仓库/Skill 库

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.

metaScreener——基于插件的桌面应用，用于 human-in-the-loop systematic literature screening。在顺序可审计的 pipeline 中结合确定性启发式过滤与 LLM 推理，通过 SHA-256 校验包实现完全可复现。MIT 协议。metaScreener — a plugin-based desktop application for human-in-the-loop systematic literature screening. Combines deterministic heuristic filters with LLM inference in a sequential, auditable pipeline. SHA-256 verified bundles for full reproducibility. MIT licensed.

多阶段气候声明检索与排序：BM25、稠密 ANN、融合、重排序与评估Multi-stage climate claim retrieval and ranking: BM25, dense ANN, fusion, reranking, and evaluation

研究问题与暂定方向Research Question and Provisional Lane

Give pure-text LLM agents eyes: zero-dependency image understanding, OCR & image Q&A via MCP server + standalone Python script. 给纯文本 AI Agent 的图片理解能力(看图/OCR/图片问答)。

用于文献与系统综述的 AI agent 流水线，对齐 PRISMA 2020、Cochrane 与 GRADE。默认无需密钥（OpenAlex/CrossRef + 标准库）；在 LLM 薄弱处设人工把关。An AI-agent pipeline for literature and systematic reviews, aligned with PRISMA 2020, Cochrane, and GRADE. Keyless by default (OpenAlex/CrossRef + stdlib); human-gated where LLMs are weak.

Linux 上的便携 GrokBuild overlay：18 个 skill、路由、MCP、hooks、Refero/Motionsites 设计库，以及可选的本地 Design Intelligence 目录。当前版本：v1.3.1。Portable GrokBuild overlay for Linux: 18 skills, routing, MCP, hooks, Refero/Motionsites design bank, and optional local Design Intelligence catalog. Current: v1.3.1.

Measured by Nova：本地空间重建 MCP server，用于构建物理上精确的 Blender 模型。Measured by Nova: local spatial reconstruction MCP server for physically accurate Blender models.

由机器强制执行的 AI Agent 前端 UI/UX Skill 包。注册表 + 懒加载：2,018 token 的路由在每次请求中从 334k token 深度内容中按需加载一个 Skill。包含 11 个发布阻塞闸门，其中一项用于校验 Skill 包自身文档与参考资料是否遵循其规则。Machine-enforced frontend UI/UX skill pack for AI agents. Registry + lazy loading: a 2,018-token router loads one skill per request out of 334k tokens of depth. 11 release-blocking gates, including one that checks the pack's own docs and reference material against its own rules.

Kosli API 的 MCP server——由目录驱动，兼容 Claude Code、Claude Desktop 及任意 MCP 客户端。MCP server for the Kosli API - catalog-driven, works with Claude Code, Claude Desktop, and any MCP client.

对接日本 gBizINFO 企业信息 REST API v2 的 MCP serverMCP server for Japan’s gBizINFO corporate information REST API v2.

用于搜索与检索日本官方 e-Stat 政府统计数据的 MCP serverMCP server for searching and retrieving Japan’s official e-Stat government statistics.

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.

多 Agent 开发的可调度性编译器 —— 观察真实代码边界、重构冲突接缝、重新编译计划以实现并行执行。Schedulability compiler for multi-agent development — observe real code boundaries, refactor the conflicting seam, recompile the plan for parallel execution

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.

一个使用 OpenAI function calling 和 DuckDuckGo 搜索的网络搜索与研究问题回答 AI Agent。An AI agent that searches the web and answers research questions using OpenAI's function calling and DuckDuckGo search.

Thesis Helper：面向学术研究的自动化统计分析 Web 应用。上传数据集即可即时生成描述性统计、相关性分析、回归和 t 检验，无需编写代码。Thesis Helper: An automated statistical analysis web app for academic research. Upload your dataset and instantly generate descriptive stats, correlations, regressions, and t-tests without coding.

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.

使用自然语言查询分析并比较 700+ DeFi 金库的风险评分，无需 API key 或安装Analyze and compare risk scores of 700+ DeFi vaults using natural language queries without requiring API keys or installations.

AI 产品运营的可复现研究流水线与案例研究，包含一个自动验证产品证据声明的 Agent。"A reproducible research pipeline and case study for AI Product Operations, featuring an automated agent that verifies product evidence claims."

面向证据治理的化学文献综述 Agent skill。Agent skill for evidence-governed chemical literature reviews

Journal Finder API——数据科学家面试作业题Journal Finder API - Data Scientist Interview Assignment

开发一个研究论文推荐系统，分析关键词、摘要、引用与用户兴趣以推荐相关论文。该系统使用图算法、相似度排序和优化技术，为研究者和学生提供个性化建议。Here's a version with **exactly 300 characters**: > Develop a research paper recommendation system that analyzes keywords, abstracts, citations, and user interests to recommend relevant papers. It uses graph algorithms, similarity ranking, and optimization techniques to deliver personalized suggestions for researchers and students.

🛠 通过此硬件插件提升 vLLM 在 Kunlun XPU 上的性能，无缝集成主流 AI 模型并优化执行效率🛠 Enhance vLLM performance on Kunlun XPU with this hardware plugin, offering seamless integration for popular AI models and optimized execution.

🧪 实验性本地优先 RAG，附带桌面 GUI：将文档拖入文件夹即可对话聊天，内置 Ollama / fastembed / OCR / reranker。🧪 Experimental local-first RAG with desktop GUI — drop documents in a folder, chat with them. Ollama / fastembed / OCR / reranker built in.

部署并运行本地 RAG 实例Deploy and run a local RAG instance

使用部署在 streamlit 上的 MCP server 构建的旅行 Agent。A Travel Agent Built using a MCP server which is deployed in streamlit

系统综述与 Meta 分析的检索、提取与分析代码，主题为基于可穿戴设备生命体征的被动认证。Retrieval, Extraction and Analysis Code for a Systematic Review and Meta-Analysis on Passive Authentication using Vital Signs Collected Via Wearable Devices

John Harper 的学术写作。Academic Writing of John Harper

可执行真实操作的 AI agent 层级——shell、GitHub、邮件、采购——以代码编写（非配置）的审批底线（Latch）作为门槛。零依赖。A hierarchy of AI agents that take real actions — shell, GitHub, email, purchases — behind an approval floor written in code, not configuration (Latch). Zero dependencies.

面向天线与相控阵 PCB 的设计编译器：输入 YAML 规格，输出综合布局、KiCad DRC 校验与 openEMS 全波验证。核心为确定性 Python 实现，可通过 MCP 被 Agent 调用。Design compiler for antenna and phased-array PCBs: YAML spec in, synthesized layout, KiCad DRC, and openEMS full-wave verification out. Deterministic Python core, agent-ready via MCP.

可移植的学术写作技能与跨 Agent 工作流系统。可见性：私有Portable academic writing skills and cross-agent workflow system Visibility：Private

一个 multi-agent 流水线，将研究问题转换为可直接播放的播客——生成双主持人 MP3 以及 AI 生成的单集封面图 🎙️A multi-agent pipeline that turns a research question into a ready-to-play podcast — a two-host MP3 plus AI-generated episode cover art 🎙️

🔍 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.

自托管的个人上下文服务器 — 你与 AI Agent 共享统一的知识与信任边界：知识库、检索、凭证与 Agent 记忆，通过 MCP 挂载Self-hosted personal context server — one knowledge and trust boundary shared by you and your AI agents: knowledge base, retrieval, credentials, and agent memory, mounted over MCP