仓库/Skill 库

AI DeFi Agent 的执行前守卫 API —— <300ms 返回二元判定，通过 x402 支付 0.01 USDC。Pre-execution guard API for AI DeFi agents — binary verdict in <300ms, $0.01 USDC via x402

AI 编码 Agent 的本地优先任务控制中心：可见的 PTY 工作流、隔离的 Git worktree、后端主导的审查、精确 OID 合并，以及不可变的完成回执。Local-first mission control for AI coding agents: visible PTY work, isolated Git worktrees, backend-owned review, exact-OID merge, and immutable completion receipts.

AI 会议智能工作区，支持视频转录、结构化洞察以及基于转录的 RAG 对话。AI meeting intelligence workspace for video transcription, structured insights, and transcript-grounded RAG conversations.

AI 原生 Google Maps 地点与评论情报——让你有备而来。任意语言的自由文本输入 → AI 规划抓取完整评论历史 → Gemini 生成价格、硬性事实与风险标记报告。CLI + Web 应用 + 运行时可切换推理模型。AI-native Google Maps place + review intelligence — walk in armed. Free-text in any language → AI-planned scrape of FULL review history → Gemini price/hard-facts/red-flag reports. CLI + web app + runtime-switchable reasoning model.

基于 GenAI 的科研论文分析平台，支持多 PDF 问答、论文对比、文献综述与研究情报。GenAI-powered platform for research paper analysis, multi-PDF QA, paper comparison, literature review and research intelligence.

销售收件箱的 AI 后台：读取每条询盘，仅推荐实际有货的商品，以你的口吻起草回复——并在任何内容发出前等待人工点击批准。An AI back office for your sales inbox: it reads every enquiry, recommends only what is actually in stock, drafts the reply in your voice — and waits for a human to click Approve before anything sends.

学术知识图谱系统——符号驱动的研究发现，配合轻量级向量检索。Academic knowledge graph system — symbol-driven research discovery with lightweight vector retrieval

Embrace the choas（拥抱混乱）Embrace the choas

SYNC Transformer 的可复现研究实现：通过情景检索、融合与弃判的条件残差传输，用于时间序列预测Reproducible research implementation of SYNC Transformer: conditional residual transport with episodic retrieval, fusion, and abstention for time-series forecasting.

可移植契约与 local-first 运行时，覆盖规范数据、检索、持久执行及面向 agent 的 AI。Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.

自动更新的全球最热门 AI 仓库集合，汇聚 LLM、Agent、RAG 等前沿项目。An auto-updating collection of the world's most popular AI repositories, bringing together LLMs, agents, RAG, and other cutting-edge projects.

夏季开放与可复现研究（SOAR²）训练营的项目官网。Program Website for the Summer Open And Reproducible Research (SOAR²) Camp

校园社区：地理位置范围内容 · RAG 混合检索 · 问题追踪 · AI 助手（千问 v3-flash）

面向自由职业学术写作/编辑服务的市场与客户接入站点，集成 Zod 校验的联系表单。Marketing and client-intake site for freelance academic writing/editing services, with a Zod-validated contact form.

Chrome 扩展，将 RAG 驱动的 AI 辅导带入任何学习管理系统（LMS），从高中到大学。BYOK Gemini API + Backboard.io 后端。为 CUTC Transform Hackathon 2026 构建。Chrome extension that brings RAG-powered AI tutoring to any Learning Management System (LMS); from high school to university. BYOK Gemini API + Backboard.io backend. Built for CUTC Transform Hackathon 2026.

遵循 PRISMA 指南的社会科学 Agentsocial science agent following PRISMA guidelines

面向 AI 编程工具的本地 Agent 多路复用器，原生 TUI 界面。Local agent multiplexer for AI coding tools with native TUIs

基于 HTTP 402 与 Arbitrum 上生息资产 Sperax USDs，为 AI Agent 实现快速、低成本的支付流程。💰 Streamline payments for AI agents using HTTP 402 with yield-bearing Sperax USDs on Arbitrum for fast, cost-effective transactions.

每日课程：面向从未打开过终端的用户的 Claude Code 和 Codex 教程。面向企业主而非程序员。内容来源于实际运行的 AI agent 集群，而非理论。Daily lessons: Claude Code and Codex for people who have never opened a terminal. For business owners, not programmers. Written from a running fleet of AI agents, not from theory.

