fourteen1416/academic-agent-toolkit

fourteen1416/academic-agent-toolkit · AGENTS.md

fourteen1416/academic-agent-toolkit · academic-toolkit/AGENTS.md

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed to answer…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/agent-bootstrap/SKILL.md · 任意智能体自举驱动本academic-toolkit：读协议、探测能力、选择路由或启动工作流。触发词：启动项目、如何驱动、bootstrap、自举、宿主无关接入、agent 开始工作。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/agent-figure-gallery/SKILL.md · Query the AgentFigureGallery visual reference KB, show candidates for human preference selection, and export selected…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/analyze-results/SKILL.md · Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/anti-ai-detection/SKILL.md · 中文学术文本 AI 特征检测：八维度加八项统计特征分析、AI 味改写建议、改写质量检查，并生成国赛 AI 使用声明。触发词：反AI检测、AI味、去AI化、AI 生成特征、AI 使用声明。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/anti-defensive-writing/SKILL.md · 删减防御性写作：去掉不必要的免责声明、模糊限定、道歉式表述、自我贬低与过度解释，同时保留必要的范围/准确性/安全/法律/伦理/方法学限定。触发词：更简洁、更有力、更直接、更自信、少限定、少免责、别啰嗦、不要过度解释、改掉…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/arxiv-metadata/SKILL.md · Fetch structured metadata for an arXiv paper. Use when you have an arXiv ID or URL and need title, authors, date, or…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/arxiv-submission-package/SKILL.md · Prepare an arXiv submission package from a LaTeX paper. Cleans the source, builds a tarball, and extracts metadata for…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/arxiv/SKILL.md · Search, download, and summarize academic papers from arXiv. Use when user says ”search arxiv”, ”download paper”, or…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/assets-inventory/SKILL.md · 扫描用户上传的资产（题目/代码/数据/图/结果），输出资产清单 ASSETS_INVENTORY.md 与一致性冲突报告 ASSETS_CONFLICTS.md，供后续步骤决定哪些资产已有、哪些需要补全。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/auto-paper-improvement-loop/SKILL.md · 论文自动改进循环（2 轮）：先由外部审稿模型评审，再按要求改稿，最后重编译验证。触发词：改论文、improve paper、论文润色循环、auto improve、迭代打磨论文。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/auto-review-loop/SKILL.md · Autonomous multi-round research review loop: write review task cards, obtain an independent review (any isolated…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/award-paper-mining/SKILL.md · 挖掘获奖论文语料，沉淀为可复用统计与版面资产（采集归档、统计报告、版面蒸馏）。触发词：优秀论文挖掘、获奖论文语料、范文库、award paper mining、历年论文归档、论文统计报告、版面蒸馏、论文套壳、章节骨架、句式模板。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/candidate-reproduction/SKILL.md · 候选交付复现：按引擎生成的复现计划在独立目录重跑候选冻结 recipe，逐目标核对结果并产出复现报告。触发词：候选复现、复现计划、candidate reproduction、冻结 recipe 重跑。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/check-citations/SKILL.md · Verifies citations against CrossRef, Semantic Scholar, and OpenAlex; detects AI-hallucinated references. Use before…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/citation-check/SKILL.md · 引用检查（CUMCM 参考文献质量检查）：格式一致性、GB/T 7714 规范性、引用完整性、来源可信度。触发词：引用检查、参考文献格式、GB/T 7714 规范、citation check；交付前引用终检时使用。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-code/SKILL.md · 数学建模竞赛编程实现。根据建模报告编写代码、执行计算、收集结果。Use when user says "编程", "写代码", "code implementation".

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-compile-en/SKILL.md · Compile English competition paper (MCM/ICM/APMCM) and run compliance checks. Use when user says ”compile MCM…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-compile-zh/SKILL.md · 数学建模竞赛中文论文编译与合规检查。编译 PDF 并检查页数、匿名、格式等竞赛要求。Use when user says "编译竞赛论文", "compile competition paper".

