仓库/Skill 库

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)

中文论文助手：有证据边界的协作式中文学术写作 Skill

本地优先的 CLI，用于评估 MCP server 的开销与能力，数据不离开本机。A local-first CLI that measures what an MCP server costs and what it can do. Nothing leaves your machine.

一个可复用的 skill，用于对临床研究、系统综述和 meta-analyses 进行严谨且有来源支持的评估与分析。A reusable skill for rigorous, source-backed appraisal and analysis of clinical studies, systematic reviews, and meta-analyses.

命令行本地优先的单用户通用 Agent。Local-first, single-user general agent for the command line.

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

本数据分析报告研究多种因素与睡眠质量的关系，旨在回答：1) 不同年龄群体的睡眠质量关联因素是否存在差异？2) 职业对睡眠质量的影响程度如何？This data analysis report investigates the relationships between various factors and sleep quality, aiming to answer the following research question: 1) Do the factors associated with sleep quality differ among different age groups? 2) To what extent is occupation associated with sleep quality?

IntentCoding 官方实现：放大代码生成中的用户意图（ACL 2026）Official implementation of IntentCoding: Amplifying User Intent in Code Generation (ACL 2026)

将真实世界的研究问题转化为带引用、可关联的 Snowflake 表。Turn real-world research questions into cited, joinable Snowflake tables.

为更好的 AI 研究问题梳理清晰的来源、主张、变更与权衡路径Calm source, claim, change, and tradeoff paths for better AI research questions

HCIFlow 是一个 HCI 研究平台，将以单一流水线替代 Gorilla/Qualtrics/Prolific/SPSS 工具链：研究设计、协作、数据采集以及 AI 生成的结果与统计分析（卡方、Mann-Whitney U、Kruskal-Wallis）。基于 Next.js 14、Tailwind、Supabase 和 Claude API 构建。HCIFlow is an HCI research platform that will replaces the Gorilla/Qualtrics/Prolific/SPSS toolchain with a single pipeline: study design, collaboration, data collection, and AI-generated result and statistical analysis (chi-square, Mann-Whitney U, Kruskal-Wallis). Built with Next.js 14, Tailwind, Supabase, and the Claude API.

用于实践可复现研究规范的练习项目。A project to practice reproducible research partices

研究问题：流动性金融资产的相关性与波动率随时间有多稳定？常用的高斯性质在真实市场数据中是否成立？Research Questions: How stable are correlations and volatility over time in liquid financial assets? Do commonly assumed Gaussian properties hold for real market data?

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

针对 umat 学生 COVID-19 疫苗接种的本科生科研项目，采用统计分析方法。Undergraduate research project on COVID-19 vaccination among umat students using statistical analysis

ABCD Study 屏幕媒介出版物的系统综述：检索、筛选与效应量审计。Systematic review of ABCD Study screen media publications: search, screening, and effect size audit

基于 Semantic Scholar 与 Crossref 的安全加固、双模式学术搜索工作台。A security-hardened, dual-mode scholarly search workbench powered by Semantic Scholar and Crossref.

MCU 串行调试桥：过滤视图、图表、标记、Web UI，以及面向 AI Agent 的 CLI。Serial debug bridge for MCUs: filtered views, graphs, markers, web UI, and a CLI for AI agents

An AI-assisted scientific research tool for exploring literature, extracting evidence, and structuring research questions.

一款简易的 GUI 工具，利用 AI 从 PDF 中系统性地提取数据，以辅助荟萃分析与系统综述。A simple GUI tool to systematically extract data from PDFs to assist in meta-analysis and systematic reviews using AI

开源、原生支持 Claude 的文献综述工作流工具：支持 arXiv/DOI/URL/PDF 论文导入、章节抽取，并通过 paper-qa 实现单篇论文问答Open-source, Claude-native literature-review workflow tool: arXiv/DOI/URL/PDF paper ingest, section extraction, single-paper Q&A via paper-qa.

本仓库包含用于系统综述和 meta 分析的全部代码，数据来自用 IMU 数据构建 ML 模型预测帕金森症状的论文。This repository contains all the codes used to systematically review and meta-analyse the data reported in papers where ML models have been built to predict Parkinson's symptoms using IMU data.

可复现研究仓库，用于复现并扩展 Maio 与 Santa-Clara 关于短期利率创新、货币体制与股票市场异象的研究。Reproducible research repo for replicating and extending Maio and Santa-Clara on short-rate innovations, monetary regimes, and stock-market anomalies.

分析葡萄牙公共养老金体系历史融资的可复现研究包Reproducible research package analyzing the historical financing of Portugal's public pension system

使用 Kaggle 数据集分析屏幕时间对生产力多方面影响的研究问题This uses a dataset from Kaggle, to analyze multiple research questions on how screen time affects productivity in multiple aspects.

面向可靠 AI 辅助工作的、人主导、模型无关的操作系统契约与 Markdown 模板。Human-controlled, model-agnostic operating contracts and Markdown templates for reliable AI-assisted work.

记录阅读路径的 PDF 阅读器——支持精确定位的返回/前进、分支浏览以及 git 友好的会话文件。A PDF reader that remembers how you got where you are - reading trails with exact-position back/forward, branching, and git-friendly session files

用于系统综述中识别、量化、验证与可视化作者重叠的 Python 工作流。可生成研究级网络图、连通分量、重叠比例、可审计的边表以及可直接发表的图表，便于透明报告。Python workflow for identifying, quantifying, validating, and visualizing author overlap among studies included in a systematic review. Generates study-level networks, connected components, overlap percentages, auditable edge tables, and publication-ready figures for transparent reporting.

本项目根据用户检索与数据集中已有论文进行论文推荐This project recommends paper based upon your search and available papers inside the dataset

科学写作作品集，涵盖医学检验科学、分子生物学、抗微生物耐药、分子诊断、基因组学、生物信息学与计算生物学。A scientific writing portfolio exploring medical laboratory science, molecular biology, antimicrobial resistance, molecular diagnostics, genomics, bioinformatics and computational biology.