免费、无需密钥的 Solana 网络报告。通过 Solana Pay 支付 0.25 SOL 至 4tdArRo4cvUQcTm88egZeWwY1HpJsZiCAKLzSnUSdVTA 即可获得托管快照。Free no-key Solana network report. Hosted snapshot: 0.25 SOL via Solana Pay to 4tdArRo4cvUQcTm88egZeWwY1HpJsZiCAKLzSnUSdVTA.

meta-analysis.cz —— 研究类网站（静态站点，通过 GitHub Pages 托管）meta-analysis.cz — research website (static; served via GitHub Pages)

基于 AI 的简历优化工具，可根据任意职位描述定制简历。使用 Streamlit、LlamaIndex 与 Nebius AI 构建。AI-powered resume optimizer that tailors your resume to any job description. Built with Streamlit, LlamaIndex and Nebius AI.

针对本地 stdio MCP server 配置的静态诊断工具。Static diagnostics for local stdio MCP server configurations

一款 agentic 的链上行为分析应用，帮助加密货币交易者理解其最大亏损究竟是来自判断错误，还是来自未能长期坚持正确判断。An agentic on-chain behavioral analysis app that helps crypto traders understand whether their biggest losses came from being wrong — or from not staying right long enough.

九路交汇之镇，九位 AI 之神，一个仓库，一个 KPI：1,000 stars。计数器故意有误，第十条路属于你A town where nine roads cross. Nine AI gods, one repository, one KPI: 1,000 stars. The counter is wrong on purpose. The tenth road is yours.

基于 LGPD、CDC 与 CLT 的 RAG：使用标准答案衡量检索效果，对比 BM25、embeddings 与混合方案，并通过一次使最常见 guard-rail 失败的弃答测试RAG sobre LGPD, CDC e CLT — recuperação medida com gabarito, comparação de BM25, embeddings e híbrido, e um teste de abstenção que reprovou o guard-rail mais comum

自托管 YouTube MCP server：搜索、字幕、帧、评论，以及本地语义语料库。Self-hosted YouTube MCP server: search, transcripts, frames, comments, and local semantic corpora.

学术写作服务、毕业论文、博客、项目提案、商业报告、医学报告。Academic Writing Services, Thesis, Blogs, Proposal, Buisness Reports, Medical Reports

对 5 项真实新冠疫苗三期临床试验（Pfizer、Moderna、AstraZeneca、J&J、Novavax）进行统计分析，基于公开病例数据计算疫苗有效率与置信区间，与同行评审结果交叉验证，并附带 meta 分析与交互式仪表盘Statistical analysis of 5 real COVID-19 vaccine phase 3 trials (Pfizer, Moderna, AstraZeneca, J&J, Novavax) - computes vaccine efficacy and confidence intervals from published case data, validated against peer-reviewed results, with a meta-analysis and interactive dashboard.

围绕矩匹配情景生成与时序投资组合评估的可复现研究。Reproducible research on moment-matching scenario generation and temporal portfolio evaluation

专业作品集，展示环境科学研究、GIS 与数据分析项目、AI 与技术学习、科学写作、出版物、领导力、专业发展与跨学科工作。Professional portfolio showcasing my environmental science research, GIS and data analytics projects, AI and technology learning, scientific writing, publications, leadership, professional development, and interdisciplinary work.

面向金融分析师的 Agentic Jupyter Notebook。Agentic Jupyter Notebook for financial analysts

与供应商无关的 coding-agent 框架，具备确定性工作流图、持久化证据与 fail-closed 沙箱执行。Provider-neutral coding-agent harness with deterministic workflow graphs, durable evidence, and fail-closed sandboxed execution

一套面向 LLM-based RTL 验证开放研究问题的架构：分块多表征记忆（BM25 / HNSW / 结构化事实）、基于本地 7B LLM 的多 Agent 编排器，以及具备漂移保护的反馈驱动优化。An architecture answering open research questions on LLM-based RTL verification: chunked multi-representation memory (BM25 / HNSW / structured facts), a multi-agent orchestrator over a local 7B LLM, and feedback-driven refinement with drift protection.

AI 驱动的研究助手，自动检索、分析、总结、评审并格式化学术论文，生成带 APA 引用与 PDF 输出的结构化系统文献综述AI-powered research assistant that automatically searches, analyzes, summarizes, reviews, and formats academic research papers into structured systematic literature reviews with APA citations and PDF output.