仓库/Skill 库

Pinakes —— 可移植、Agent 优先的知识库。一个目录即一个 KB。Pinakes — a portable, agent-first knowledge base. One directory = one KB.

von der Heyde, L., Keusch, F., Buskirk, T. D., & Eck, A. (2026). AI in the Loop?! A Systematic Review of the Use of Large Language Models in Survey and Public Opinion Research. SocArXiv. https://doi.org/10.31235/osf.io/eubj4_v1 的复现材料与文献数据库Replication materials and literature databases for von der Heyde, L., Keusch, F., Buskirk, T. D., & Eck, A. (2026). AI in the Loop?! A Systematic Review of the Use of Large Language Models in Survey and Public Opinion Research. SocArXiv. https://doi.org/10.31235/osf.io/eubj4_v1.

Telegram RAG 机器人，以暗黑荒诞的《权力的游戏》谋士风格回答问题；支持英中双语，基于 LLaMA 3.3 70B + Firestore 向量搜索。A Telegram RAG bot that answers your questions as a darkly absurdist Game of Thrones advisor — bilingual (EN/ZH), powered by LLaMA 3.3 70B + Firestore vector search.

一套可移植、可复现的 PRISMA 2020 系统综述流水线：检索 15 个数据库、执行去重、以完整审计追踪管理人工筛选，并根据决策日志计算 PRISMA 流程计数。A portable, reproducible PRISMA 2020 systematic literature review pipeline. Searches 15 databases, deduplicates, manages human screening with a full audit trail, and computes PRISMA flow counts from the decision log.

这个仓库展示了我的技能、项目，以及从数据工程转型为数据科学家角色的持续学习历程。This repository showcases my skills, projects, and continuous learning journey as I transition from Data Engineering to a Data Scientist role.

自动化 n8n 工作流，抓取 LinkedIn 产品经理职位，通过向量相似度与简历匹配打分，并使用 Claude 为每个职位生成简历修改建议Automated n8n workflow that scrapes LinkedIn PM jobs, scores them against your resume with vector similarity, and uses Claude to suggest per-job resume edits.

基于 Neo4j 知识图谱回答生物医学研究问题的多 Agent 系统——采用 LangGraph 编排、图+向量混合 RAG、只读 Cypher 护栏、Docker 隔离的代码执行与人在环上审核。Multi-agent system answering biomedical research questions over a Neo4j knowledge graph — LangGraph orchestration, hybrid graph+vector RAG, read-only Cypher guardrails, Docker-isolated code execution and human-in-the-loop review

🔍 Self-Corrective RAG 基于 LangGraph 与 Google Gemini 优化查询并评估文档相关性，提升检索效果🔍 Enhance your searches with Self-Corrective RAG, a system that optimizes queries and evaluates document relevance using LangGraph and Google Gemini.

基于 .NET 的 RAG 文档摄取流水线 — 追踪 git 备份仓库中的文件夹，提取并分块文件，保持向量索引同步。.NET document ingestion pipeline for RAG — tracks a folder of files in a git-backed vault, extracts and chunks them, and keeps a vector index in sync.

基于你的 Zotero library 的个人论文推荐器。Personal paper recommender based on your Zotero library

为仿制药临床法规事务团队打造的法规准备加速器。A regulatory prep accelerator for a generic-drug Clinical Regulatory Affairs team.

自托管共享记忆，面向 AI Agent 团队。支持房间（Rooms）、L0-L3 层级深度与 MCP；读取路径不调用任何语言模型。基于 vectorize-io/hindsight（MIT）的 fork。Self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. Fork of vectorize-io/hindsight (MIT).

全栈量化研究平台：因子分析、系统化策略回测、真实交易成本建模、滚动前推 ML 验证、投资组合风险分析与稳健性测试，基于美股日频数据。为可复现研究而构建——非实盘交易。Full-stack quantitative research platform for factor analysis, systematic strategy backtesting, realistic transaction-cost modeling, walk-forward ML validation, portfolio risk analytics, and robustness testing on daily U.S. equity data. Built for reproducible research—not live trading.

AI 驱动的每周生活规划器 — 由多供应商 Agent 生成饮食、学习、锻炼、习惯和娱乐方案，并附带每周日程追踪。AI-powered weekly life planner - nutrition, study, workouts, habits and fun generated by a multi-provider agent, with a weekly schedule tracker.

OptiBuild 工程案例研究——一款 AI 驱动的施工现场管理平台：工程量清单解析、成本核算、进度报告与按角色划分的数据权限。Engineering case study of OptiBuild, an AI-enabled construction-site management platform: quantity-survey parsing, costing, work-progress statements and role-scoped data.

Athleta 工程案例研究——一款 AI 健身产品，采用每用户一个知识图谱的设计，由 Agent 提议、用户确认。Engineering case study of Athleta, an AI fitness product with a per-user knowledge graph where the agent proposes and the user confirms.

面向 AI Agent 的学术研究情报——论文检索、科学文献、引用分析、arXiv、作者指标、前沿研究与语义相关工作（pgvector）。支持 MCP + x402。Academic research intelligence for AI agents — paper search, scientific literature, citation analysis, arXiv, author metrics, trending research & semantic related-work (pgvector). MCP + x402.

PostgreSQL MCP 2026：面向开发者的最佳 AI 数据库访问工具PostgreSQL MCP 2026 Best AI Database Access Tool for Developers

面向 AI Agent 的本地网页搜索代理与缓存。兼容 Exa 的 HTTP API + MCP，DuckDuckGo 后端，SQLite TTL。Local web-search proxy and cache for AI agents. Exa-compatible HTTP API + MCP, DuckDuckGo backend, SQLite TTL.

