
View all →paper figure / illustration / mermaid / drawio / plotly / seaborn 等可视化与配图。
drawio
Chanw-research/claude-code-paper-writing
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).
figure-description
Chanw-research/claude-code-paper-writing
Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.
figure-generation
Chanw-research/claude-code-paper-writing
Generate publication-quality scientific figures using matplotlib/seaborn with a three-phase pipeline (query expansion, code generation with execution, VLM visual feedback). Handles bar charts, line plots, heatmaps, training curves, ablation plots, and more. Use when the user needs figures, plots, or visualizations for a paper.
figure-planner
Chanw-research/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.
figure-spec
Chanw-research/claude-code-paper-writing
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
mermaid-diagram
Chanw-research/claude-code-paper-writing
Generate Mermaid diagrams from user requirements. Saves .mmd and .md files to figures/ directory with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.
nature-data
Chanw-research/claude-code-paper-writing
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for academic publication, or Chinese-to-English data availability wording for Chinese-speaking authors preparing Nature-family submissions.
nature-figure
Chanw-research/claude-code-paper-writing
Submission-grade Nature/high-impact journal figure workflow for Python or R. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, or journal-ready SVG/PDF/TIFF outputs, especially for Nature-family or other high-impact journals. Before plotting, define the figure's conclusion, evidence logic, export needs, and review risks. If the user has not chosen Python or R, ask "Python or R?" and stop. Use only the selected backend for figure generation, previewing, exporting, and QA. Supports matplotlib/seaborn and ggplot2/patchwork/ComplexHeatmap. Not for dashboards or Illustrator/Figma-first infographics.
paper-figure
Chanw-research/claude-code-paper-writing
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.
paper-illustration
Chanw-research/claude-code-paper-writing
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
plotly
Chanw-research/claude-code-paper-writing
Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.
seaborn
Chanw-research/claude-code-paper-writing
Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.
论文 · 文献综述
View all →arxiv / pyzotero / systematic-review / citation-audit 等文献检索、引用核对与综述写作。
alphaxiv
Chanw-research/claude-code-paper-writing
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
arxiv-database
Chanw-research/claude-code-paper-writing
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.
arxiv
Chanw-research/claude-code-paper-writing
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
citation-audit
Chanw-research/claude-code-paper-writing
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
citation-management
Chanw-research/claude-code-paper-writing
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.
citation-verifier
Chanw-research/claude-code-paper-writing
Use when checking manuscript citations, bibliography hygiene, DOI or PMID completeness, placeholder references, or BibTeX consistency before submission or revision.
comm-lit-review-claude-single
Chanw-research/claude-code-paper-writing
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.
deep-research
Chanw-research/claude-code-paper-writing
Conduct systematic academic literature reviews in 6 phases, producing structured notes, a curated paper database, and a synthesized final report. Output is organized by phase for clarity.
deepxiv
Chanw-research/claude-code-paper-writing
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
exa-search
Chanw-research/claude-code-paper-writing
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
literature-review
Chanw-research/claude-code-paper-writing
Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.
management-review-planner
Chanw-research/claude-code-paper-writing
Plan management and strategy literature reviews before drafting, build and freeze a reusable review framework inside the workspace, trace key construct definitions back to anchor sources, and refine the section and paragraph blueprint with the user before handing off to the writing skill.
management-review-writer
Chanw-research/claude-code-paper-writing
Draft management and strategy literature reviews from an OpenAlex review workspace or a curated paper list, using paragraph-only academic prose, real APA citations, and synthesis across theory, methods, and context. Use only after an approved review plan exists.
nature-citation
Chanw-research/claude-code-paper-writing
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF.
novelty-check
Chanw-research/claude-code-paper-writing
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
openalex-ajg-insights
Chanw-research/claude-code-paper-writing
Search ABS/AJG-ranked literature through the bundled openalex-ajg-mcp backend, preserve review corpora for systematic literature reviews, download shortlisted papers through the bundled paper-download backend, convert collected PDFs to Markdown with MinerU, and retrieve abstract or full-text viewpoints efficiently.
prior-art-search
Chanw-research/claude-code-paper-writing
Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find relevant prior art.
pyzotero
Chanw-research/claude-code-paper-writing
Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use this skill when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.
reference-audit-guide
Chanw-research/claude-code-paper-writing
Use when the user asks for citation-verification principles, reference-audit best practices, or guidance on preventing fake or inaccurate citations in academic writing.
research-lit
Chanw-research/claude-code-paper-writing
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
research-refine-pipeline
Chanw-research/claude-code-paper-writing
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
research-refine
Chanw-research/claude-code-paper-writing
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
review-orchestrator
Chanw-research/claude-code-paper-writing
Coordinate long-running literature review projects across the search, planning, and writing subagents. Use when the user wants the system to decide the next stage, enforce plan approval before drafting, or manage the review workflow over time.
semantic-scholar
Chanw-research/claude-code-paper-writing
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.
systematic-literature-review
Chanw-research/claude-code-paper-writing
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）。
论文 · 写作流程与纪律
View all →论文写作的全套纪律：bootstrap / plan / write / claim audit / rebuttal / submission audit。
academic-researcher
Chanw-research/claude-code-paper-writing
Use when conducting literature reviews, summarizing papers, comparing methodologies, identifying research gaps, or supporting scholarly writing across disciplines.
conference-paper-writing
Chanw-research/claude-code-paper-writing
Use when writing or revising ML or AI conference papers for venues such as NeurIPS, ICML, ICLR, ACL, AAAI, or COLM, especially when the workflow is conference-first rather than Nature-style journal-first.
