com um clique
deepseek-nyamu
deepseek-nyamu contém 17 skills coletadas de jrcjrcc, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
统一学术论文写作全流程核心技能。涵盖科学论文写作(IMRAD结构)、ML/AI会议论文(NeurIPS/ICML/ICLR/ACL/AAAI/COLM)、系统会议论文(OSDI/SOSP/ASPLOS/NSDI/EuroSys)、报告规范与图表(CONSORT/STROBE/PRISMA)、引用管理(APA/AMA/Vancouver/Chicago/IEEE)、Python代码工具(IMRAD结构/统计报告/引用格式化/论证结构/审稿回应)、以及5阶段论文写作管线(从平台分析到提交准备)。当用户说"写论文"、"写学术论文"、"写科学论文"、"写 ML 论文"、"写系统论文"、"写期刊论文"、"NeurIPS 论文"、"OSDI 论文"、"规划论文"、"论文大纲"、"帮我规划一篇论文"、"设计论文结构"、"写一篇关于...的论文"、"论文审稿回应"等时触发。
中英文论文全流程审阅与质量审计系统。当用户说"审稿"、"论文评审"、"帮我看看论文"、"模拟审稿"、"paper review"、"自检论文"、"论文质量检查"、"检查论文完整性"、"验证论文结构"、"gate 这篇论文"、"audit 我的 manuscript"、"deep review"、"quick audit"、"看看论文能不能投"、"查重自查"、"检查提交前准备"、或提到论文预提交检查、修改后再审、委员会评审、审稿人质询等场景时触发。整合了深度审计 (v4.2)、5 角色委员会评审、review-paper 6 维度评估框架、以及轻量级论文自检清单。支持 LaTeX/Typst/PDF 格式,中英文论文。
Conduct comprehensive, systematic literature reviews while mastering information synthesis, meta-analysis, and knowledge integration across sources. Search multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.), synthesize findings using diverse methodological approaches (narrative, thematic, meta-analytic, evidence mapping), and generate professionally formatted documents with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.). Use for systematic reviews, meta-analyses, research synthesis, knowledge mapping, evidence gap analysis, and comprehensive literature searches across biomedical, scientific, and technical domains.
Complete citation lifecycle management for academic writing: collect citations from DOI/OpenAlex/arXiv, verify against Google Scholar to prevent AI-faked references, convert between BibTeX/APA/MLA/Chicago/Vancouver/IEEE formats, and retrieve open-access full-text via Unpaywall
Universal LaTeX document skill: create, compile, and convert any document to professional PDF with PNG previews. Supports resumes, reports, cover letters, invoices, academic papers, theses/dissertations, academic CVs, presentations (Beamer), scientific posters, formal letters, exams/quizzes, books, cheat sheets, reference cards, exam formula sheets, fillable PDF forms (hyperref form fields), conditional content (etoolbox toggles), mail merge from CSV/JSON (Jinja2 templates), version diffing (latexdiff), charts (pgfplots + matplotlib), tables (booktabs + CSV import), images (TikZ), Mermaid diagrams, AI-generated images, watermarks, landscape pages, bibliography/citations (BibTeX/biblatex), multi-language/CJK (auto XeLaTeX), algorithms/pseudocode, colored boxes (tcolorbox), SI units (siunitx), Pandoc format conversion (Markdown/DOCX/HTML ↔ LaTeX), and PDF-to-LaTeX conversion of handwritten or printed documents (math, business, legal, general). Compile script supports pdflatex, xelatex, lualatex with auto-detect
论文图表生成工具。支持架构图/系统流程图(Gemini AI生成)和数据图表 (matplotlib/seaborn 折线图/柱状图/散点图/热力图)。 当用户说"画图"、"论文图表"、"Figure"、"architecture diagram"、"plotting"、 "数据可视化"、"画个图"时触发。
中英文写作人工化与 AI 痕迹消除。当用户说"去 AI 味"、"降 AIGC 检测率"、"remove AI writing patterns"、"remove AI-isms"、"humanize"、"让文字不像 AI 写的"、"知网 AIGC"、"降重"、"论文查重 AI"、"改得像人写的"、"去 AI 痕迹"、"audit for AI tells"、"clean up AI writing"、"人工化重写"时触发。支持两类工作流:(1) 英文 AI 模式检测与重写(481 行规则库,覆盖词汇/句式/结构/节奏);(2) 中文学术 AIGC 降检测率(17 类中文 AI 痕迹模式,五步闭环工作流);(3) 标点符号审查(统计破折号数量,零容忍)。
科研基金申请写作。支持 NSF、NIH、DOE、DARPA、NSTC 等机构的 基金申请书撰写,包括机构特定格式、评审标准、预算编制和创新论证。 当用户说"基金申请"、"grant"、"proposal"、"NSF"、"NIH"、 "科研资助"、"基金写作"时触发。
科学假设生成与实验设计。从观察或数据出发,系统性地生成可检验的假设, 设计实验方案并制定预测。遵循科学方法框架。 当用户说"生成假设"、"提出假设"、"实验设计"、"hypothesis"、 "设计实验"、"研究假设"时触发。
统一论文写作全流程技能。涵盖论文写作(IMRAD结构/ML会议/系统会议)、 论文审稿与质量审计(deep-review/quick-audit/gate/re-audit/polish 5模式)、 系统性文献综述、引用管理(BibTeX/APA/MLA/Chicago/Vancouver/IEEE)、 引用验证防伪、开放获取检索、LaTeX排版与编译、论文图表绘制、 中英文写作AI痕迹消除、科研基金申请、科学假设生成与实验设计。 用户说"写论文"、"审稿"、"文献综述"、"引用管理"、"LaTeX"、"论文图表"、 "去AI味"、"基金申请"、"假设生成"、"paper review"、"literature review"、 "citation"、"latex"、"写作"、"降重"、"降AIGC"、"图表"、"plotting"等时触发。
Strategic delegation for multi-step coding, research, or verification work. Use when a task can be split into parent reasoning plus focused sub-agent execution through agent_open, agent_eval, and agent_close.
Create, edit, inspect, or convert Word documents and DOCX deliverables such as memos, reports, letters, templates, and forms.
Scaffold codewhale local plugin directories and activation notes. Use when the user asks to create, package, or sketch a plugin for codewhale.
Create, edit, inspect, or convert PowerPoint decks and PPTX slide presentations with practical layout and verification steps.
Create or improve codewhale skills. Use when the user wants a new skill, wants to update an existing skill, or needs guidance on when a skill should be a skill versus MCP, hooks, tools, or a plugin scaffold.
Create, edit, analyze, clean, or convert spreadsheets including XLSX, CSV, TSV, formulas, charts, and tabular reports.
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.