面向《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 的 12 个中文技能，覆盖投稿、修回答复、录用定稿、代码数据可用性、可复现性、补充材料、审稿流程、中文写作规范、相关工作、图形/几何实验设计、全流程与选题栏目定位。关键事实以官网 jcad.cn、CNKI 与 CCF 推荐中文科技期刊目录双源核实，核验日期 2026-07-09。
Plugin jcadcg-skills from marketplace awesome-journal-skills in brycewang-stanford/Awesome-Journal-Skills. Commands read from the repo's manifest — 1 month ago.
jcadcg-artifact-evaluation在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 准备代码与数据可用性、撰写诚实的可用性声明时调用。说明本刊是否设正式制品评审(artifact evaluation)属待核实的现状，给出无论政策如何都应做到的图形学制品自律标准：代码/数据/网格/预训练模型/渲染脚本的公开与托管、双盲外审下的匿名化、演示视频与结果可复现、受限数据的替代核验途径，以及可用性声明的写法。适用于把图形/几何论文的制品打包到经得起审阅、避免声明与实际不符的场景。
jcadcg-author-response在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 撰写审稿意见答复(rebuttal)与修回说明时调用。覆盖点对点(point-by-point)逐条答复的组织、大修/小修的不同策略、如何用新增图形证据(渲染对比、几何误差、消融、用户研究)回应质疑、修改处在正文的定位标注、不采纳意见时的礼貌据理说明、以及修回说明信的结构。适用于收到外审意见后把每条意见闭环、准备好经得起复审与主编终审的修回材料的场景。
jcadcg-camera-ready在《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 稿件录用后、准备定稿与校样清样时调用。覆盖录用后解除匿名(补真实致谢、基金编号、作者简介、代码/数据真实链接)、按编辑部要求定稿排版、校样(清样)校对流程、图形结果的印刷分辨率与色彩、演示视频/多媒体附件的最终提交、版权与出版许可、以及见刊前最后一轮易错项核对。适用于把已录用的图形/CAD 论文稳妥推进到见刊、避免校样阶段出错的场景。
jcadcg-experiments在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 设计与呈现实验证据时调用。覆盖图形学/CAD 论文特有的证据：几何精度指标(Chamfer/Hausdorff)、渲染质量(PSNR/SSIM/LPIPS)、可视化有效性与用户研究、公平基线与相同预算对比、消融、时间与显存开销、渲染图与几何误差色图呈现、以及主客观评测与统计口径。适用于把方法主张与图形/几何证据一一绑定、避免"只有指标无视觉对比"或"基线不公平"在外审被质疑的场景。
jcadcg-related-work在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 撰写相关工作与文献综述、确立图形/几何创新性时调用。覆盖 delta 优先的相关工作组织、如何把本文与最接近的图形学/CAD/可视化/VR 工作区分、如何按贡献类型(几何处理、渲染、CAD、可视化、VR、图像视频)分类梳理、GB/T 7714 引用与中文文献中英文对照、以及避免文献罗列与漏引本刊相关工作。适用于把相关工作写成支撑创新性论证而非文献清单、并在外审前站稳增量的场景。
jcadcg-reproducibility在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 提升论文可复现性与实验可重复时调用。覆盖图形学/CAD 特有的可复现要点：固定随机种子、记录 GPU/驱动/渲染器版本、锁定网格/点云/纹理/视频数据集、固定渲染与几何管线参数(采样数、光照、相机、分辨率)、复现包冒烟测试、几何误差与渲染质量指标的计算脚本对齐、以及大数据的稳定托管。适用于让外审与读者能重跑出论文表图、避免"结果无法复现"质疑的场景。
jcadcg-review-process在需要理解《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 审稿流程、稿件状态与各轮次预期时调用。覆盖编辑初审→专家外审(双盲)→复审退修→栏目主编组织编委终审的同行评议链路、综述稿通过初审后一般由 3~4 名专家审阅的口径、初审退稿常见理由、修回轮次(大修/小修)与重新送审、在线系统的状态跟踪、以及审稿周期/录用率等待核实项。适用于投稿后判断当前处于哪一环、下一步该做什么、如何合理预期时间线的场景。
jcadcg-submission在向《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 正式提交稿件前做投稿就绪审计时调用。覆盖官网 jcad.cn 在线投稿系统注册与提交、DOC/PDF/ZIP/RAR 电子版格式、题目 20 字以内、中英文摘要与关键词、中图分类号(TP)、GB/T 7714 参考文献中英文对照、图形结果与演示视频的匿名化、学术不端查重、栏目归属与退稿风险分诊。适用于把一份计算机图形学/CAD/可视化/VR 方向的中文原创论文打磨到符合本刊同行评议门槛的场景。
jcadcg-supplementary在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 组织附录、补充材料与多媒体附件(尤其演示视频)时调用。覆盖按"决定性"划分正文与附录的原则、图形学论文特有的演示视频/交互录屏/高分辨率渲染图/额外几何结果的归属、补充材料的匿名化与格式(DOC/PDF/ZIP/RAR/视频编码)、以及正文自足性(不依赖补充材料才能读懂主张)。适用于把决定性证据留正文、把扩展性材料稳妥外置、避免正文臃肿或关键证据被埋没的场景。
jcadcg-topic-selection在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 选题定位、判断稿件是否落在本刊图形学/CAD 版图、以及在兄弟中文刊之间选择落点时调用。覆盖本刊图像视频处理、可视化与可视分析、CAD/CAE/CAM、VR/AR/MR、三维图形计算与交互等栏目的边界，帮助判断选题的图形/几何增量是否充分、与综合刊《计算机学报》和软件方向《软件学报》如何分工、以及该选研究论文还是综述。适用于动笔前确认选题契合、避免因不符宗旨在初审被退的场景。
