Browse reusable Agent Skills, each with a clear purpose and practical guidance.
在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 处理代码与数据可用性、撰写可用性声明时调用。本刊作为中文期刊是否设立独立的制品评审徽章(artifact badge)制度目前待核实——本技能讲清现状与稳妥做法：如何写诚实的代码/数据可用性声明、如何组织可供外审核验的复现仓库、如何在不可公开时说明原因与替代验证途径、如何与审稿匿名要求(是否双盲待核实)协调。用于让模式识别/机器学习论文的制品支撑而非拖累评审，避免可用性声明与实际提供的材料不一致。
在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 撰写审稿意见答复(rebuttal)与修回说明时调用。覆盖如何逐条回应外审与编辑意见、如何组织答复信结构、如何在修订稿中标注并定位修改、如何礼貌而有据地处理不同意的意见、如何应对"较大修改重新送审"、以及补做实验/改写后的证据呈现。用于把一轮大修/小修转化为经得起复审的答复信与修订稿，提升再审通过率；本刊多轮修回为常态，答复质量直接影响录用。
在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 撰写相关工作/文献综述并确立创新性时调用。本刊要求成果具原创创新价值，相关工作须 delta 优先——把本文相对最接近工作的增量讲清，而非文献罗列。覆盖如何组织相关工作、如何在模式识别/机器学习/视觉/NLP 语境中定位 delta、如何用 GB/T 7714 规范引用中英文文献并给中文文献英文对照、如何避免"综述式罗列"与"漏引近作"两类退稿风险。用于把创新性写到经得起外审质疑的水准。
在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 判断一个选题是否契合、以及该写成何种稿件类型时调用。本刊专注模式识别、人工智能、机器学习、计算机视觉、自然语言处理、智能系统等 AI 细分方向，比综合性计算机刊更聚焦 AI，与《自动化学报》(控制为主)、《计算机学报》(全学科)、《软件学报》(系统软件)分工不同。用于评估贡献是否有原创增量、是否落在本刊 AI 学科范围、该投研究论文还是综述、以及是否更适合改投兄弟刊，避免因不符宗旨在初审被退。
在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 撰写或打磨中文长文体例时调用。覆盖报道性中文摘要(约200字)与English Abstract(约200词)的四要素、中英文关键词(3~5)、中图分类号(TP)、作者简介与基金项目、参考文献 GB/T 7714 且中文文献中英文对照、量与单位法定用法、首页范式(问题→现状不足→贡献→证据→意义)，以及模式识别/机器学习论文的公式、算法、图表规范。用于把一份 AI 细分方向的中文稿件写到符合本刊体例、经得起编辑初审与外审的水准。
Use when a Physical Review Letters manuscript exceeds the strict deductible length limit, where figures, equations, and references all count against the budget. Triages what to cut, compress, or move to Supplemental Material; does not rewrite content from scratch.
Use when responding to Physical Review Letters referee reports or editor decisions — point-by-point reply, resubmission, and the APS appeal route. Structures the response and revision; does not redraft the science from scratch.
Use when imposing a conceptual argument or analytical structure on a human-geography literature for a Progress in Human Geography (PiHG) review — the "spine" that turns a reading list into an argument about where the subfield is and should go. Designs the framework; it does not gather the literature (proghg-literature-synthesis) or judge balance (proghg-comprehensiveness-and-balance).
Use when responding to Progress in Human Geography (PiHG) editor and referee feedback on a review or progress report — coverage gaps, fairness/reflexivity complaints, conceptual-argument asks, accessibility, and scope/strand fit. Drafts the response and revision plan; it does not run the submission preflight (proghg-submission) or redesign the spine from scratch (proghg-organizing-framework).
Use when documenting the scholarly apparatus, positionality, and coverage/search account of a Progress in Human Geography (PiHG) review under qualitative and critical-geography norms (not PRISMA tallies). Builds the transparency and reflexivity record; it does not gather the literature (proghg-literature-synthesis) or appraise individual works (proghg-comprehensiveness-and-balance).