仓库/Skill 库

2026 年开发者必备的 7 款最佳 AI 调试工作流插件——更快修复你的代码7 Best AI Debugging Workflow Plugins for Developers in 2026 – Fix Your Code Faster

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)

一次查询，覆盖全部学术数据库；每次运行归档井然有序。跨 OpenAlex、ADS、arXiv、INSPIRE、Scopus、Semantic Scholar、Crossref 与 WoS 的可复现、合规文献检索One query. Every scholarly database. A tidy archive of every run. Reproducible, ToS-compliant literature search across OpenAlex, ADS, arXiv, INSPIRE, Scopus, Semantic Scholar, Crossref and WoS.

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

面向精确 MCP 能力发现、有界调用与提供者效应验证的 Agent Skill。Agent Skill for exact MCP capability discovery, bounded invocation, and provider-effect verification

ResearchIQ Copilot 是一款 AI 驱动的学术研究助手，允许用户与研究论文对话、生成文献综述、识别研究空白、对比方法论、发现经核验的同行评审研究，并将研究成果导出为 PDF 报告ResearchIQ Copilot is an AI-powered academic research assistant that allows users to chat with research papers, generate literature reviews, identify research gaps, compare methodologies, discover verified peer-reviewed studies, and export research outputs as PDF reports.

使用 vision-language model 处理视觉与文本数据，执行多模态推理与图像理解任务。Process visual and textual data with this vision-language model for multimodal reasoning and image understanding tasks.

EconOps：面向经济学实证研究的透明、可复现研究工作流EconOps is a reproducible research workflow for transparent empirical work in economics.

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.

开源数字全息显微镜（DHM）工作站：离轴全息重建、定量相位成像、自动对焦，以及基于经典 + CNN 混合管线的无参考相位检索。PySide6 GUI，可选 Apple Silicon MLX 加速，并提供面向 AI Agent 的 MCP server。Open-source digital holographic microscopy (DHM) workstation: off-axis hologram reconstruction, quantitative phase imaging, autofocus, and reference-free phase retrieval via a hybrid classical + CNN pipeline. PySide6 GUI, optional Apple Silicon MLX acceleration, and an MCP server for AI agents.

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?

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG, citation (GB/T 7714), knowledge graph.

ZN 十年期国债期货与 6E 欧元外汇期货日内 VWAP 均值回归的系统研究，包括数据验证、统计分析、回测、Monte Carlo 模拟与实盘部署。Systematic research on intraday VWAP mean reversion in ZN Treasury and 6E Euro FX futures, including data validation, statistical analysis, backtesting, Monte Carlo simulation, and live deployment.

面向 AI agent 的技能经济协议——涵盖身份、信誉、托管与治理，已上线 Casper Testnet（Odra）与 Stellar Testnet（Soroban ZK）。Agentic skill-economy protocol for AI agents — identity, reputation, escrow, and governance, live on Casper Testnet (Odra) and Stellar Testnet (Soroban ZK).

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

基于 Agentic LLM 的系统综述数据提取。Agentic LLM-assisted data extraction for systematic reviews

截至 2026-08-10 的投机解码研究知识库：66 篇核心论文全文精读、方法谱系、系统比较与研究空白

为将 MCP 服务器推向企业部署的团队提供的实用 MCP 就绪、安全与无状态迁移资源。Practical MCP readiness, security and stateless-migration resources for teams moving MCP servers toward enterprise deployment.

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

在 Oracle Cloud Infrastructure (OCI) 上部署 Odoo，并集成 Agentic AI 工作流与自动化Odoo deployment on Oracle Cloud Infrastructure (OCI) integrated with Agentic AI workflows and automation.

ScientiaPilot 公开展示——从研究问题到发表全流程的科研出版操作系统。Public showcase for ScientiaPilot — a research publication operating system from research question to publication.

AI 辅助的科研工具，用于文献探索、证据抽取与研究问题结构化。An AI-assisted scientific research tool for exploring literature, extracting evidence, and structuring research questions.

一个端到端的研究智能系统：摄取学术论文并进行语义理解，映射研究领域的关系与演进，探测尚未探索的研究空白，并使用多 Agent AI 流水线生成文献综述与回答研究问题——全部以纯 Python 构建。An end-to-end research intelligence system that ingests academic papers, understands them semantically, maps how research areas relate and evolve, detects unexplored research gaps, and uses a multi-agent AI pipeline to generate literature reviews and answer research questions — all built in pure Python.

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

Agent 优先、安全优先的工具包，用于开发和定制 reMarkable Paper Pure 平板。Agent-first, security-conscious toolkit for developing and customizing reMarkable Paper Pure tablets

模板化的元研究范例：自文档化的可复现研究仓库。Template meta-research exemplar: self-documenting reproducible research repo

The Triplicate：数据驱动的大幅面报纸排版引擎 —— docxology/template 可复现研究范式的公开范例（测试覆盖率 ≥90%，无 mock，GitHub 与 Zenodo 10.5281/zenodo.20533675 双重发布）。The Triplicate: a data-driven large-format newspaper layout engine — public exemplar of the docxology/template reproducible-research paradigm (≥90% test coverage, no mocks, double-published GitHub + Zenodo 10.5281/zenodo.20533675).

系统综述材料：研究方案、PRISMA 记录、各研究的数据以及筛选决策。Systematic review materials: protocol, PRISMA records, per-study data, screening decisions