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-consistency/SKILL.md · Use when a competition paper must be checked against canonical results JSON, code outputs, figures, and headline…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-contest-research/SKILL.md · 深度调研（Deep Research for CUMCM）——赛题分析的顶层调研技能。比赛出题后 6 小时内快速吃透题目背景、数据来源、前沿方法、可用工具，为选题决策提供证据。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-cumcm-disclosure/SKILL.md · CUMCM AI 工具使用申报双件套入口：生成/校验《AI工具使用详情》PDF 与正文 AI 使用声明，核对口径一致。触发词：AI 申报、AI工具使用详情、AI 使用声明、disclosure、人工智能工具使用规定、申报四节。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-cumcm-package/SKILL.md · 竞赛提交打包沙演与合规终审入口；口径必须显式选择（国赛 comp_cumcm / 华为杯 comp_huawei），不按文本猜赛事。触发词：竞赛打包、合规终审、提交沙演。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-editor/SKILL.md · Use when a mathematical modeling competition draft needs controlled edits in response to documented reviewer findings…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-final-audit/SKILL.md · 数模竞赛交付前的最终审计：核对证据链、质量检查结论、审稿记录与交付文件，产出可追溯的审计结论。触发词：交付审计、最终审计、AUDIT_REPORT、交付前检查。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-final-review/SKILL.md · Use when a mathematical modeling competition submission requires a final evidence-based re-review after edits and…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-latex-writing/SKILL.md · 国赛 LaTeX 写作（Latex Writing for CUMCM）——数模竞赛论文写作方法技能（公式/表格/算法三件套+摘要页精修）；骨架一律走 comp-paper-zh 主线 _templates，禁止自造 preamble。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-literature/SKILL.md · Use when a math modeling competition workflow needs verified literature research, citation provenance, or a reference…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-model-innovation/SKILL.md · 模型创新辅助专家。提供 3 个核心能力： 1. arxiv + duckduckgo 实时检索前沿方法 2. 查重（避免和历年国一撞方法） 3. 魔改/组合/自创模型的 prompt 模板 【国一价值】25% 权重——创新是国一核心

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-modeling/SKILL.md · 数学建模竞赛核心建模与求解。建立数学模型、推导公式、设计算法。Use when user says "建模", "modeling", "模型建立".

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-paper-en-docx/SKILL.md · English competition paper (MCM/ICM/APMCM), Word docx mode; docx counterpart of comp-paper-en, produces main.md. 区别于…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-paper-en/SKILL.md · Mathematical modeling competition paper writing in English. Supported contests (canonical comp_rules IDs): comp_mcm…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-paper-zh-docx/SKILL.md · 数模竞赛/统计建模中文论文撰写（Word docx 模式），comp-paper-zh 的 docx 对应版，只产出 paper/main.md。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-paper-zh/SKILL.md · 数学建模竞赛/统计建模中文论文撰写。按竞赛规范结构生成完整 LaTeX 论文。Use when user says "写竞赛论文", "competition paper", "建模论文".

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-pipeline/SKILL.md · 数学建模竞赛全流程入口：竞赛任务映射到引擎工作流模板（comp_cumcm、comp_huawei 等），引擎分派步骤并独占流程状态。触发词：数模全流程、完整做一道竞赛题、comp-pipeline、从读题到交付。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-problem-analysis/SKILL.md · 数学建模竞赛赛题分析。拆解子问题、定义变量、拟定建模思路。Use when user says "赛题分析", "problem analysis", "分析题目".

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-review/SKILL.md · 数学建模竞赛逻辑对抗复核：编程实现后、论文撰写前，用独立视角挑方向反/重复计量/外推过硬/漏变量/跨问矛盾等硬错。触发词：逻辑复核、对抗审查、模型审查。Use between comp-code and comp-paper。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-simulation/SKILL.md · 仿真建模主链：方法选型（多智能体/离散事件/系统动力学/连续系统/蒙特卡洛/数据驱动融合）、模型规格化、校准与校核验证、实验设计与重复运行纪律、敏感性分析与不确定性量化、仿真产物契约。用于仿真建模类竞赛（如全国大学生仿真建模应用挑战赛）与仿…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-statistics-topic/SKILL.md · 统计建模大赛选题与数据规划。根据官方主题方向，自拟具体题目、设计研究方案、规划数据来源。Use when user says ”统计建模选题”, ”stats topic”, ”自拟题目”.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/comp-visual-review/SKILL.md · Use when a competition paper or its figures need visual review for readability, clipping, labels, units, and export…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/contest-retrospective/SKILL.md · 赛后/项目后复盘与经验沉淀：从留痕取证分类典型场景、踩坑与交付清单，归因真实强制点，双写经验库并机检闭环。触发词：复盘、赛后总结、经验沉淀、教训清单、事故归因、post-mortem、retrospective、把教训写进项目、避免下届重踩…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/copyright-build/SKILL.md · 软著申请资料成品阶段：读取草稿与检查结果，生成正式的 Word 材料（源代码、操作手册）与申请表信息文本。触发词：软著成品、生成软著材料、软著 Word、操作手册。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/copyright-draft/SKILL.md · 一句话/一段描述/一份大纲 → 起草软件著作权申请资料草稿。AI 直接撰写业务理解、 申请表信息、代码材料（合成可运行的示例源码）、操作手册，并生成模拟页面截图， 产出成品脚本所需的全部草稿与门禁 JSON。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/copyright-source-materials/SKILL.md · 从真实本地项目离线抽取、清洗、分页、审计并导出软著源程序材料。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/course-paper/SKILL.md · 课程论文撰写。基于已生成的大纲（OUTLINE.md）、数据分析（RESULTS.md）、图表（figures/）撰写完整正文并嵌入图片，严格遵守 Claims-Evidence Matrix 与图表/引用闭环自检。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/course-plan/SKILL.md · 课程论文大纲规划。读取用户主题、上传资料，产出大纲、数据分析规划、图表规划，为后续数据分析和正文撰写做准备。Use when starting a course paper workflow.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/course-report-plan/SKILL.md · 课程报告大纲规划。读取项目源码与上传资料，提取项目事实，产出大纲与数据/图表/架构图规划。Use when starting a course report workflow.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/course-report/SKILL.md · 课程报告撰写。基于已生成的项目事实底稿、大纲、数据与架构图撰写完整正文并嵌入图片，严格遵守事实/Claims/图表/引用闭环自检。Use when continuing a course report workflow.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/course-syllabus-reading-list/SKILL.md · Builds a supplementary reading list from a course syllabus (Consensus search, .docx output). Use when expanding a…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-exploratory-analysis/SKILL.md · Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats, with format…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-processing/SKILL.md · Data Processing Skill——把原始数据（CSV/Excel/JSON/爬虫）变成”能直接喂给模型”的干净数据。

