Use when drafting, restructuring, or polishing Chinese NSFC proposals (2026 template), especially when strict section-by-section gating, hypothesis-objective-content-problem consistency, literature verification via paper-search MCP, and anti-AI Chinese academic writing constraints are required. 触发词：国自然、国家自然科学基金、基金申请书、科研申请、NSFC、标书、本子、面上项目、青年基金。
Universal assistant for writing high-impact academic literature reviews (Nature/Cell/Lancet level). Supports real-time Zotero integration, outline persistence, and multi-mode reference management. Use when writing a comprehensive review article requiring systematic search, synthesis, and citation management. 触发词：写综述、文献综述、综述写作、literature review、review article、改综述、完善综述、继续写综述、improve review。
用于从零撰写或润色符合Nature/Science/Cell标准的SCI研究论文（Article类型），适用于多学科。触发词：写论文、SCI论文、学术写作、科研写作、论文润色、研究论文、学术投稿、投稿、润色论文、polish paper、write SCI paper、academic writing、draft paper、manuscript writing。路由说明：退稿/返修改主稿→用revise-sci；只写审稿意见回复→用reviewer-response-sci；独立成稿的纯语言润色（拿到别人写好的整稿只改语言、不进本管道）→用polish-sci，本技能的润色仅指管道内 Phase 10 对自写稿的润色；综述/文献综述→用review-writing。本技能侧重写新稿与自写稿润色，Phase 13B含内部初步退稿自查但不出回复包也不出修订稿docx。
用于SCI审稿意见逐条回复的全流程技能，适用于期刊大修/小修阶段，只出回复包（HTML），不改主稿。触发词：审稿意见回复、回复审稿人、回复reviewer、response letter、回复信、rebuttal、逐条回复、Response to Reviewer、revise and resubmit、R&R、reviewer comments。路由说明：与revise-sci区分，本技能只出回复包不改主稿，需同时改主稿并出修订稿docx请用revise-sci；与reviewer-simulator区分，本技能针对已收到的意见写回复，后者是模拟生成审稿意见。
退稿/返修全管道，同时出逐条回复信+修改后正文docx+Patch修订。触发词：改稿、修改稿子、修订正文、退稿改进、返修、revise manuscript、major revision、minor revision、revise and resubmit、point-by-point response、revised manuscript。路由说明：与reviewer-response-sci区分，本技能同时改主稿+出回复包，后者只出回复不改稿；与gsw区分，gsw写新稿，本技能专处理已有稿子的审稿意见驱动修改。
用于将SCI论文材料转化为中文博士或硕士学位论文草稿，执行严格的章节结构、原子化Markdown工作流、门禁检查和版本回滚。当用户提到博士论文、硕士论文、学位论文、毕业论文、SCI转论文、doctoral thesis、master thesis、dissertation 时优先调用。
用于模拟高标准学术同行评审，对医学、生物、药学等领域稿件进行法医式检查、目标期刊契合度评估和证据锚定批评，输出结构化中文审稿报告。当用户提到模拟审稿、帮我审稿、预审、审稿报告、做reviewer、审一下这篇文章、投稿前自查、审稿人会怎么挑刺、这篇能不能中、peer review、simulate reviewer、review manuscript 时优先调用。注意与 reviewer-response-sci（用于回复审稿意见）区分：本技能是模拟审稿人写审稿意见，后者是针对已收到的审稿意见撰写回复。
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).