idea-creator
Chanw-research/claude-code-paper-writing
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
idea-discovery
Chanw-research/claude-code-paper-writing
Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
nature-portfolio-playbook
Chanw-research/claude-code-paper-writing
Use when choosing among Nature, Nature Methods, or Nature Biotechnology, or when preparing a Nature Portfolio life-science manuscript for venue fit, article-type framing, and policy-aware pre-submission checks.
paper-analyzer
Chanw-research/claude-code-paper-writing
Use when deeply analyzing a single paper and producing structured notes on claims, methods, figures, evaluation, strengths, limitations, and related work.
paper-backup-before-word
Chanw-research/claude-code-paper-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。
paper-bootstrap
Chanw-research/claude-code-paper-writing
Use when starting a new manuscript project or cleaning up an existing paper directory and you need a standard structure, active source files, project memory, and venue defaults before deeper writing begins.
paper-claim-audit
Chanw-research/claude-code-paper-writing
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
paper-claude-md-bootstrap
Chanw-research/claude-code-paper-writing
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。
paper-compile
Chanw-research/claude-code-paper-writing
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.
paper-confirm-before-doing
Chanw-research/claude-code-paper-writing
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。
paper-logical-consistency
Chanw-research/claude-code-paper-writing
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"。
paper-one-session-one-task
Chanw-research/claude-code-paper-writing
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。
paper-parallel-audit
Chanw-research/claude-code-paper-writing
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）。
paper-pilot-before-batch
Chanw-research/claude-code-paper-writing
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..."）。
paper-plan
Chanw-research/claude-code-paper-writing
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.
paper-protect-terminology
Chanw-research/claude-code-paper-writing
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。
paper-reviewer
Chanw-research/claude-code-paper-writing
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.
paper-translate-advisor-feedback
Chanw-research/claude-code-paper-writing
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"。
paper-using-skills
Chanw-research/claude-code-paper-writing
《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。
paper-verify-before-handoff
Chanw-research/claude-code-paper-writing
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」。
paper-workflow
Chanw-research/claude-code-paper-writing
Use when deciding which paper-related skill to use or how to sequence manuscript work from project setup through submission and rebuttal.
paper-write
Chanw-research/claude-code-paper-writing
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
paper-writing-discipline
Chanw-research/claude-code-paper-writing
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"。
paper-writing
Chanw-research/claude-code-paper-writing
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.
rebuttal-response
Chanw-research/claude-code-paper-writing
Use when responding to journal or conference reviewer comments and you need a structured author response, aligned manuscript edits, and clear decisions about when to clarify, add evidence, concede, or respectfully disagree.
rebuttal
Chanw-research/claude-code-paper-writing
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
submission-audit
Chanw-research/claude-code-paper-writing
Use when a manuscript is close to submission or resubmission and you need a preflight audit for claim support, figure-panel coverage, legend sync, methods references, terminology stability, and venue-facing risks.
论文 · 演讲与海报
View all →academic-presentations / pptx / paper-poster / paper-to-beamer 等演讲与海报。
academic-presentations
Chanw-research/claude-code-paper-writing
Create academic presentation slide decks and optionally demo videos from research papers. Use when the user asks to "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides", or wants to turn a paper into a visual presentation. Covers slide generation, narration scripts, TTS audio, and video assembly.
nature-paper2ppt
Chanw-research/claude-code-paper-writing
Build a complete but efficient Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, abstract, figure legends, or reading notes. Use this skill whenever the user asks to make slides/PPT/PPTX for journal club, group meeting, paper sharing, thesis seminar, lab meeting, department report, or academic presentation from a research paper, not only medical papers. It identifies the paper type and argument, selects only the figures needed for the story, writes Chinese slide content and speaker notes, creates the actual .pptx deck, and performs lightweight verification with cross-platform Python tooling by default.
paper-poster
Chanw-research/claude-code-paper-writing
Generate a conference poster (article + tcbposter LaTeX → A0/A1 PDF + editable PPTX + SVG) from a compiled paper. Use when user says "做海报", "制作海报", "conference poster", "make poster", "生成poster", "poster session", or wants to create a poster for a conference presentation.
paper-slides
Chanw-research/claude-code-paper-writing
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
paper-to-beamer
Chanw-research/claude-code-paper-writing
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.
pptx
Chanw-research/claude-code-paper-writing
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.
论文 · 语言润色
View all →manuscript-optimizer / scientific-writing / humanizer-zh / 各档 polish 流程。
grant-proposal
Chanw-research/claude-code-paper-writing
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
humanizer-zh
Chanw-research/claude-code-paper-writing
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。
manuscript-optimizer
Chanw-research/claude-code-paper-writing
Use when reviewing or revising an academic manuscript whose central claim, evidence chain, figures, terminology, and prose may have drifted out of sync before submission or resubmission.
nature-polishing
Chanw-research/claude-code-paper-writing
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.
paper-polish-workflow
Chanw-research/claude-code-paper-writing
Systematic top-down workflow for polishing academic papers. Structure to logic to expression with user confirmation at each step.
results-section-revision
Chanw-research/claude-code-paper-writing
Use when revising a scientific manuscript Results section whose figures, evidence, and main claims are mostly fixed, but subsection flow, paragraph openings, reader guidance, and argumentative progression still feel abrupt, repetitive, or figure-by-figure.
scientific-writing
Chanw-research/claude-code-paper-writing
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.