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/SKILL.md · Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/references/arc-stat-research/skills/stat-research-orchestrator/SKILL.md · Orchestrate a statistical research pipeline centered on formal problem formulation, method proposal, theoretical…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/references/arc-stat-research/skills/stat-result-validator/SKILL.md · Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/references/arc-stat-research/skills/statistical-experimental-evaluation/SKILL.md · Design and run statistical experiments that test the formal problem, proposed methods, theoretical predictions…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/references/arc-stat-research/skills/statistical-method-design/SKILL.md · Design statistical methods, baselines, diagnostics, variants, and ablations that directly address a formal problem…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/references/arc-stat-research/skills/statistical-problem-formulation/SKILL.md · Formulate statistical research problems with formal notation, target parameters, assumptions, hypotheses, evaluation…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-analyst/references/arc-stat-research/skills/statistical-theory-analysis/SKILL.md · Analyze theoretical properties of statistical methods under the formal formulation: identifiability, bias, variance…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/data-statistics-report/SKILL.md · Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-adversarial-code-review/SKILL.md · Adversarial code review from hostile reviewer personas. Use when a genuinely critical review must break self-review…

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-ai-security/SKILL.md · Use when assessing AI/ML systems for prompt injection, jailbreak, model inversion, data poisoning, or agent tool abuse.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-code-backend/SKILL.md · 一句话生成项目·后端编码。按设计实现后端(FastAPI/Flask/Express)+数据库。Use when 后端编码/写后端.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-code-frontend/SKILL.md · 一句话生成项目·前端编码。按设计实现前端界面(React/Vue/纯HTML)。Use when 前端编码/写前端.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-code-review-guide/SKILL.md · Use when writing review comments, auditing code quality, or establishing team review standards and process.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-code-review/SKILL.md · Automated multi-language code review; detects issues and generates review reports. Use when reviewing code changes.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-code/SKILL.md · 一句话生成项目·编码实现。按设计文档写真实可运行的代码(全栈/纯前端/CLI/脚本)。Use when user says 编码实现/写代码.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-daily-coding/SKILL.md · Use for everyday coding tasks that involve writing or modifying source code.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-debug/SKILL.md · Use when the user asks to ”debug this”, ”fix this error”, ”investigate this bug”, or ”troubleshoot a failure”.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-design/SKILL.md · 毕业设计(软件开发)系统设计。基于需求规格产出架构/数据库/API设计。Use when user says 系统设计/毕设设计.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-frontend-design/SKILL.md · Create production-grade frontend interfaces. Use when the user asks to build or redesign a web UI, page, or component.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-git-workflow/SKILL.md · Use when the user asks to ”create git commit”, ”manage branches”, ”follow git workflow”, or ”use conventional commits”.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-ml-registry-pattern/SKILL.md · Use only when creating new registrable ML components that require Factory or Registry patterns.

fourteen1416/academic-agent-toolkit · academic-toolkit/skills/dev-report/SKILL.md · 一句话生成项目·项目报告撰写。把项目文档+代码+测试整理成毕设风格报告(供编译PDF/导出Word)。Use when 项目报告/写报告.