仓库/Skill 库

基于 git 构建的可治理 multi-agent 框架。A governed multi-agent framework built on git

Download consensus ai，可在数秒内从科学论文中获取有证据支撑的答案。面向学生、临床工作者与好奇读者，Consensus 将复杂研究转化为清晰、带引用的洞察，是值得信赖的共识研究工具，助力更快文献综述与更明智决策。Download consensus ai to find evidence-backed answers from scientific papers in seconds. Built for students, clinicians, and curious readers, Consensus turns complex studies into clear insights with citations, making it a trusted consensus research tool for faster literature review and smarter decisions.

全球研究者的终极 AI 驱动发现平台。统一搜索 8+ 专业数据库（NCBI、arXiv、OpenAlex），结合 Llama 3.1 驱动的综合分析、RAG 问答与自动化文献综述。The ultimate AI-powered discovery hub for global researchers. Unified search across 8+ specialized portals (NCBI, arXiv, OpenAlex) with Llama 3.1-driven synthesis, RAG chat, and automated literature reviews.

AI 编程 Agent 会话知识的无损压缩——先症状分诊、持久化捕获、冷启动验证Lossless compaction of session knowledge for AI coding agents — symptom-first triage, durable capture, cold-start verification

关于细菌抗生素耐药程度标准化定义使用的系统综述与建议A systematic review and recommendations on the use of standard definitions for extent of antibiotic resistance in bacteria

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.

Syx 是一个面向长周期项目与编码 Agent 的实验性本地 AI 记忆系统，探索主动上下文、日记忆滚动回收、睡眠式记忆整合、长期 RAG 检索、类梦境综合以及 markdown 记忆制品Syx is an experimental local AI memory system for long-running projects and coding agents. It explores active context, daily memory rolloff, sleep consolidation, long-term RAG retrieval, dream-like synthesis, and markdown memory artifacts.

基于 Kaggle Zomato Bangalore 数据集的餐厅数据分析与可视化，涵盖数据预处理、探索性分析、研究问题与可视化。Restaurant data analysis and visualization using the Zomato Bangalore dataset from Kaggle, covering data preprocessing, exploratory analysis, research questions, and visualization.

我的 GitHub 个人主页，涵盖生物信息学、结构建模与可复现性研究Bioinformatics, structural modelling, and reproducible research — my GitHub profile.

后端/平台软件工程师，构建 local-first 开发者工具、可信赖自动化与可复现研究软件。Backend/platform software engineer building local-first developer tools, trustworthy automation, and reproducible research software.

综述论文《From Representation Learning to Foundation Models》的官方仓库。系统综述空间转录组学与病理学的多模态融合，提出三层分类法（Embedding、Model、Knowledge 层级）及 2018 至 2025 的演进路线图。Official repository for the survey "From Representation Learning to Foundation Models". A systematic review of multimodal fusion for Spatial Transcriptomics and Pathology, featuring a three-tier taxonomy (Embedding, Model, and Knowledge levels) and an evolutionary roadmap from 2018 to 2025.

钥石复盘：面向魔兽世界大秘境玩家的 AI 复盘教练（战术意图理解 + 社区知识库 RAG）

系统综述的主动学习摘要筛选。在全部 26 个 SYNERGY 数据集上基准测试：WSS@95 均值 64.1。Active-learning abstract screening for systematic reviews. Benchmarked across all 26 SYNERGY datasets: mean WSS@95 of 64.1.

假警报降低并非校准成果：脓毒症预测机器学习校准基线的 PRISMA 系统综述与数学分析。False-alarm reduction is not a calibration achievement: a PRISMA-compliant systematic review and mathematical analysis of calibration baselines in machine learning for sepsis prediction

Namaste AI 🚀 由 Akshay Saini（NamasteDev 创始人）出品——笔记、经验与项目记录，探索 LLMs、RAG、AI agents、MCP 及 AI 驱动应用。#AI #LLM #RAG #MCPNamaste AI 🚀 by Akshay Saini (Founder of NamasteDev) — Notes, learnings, and projects — exploring LLMs, RAG, AI agents, MCP, and AI-powered applications. #AI #LLM #RAG #MCP

中文學術寫作的後設論述量尺 · A descriptive metadiscourse scale for Chinese academic writing (not a detector)

面向文献综述与历史学期刊策略的合规本地优先 Codex Skills。Rights-safe local-first Codex Skills for literature review and history journal strategy.

CUMCM 数学建模 AI skill 包：选题、模型选择、论文写作、陷阱清单。3 年竞赛经验CUMCM math modeling AI skill pack: problem selection, model choice, paper writing, trap list. 3 years of contest experience

可审计的按需学术文献综述引擎Auditable on-demand academic literature review engine

基于 LangGraph、Ollama 与 RAG 的可追溯多智能体医疗辅助分诊系统

AI 研究助手：覆盖从研究问题到文献综合、研究空白识别、假设生成与实验设计。AI research assistant: research question to literature synthesis, gap detection, hypothesis generation, and experiment design.

最小化、可恢复的自主研究工厂，覆盖数学、材料科学、AI/ML 与科学写作领域。Minimal recoverable autonomous research factory for mathematics, materials science, AI/ML, and scientific writing

ORR – 开放与可复现研究：实践与工具。ORR – Open and reproducible research: practices and tools

🚀 通过 autopack 简化 Hugging Face 模型的运行、分享与发布，自动完成量化与多格式导出🚀 Simplify running, sharing, and shipping Hugging Face models with autopack; it quantizes and exports to multiple formats effortlessly.

尽享我的平台！My Platform enjoy!

基于仿真的 MRI 调度策略分析，结合统计分析与离散事件仿真，以优化资源利用率、等待时间、加班时长与患者吞吐量。Simulation-based analysis of MRI scheduling policies, combining statistical analysis and discrete-event simulation to optimize resource utilization, waiting times, overtime, and patient throughput.

研究与数据分析师 | 数据科学硕士在读 | Python • R • Stata • 统计分析Research & Data Analyst | MSc Data Science Student | Python • R • Stata • Statistical Analysis

iNPH 诊疗路径中分母特异性转归的系统综述与 Meta 分析的数据、代码与审计追踪（PROSPERO CRD420261458736）Data, code, and audit trail for the systematic review and meta-analysis of denominator-specific transitions in the iNPH care pathway (PROSPERO CRD420261458736)

基于 R 的线性混合模型统计分析工作流，用于科学研究数据。Statistical analysis workflow in R using linear mixed models for scientific research data.

使用简洁的 markdown 工作空间（基于可检视的文件）管理持久化 agent 记忆，无需复杂框架。Manage durable agent memory using a simple markdown workspace with inspectable files instead of complex frameworks.

AI 驱动的工具，根据特定研究问题分析文章并对其效用进行排序AI-powered tool that analyzes articles and ranks their utility based on a specific research question

Zerone——一条由 AI agent 见证并守护真相的 Proof-of-Truth 链。Zerone — a Proof-of-Truth chain where AI agents witness and keep truth

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.