通过硬件 IP 核在硅层级抑制 LLM 幻觉，强制 LLM 输出的语义完整性Enforce semantic integrity in LLM outputs with a hardware IP core that suppresses hallucinations at the silicon level

面向印度诊所的多语言医疗分诊助手—— LangChain + Groq Agent，基于 WHO 症状指南与 ICD-11 的 FAISS RAG，支持英语/印地语/卡纳达语的 Whisper 语音输入，FastAPI + PostgreSQL 后端。提供在线 demo。Multilingual medical triage assistant for Indian clinics — LangChain + Groq agent, FAISS RAG over WHO symptom guides and ICD-11, Whisper voice input in English/Hindi/Kannada, FastAPI + PostgreSQL backend. Live demo.

纯 Go 实现的分布式列式 SQL 分析引擎——对 S3 上 Parquet 进行向量化执行，无需 JVM、无需 CGo。以 Trino 级别的能力提供相当性能，却只需极小资源占用。原生支持 IPv4/CIDR/MAC 等网络类型，适用于遥测和安全场景。Distributed columnar SQL analytics engine in pure Go — vectorized execution over Parquet on S3, no JVM, no CGo. Trino-class performance on a fraction of the footprint. Network-native IPv4/CIDR/MAC types for telemetry and security workloads.

即时评估课程资格，输出明确的通过/未通过结果以及定制化的入学测试。Instantly evaluate course eligibility with clear pass/fail results and tailored entry assessments.

将研究压缩包转化为可搜索、可引用的素材。拆分为论文、代码与数据集，索引后即可提出 Deep Research 问题，并引用页码与源行。Self-hosted（Postgres、MinIO、Qdrant）。Turn research zips into searchable, citable materials. Split papers, code, and datasets; index them; ask Deep Research questions that cite pages and source lines. Self-hosted (Postgres, MinIO, Qdrant).

面向基于丙泊酚的 ICU 镇静的计算数字孪生：SQL 数据提取、特征工程、消融实验和论文图表。Computational digital twin for propofol-based ICU sedation: SQL extraction, feature engineering, ablation experiments, and publication figures.

为 coding agent 提供并行、隔离的本地环境——基于 git worktree + 容器，每个 bay 拥有独立端口、hostname 和数据库，可通过 CLI 或 MCP 驱动。Parallel, isolated local environments for coding agents — git worktree + containers + per-bay ports, hostname and database, driven by CLI or MCP.

受治理的 Data Agent：基于 OpenMetadata，针对 Fabric、PostgreSQL 等的自然语言查询。每次查询经过双重鉴权——服务端的角色规则，再以调用者自身身份由引擎执行。任意 MCP 客户端无需修改即可对接真实 Azure。A governed Data Agent: natural-language questions over Fabric, PostgreSQL and more, grounded in OpenMetadata. Each query is authorized twice — role rules in the service, then the engine under the caller's own identity. Any MCP client, unchanged against real Azure.

基于 3,377 篇 arXiv 预印本的混合搜索与有依据问答，并附带若检索质量回退则失败 CI 的检索消融实验。Hybrid search and grounded question answering over 3,377 arXiv preprints — with a retrieval ablation that fails CI if quality regresses.

2026 年面向 AI 代码生成的 PostgreSQL 优化终极指南。The Ultimate guide to PostgreSQL Optimization for AI Code Generation in 2026

2026 掌握 LLM 搜索：完整的语义 AI 手册Master LLM Search in 2026: The Complete Semantic AI Handbook

一款全栈应用，通过 Chrome 扩展自动捕获求职申请，在统一面板中跟踪记录，并提供洞察以优化求职流程。A full-stack application that automatically captures job applications through a Chrome extension, tracks them in a centralized dashboard, and provides insights to improve your job search.

拥有持久记忆的终端 AI 角色扮演客户端 —— 本地 SQLite、语义召回以及每次调用的成本统计。兼容 OpenAI，已在 OpenRouter 上测试。A terminal AI roleplay client with a memory that does not forget — local SQLite, semantic recall, and what every call cost. OpenAI-compatible, tested on OpenRouter.

可衡量的 Agent 分诊：判断一次编辑是否需要人工，还是可由 AI 处理。我们衡量 Agent 下方的图能否触达守住变更的测试（7 个仓库合并值 0.42），并发布 fail-closed 闸门，将未经证明的映射路由到人工核验。CLI · MCP · SARIF · 内置于 HydraDB。Agent triage, measured: does this edit need a human, or can the AI handle it? We measure whether the graph under the agent can reach the tests that guard a change (0.42 pooled, 7 repos) and ship the fail-closed gate that routes unproven maps to human verification. CLI · MCP · SARIF · in-engine on HydraDB.

基于 LLM 的 AI 研究 Agent：检索 arXiv、生成假设，以及一个能够拒绝自身输出的 Critic Agent。支持通过 Ollama 在本地运行，或使用 Anthropic API。LLM-backed AI research agent: arXiv retrieval, hypothesis generation, and a Critic agent that can reject its own output. Runs locally with Ollama or via the Anthropic API.

自包含的系统综述工作台——多库检索、双评审筛选、AI 辅助批判性评价（RoB 2、ROBINS-I、GRADE…）。单 HTML 文件，无后端，数据不离开浏览器。Self-contained systematic review workbench — multi-database search, dual-reviewer screening, AI-assisted critical appraisal (RoB 2, ROBINS-I, GRADE…). One HTML file, no backend, data never leaves your browser.

基于书签或主题推荐 arXiv 论文的 AI AgentAI agent that recommends arXiv papers based on bookmarks or topics.