jcadcg-workflow在需要《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 投稿从选题到见刊的全流程时间线与技能编排时调用。把 12 个技能串成一条弧线：选题契合(图形/CAD 版图)→中文写作体例→相关工作 delta→图形/几何实验→可复现与制品→补充材料/演示视频→投稿就绪审计→审稿流程→修回答复→录用定稿校样，并标注每阶段的关键产物、易变待核实项与决策点。适用于统筹一次 JCAD&CG 投稿、明确当前处于哪一步与下一步该调用哪个技能的场景。
jcadcg-writing-style在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 撰写或打磨中文论文体例时调用。覆盖报道性中英文摘要(问题/方法/结果/结论四要素)、中英文关键词、中图分类号(TP 系列)、题目 20 字以内、GB/T 7714 参考文献且中文文献中英文对照、量与单位法定计量、图题表题中英文规范、以及图形学论文首页范式(问题→现状不足→贡献→图形证据→意义)。适用于把图形/几何/可视化/CAD 稿件写到符合本刊中文科技写作规范、避免因体例不合在初审被退补正的场景。
AI-first computer-science conference skill stack: 155 conference fit-and-submission profiles plus a CS/AI router. Covers top AI/ML, data mining, vision, NLP, robotics, HCI, systems, security, software engineering, programming languages, databases, and theory venues, with current-cycle CFP and author-kit re-check discipline.
156 skills
English natural-science / clinical / physical / formal-science journal routing and per-journal fit skills with official-submission-check discipline.
155 skills
Chinese social-science journal routing and per-journal fit skills with official-submission-check discipline.
103 skills
English economics / business journal routing and per-journal fit skills with official-submission-check discipline.
101 skills
English engineering / technology journal routing and per-journal fit skills with official-submission-check discipline.
41 skills
English humanities journal routing and per-journal fit skills with argument-, source-, and style-guide discipline.
37 skills
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers, and more.
2 skills · 1 MCP server
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers, and more.
2 skills · 1 MCP server
Enterprise / cross-functional Research Operations domain — the managed counterpart to the academic research/ domain. v2.9.0 ships 5 skills: orchestrator (context: fork), clinical-research (protocol synopsis, endpoint selection, sample-size/power for means/proportions/survival, phase-gate feasibility), research-finance (R&D budgeting with F&A split, burn/runway, capitalize-vs-expense routing, portfolio ROI), market-research (TAM/SAM/SOM top-down and bottoms-up, survey sampling with FPC, Kotler segmentation), and product-research (goal-matched study design, method-based saturation, insight synthesis flagging single-source anecdotes). Hard rules: outputs are estimates routed to a named clinical or finance owner, market sizes show method + assumptions, product insights require recurrence across independent participants. 24 stdlib Python tools, 12 reference docs. Distinct from ra-qm-team, finance, research/grants, product-team, and marketing-skill.
6 skills · 7 commands · 2 agents
Contribution-first, reviewer-aware academic paper and report writing system.
2 skills
Semi-automated research assistant with skills for literature review, experiments, analysis, writing, and project knowledge management
45 skills · 66 commands · 6 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.