仓库/Skill 库

Minh Phan 作品集：机器学习系统、计算机视觉、可复现研究与软件工程Minh Phan portfolio: ML systems, computer vision, reproducible research, and software engineering.

🌐 使用 LangExtract 无缝从文本中提取语言，简化语言检测，为项目提供便捷且高准确率的增强。🌐 Extract languages from text seamlessly using LangExtract. Simplify language detection and enhance your projects with ease and accuracy.

免费开源的零代码桌面应用，用于系统综述与 Meta 分析（PRISMA 2020）。Tauri + React + C# 引擎，支持 Windows、macOS、Linux。Free, open-source, no-code desktop app for Systematic Reviews & Meta-Analyses (PRISMA 2020). Tauri + React + C# engine — Windows, macOS, Linux.

Codex Skill：学术期刊 rebuttal 与修改工作流Codex skill for academic journal rebuttal and revision workflows.

对我的第一个 agentic 的测试Test of my first agentic

确定性研究亲和度匹配、文献空白发现（Ω 指数）、跨学科共同作者雷达，以及不产生生成式幻觉的逐字引文证据审计。Deterministic research affinity matching, literature white-space discovery (Ω index), cross-disciplinary co-author radar, and verbatim citation evidence auditing without generative hallucinations.

系统综述《Techniques for Adapting Large Language Models to Low-Resource, Morphologically Rich Languages》的补充材料。Supplementary materials for the systematic review: Techniques for Adapting Large Language Models to Low-Resource, Morphologically Rich Languages

基于 Next.js、FastAPI 和 Supabase 的 AI 辅导应用。上传 PDF 与 URL，即可生成结构化摘要、多轮对话和自定义测验。自定义主题通过 Wikipedia、ArXiv 和 DuckDuckGo 进行联网搜索，以生成测验并围绕主题展开对话。Next.js AI tutor with FastAPI and Supabase. Upload PDFs and URLs to generate structured summaries, multi-session chat, and custom quizzes. Custom topics use web search through Wikipedia, ArXiv, and DuckDuckGo to generate quizzes and chat about the topic.

在 VS Code 中构建 AI 辅助的科研工作流：文献综述、引用追踪与可发表级导出Build AI-assisted scientific research in VS Code with literature review, citation tracking, and publication-ready export

面向 LLM agent 的 MCP server，用于加拿大调整后成本基础（ACB）与资本利得：支持平均成本法与 superficial-loss 检测。MCP server for Canadian adjusted cost base (ACB) and capital gains: average-cost, superficial-loss detection, for LLM agents.

NEXORA 的黑客松团队仓库 - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:nexora]Hackathon team repository for NEXORA - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:nexora]

Codiacs 黑客松团队仓库 - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codiacs]Hackathon team repository for Codiacs - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codiacs]

CodeByte 黑客松团队仓库 —— [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codebyte]。Hackathon team repository for CodeByte - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codebyte]

Codex skill，面向交通运输与低空出行领域的学术写作（知识蒸馏自 LT）。Codex skill for transportation and low-altitude mobility academic writing (Knowledge distillation from LT)

适用于 DeepSeek、Qwen、GLM 及多种 AI 模型的 OpenAI 兼容 API 示例。OpenAI Compatible API examples for DeepSeek, Qwen, GLM and multiple AI models.

Local-first 可视化任务图，使人类与 AI Agent 在目标、进度、推理与下一步行动上保持对齐。Local-first visual task graph that keeps humans and AI agents aligned on goals, progress, reasoning, and the next action.

隐私优先的本地 Web 研究 MCP server，集成 SearXNG、隔离 Tor 路径、证据抽取、排序与精确引用。Privacy-first local web research MCP server with SearXNG, isolated Tor paths, evidence extraction, ranking, and exact citations.

ENGR 820 文献综述ENGR 820 literature review

Great Assignment Help 提供的学术写作资源，涵盖作业规划、论文结构、研究技巧、引用指南与学习策略，旨在提升学术写作能力并提供实用学习支持。Academic Writing Resources by Great Assignment Help offers practical guidance for students, including assignment planning, essay structure, research tips, referencing help, and study strategies. It aims to improve academic writing skills and provide useful learning support resources.

一个真实场景下的多能力 AI Agent，可接收用户的研究问题，自主决策所需信息，调用工具/MCP，分析信息并产出结构化报告。A real world multi capability AI agent that can take a user's research question, decide what it needs, use tools/MCP, analyze information, and produce a structured report.

面向多源检索、证据抽取与带引用研究摘要的自主 AI 研究助手。Autonomous AI research assistant for multi-source retrieval, evidence extraction, and cited research summaries.

GoVail MCP —— 用于 GoVail 平台集成的 Model Context Protocol server 与工具。GoVail MCP — GoVail 플랫폼 연동을 위한 Model Context Protocol 서버 및 도구

中文论文助手：有证据边界的协作式中文学术写作 Skill

学术 PDF 阅读器：在浏览器中并排展示印刷版页面与重排阅读视图，由同一模型解析并联动。An academic PDF reader: the printed page and a reflowed reading view, side by side, linked by one model parsed in your browser.

基于 C/Python 的 ML 算法ML algo on C/Python

用于探索 LLM Security 新兴研究主题的研究路线图与文献综述仓库。A research roadmap and literature review repository for exploring emerging research topics in Large Language Model Security.

Radiopaedia cite（用户脚本）——文章编辑器工具栏中的引用选择器：输入即可引用文章已有的参考文献，或粘贴 DOI/PMID 自动查询并添加为下一条编号引用，同时完成插入引用Radiopaedia cite (userscript) — a citation picker in the article editor's toolbar: type to cite a reference the article already has, or paste a DOI/PMID and it is looked up, added as the next numbered reference, and cited in the same press.

RISE Collective 是一个学术、研究、创新与专业咨询平台，支持学生、研究人员、学者和职业发展者。服务包括研究 & 发表、咨询 & 职业、项目 & 创新、学术写作、图书出版、留学支持与知识产权服务。RISE Collective is an academic, research, innovation, and professional advisory platform supporting students, researchers, academics, and aspiring professionals. Services include research & publication, consulting & careers, projects & innovation, academic writing, book publishing, study abroad support, and intellectual property services.

在真实 MCP 客户端上对 Remote MCP 服务器进行实时互操作性测试。Live interoperability testing for Remote MCP servers across real MCP clients.

本地优先的研究论文工作空间与可视化 AI Agent 工作流构建器Local-first research paper workspace and visual AI agent workflow builder

面向 AI Agent 调试 Android React Native/Expo 应用的本地运行时可观测性桥接层——以证据为先：截图、UI 树、逐请求网络数据、FPS、React 渲染、CDP console/heap/profile、确定性诊断、前后对比。Local runtime observability bridge for AI agents debugging React Native/Expo apps on Android — evidence-first: screenshots, UI trees, per-request network, FPS, React renders, CDP console/heap/profile, deterministic diagnosis, before/after compare.

面向本地学术文档研究：用户对多篇PDF/Markdown论文提问，Agent自主决定检索范围、读取文本/页面/图表证据、判断证据是否充分并生成带引用回答；过程实时可看、结果可离线评测。

一个独立开发的板块轮动预测项目，2026 年重构为含回顾性方法学审计的可复现研究工具包An independently developed sector-rotation forecasting project, rebuilt in 2026 as a reproducible research toolkit with a retrospective methodological audit.