仓库/Skill 库

AI agent 沙箱的时间旅行调试——基于 Firecracker microVM，支持 record、snapshot、restore 与 diff，非容器方案。Time-travel debugging for AI agent sandboxes — Firecracker microVMs with record, snapshot, restore, and diff. Not containers.

开源、自托管的 Claude Code 与 opencode 客户端。Agent 在你自己的 Linux 主机或 Mac 上的真实 tmux 中运行，可通过桌面、手机或浏览器经 HTTPS 远程操控。Open-source, self-hosted Claude Code and opencode client. Agents run in real > tmux on your own Linux box or Mac, and you drive them from desktop, phone or > browser over HTTPS.

MCP 桥接，让 Claude Code 和其他宿主将实现工作委托给 OpenAI Codex CLI。MCP bridge that lets Claude Code and other hosts delegate implementation to the OpenAI Codex CLI

Webasyst MCP Server 2026：面向应用、插件与主题的 AI 工具。Webasyst MCP Server 2026: AI Tools for Apps, Plugins & Themes

基于 Pingora 构建的纯 Rust API gateway，具备安全流量排空、不可变配置变更、限定作用域的 MCP 工具以及内置管理控制台。Pure Rust API gateway built on Pingora, with safe traffic draining, immutable config changes, scoped MCP tools, and an embedded admin console.

📄 面向 AI Agent、RAG、知识图谱的每日论文发现 —— 覆盖 arXiv + HuggingFace + Papers With Code📄 Daily paper discovery for AI Agent, RAG, Knowledge Graph - arXiv + HuggingFace + Papers With Code

企业级数字支付平台：Java 21 / Spring Boot 3 微服务、Kafka 事件驱动、六边形（端口与适配器）架构，由专业 AI Agent 团队以 spec 驱动并编排，包含完整 CI/CD、GitOps 和供应链安全。Enterprise-grade digital payment platform: Java 21 / Spring Boot 3 microservices, Kafka event-driven, hexagonal (ports & adapters) architecture, spec-driven and orchestrated by a team of specialized AI agents. Includes full CI/CD, GitOps, and supply-chain security.

Codex Autonomous Objective Loops 2026：强制审查与验证的 AICodex Autonomous Objective Loops 2026: AI with Mandatory Review & Verification

开源 MCP 监督器，用于在 Codex 中委派、监控与管理 Grok、Cursor 与 DeepSeek 等编程 AgentOpen-source MCP supervisor for Codex to delegate, monitor, and manage Grok, Cursor, and DeepSeek coding agents.

📄 从任意网站提取面向 AI Agent 和 LLM 的文档，通过便捷访问 llms.txt 和 install.md 文件简化自动化工作流。📄 Extract documentation for AI agents and LLMs from any website, simplifying automation workflows with easy access to llms.txt and install.md files.

一款将模型命令沙箱化，并使用可编辑状态机处理长时间任务的编码 AgentA coding agent that jails model commands and uses editable state machines for long-running tasks

OWNEX——自主工作操作系统（Autonomous Work Operating System）：机会发现、安全自动化、Agent 编排、本地优先 AI 路由、收入情报。Python/FastAPI + Vue 3 + Tauri。OWNEX — Autonomous Work Operating System: opportunity discovery, security automation, agent orchestration, local-first AI routing, revenue intelligence. Python/FastAPI + Vue 3 + Tauri.

AI 驱动的 Monorepo 2026：设计系统、React 应用、Fastify API 与 Pulumi IaC。AI-Powered Monorepo 2026: Design System, React Apps, Fastify APIs & Pulumi IaC

面向 Webasyst 2026 的非官方 Codex-First MCP——应用、插件与 UI 审计工具。Unofficial Codex-First MCP for Webasyst 2026 – Apps, Plugins & UI Audit Tools

一个通过自博弈掌握 LLM 工具调用的 Python 库A Python library for LLM tool call mastery through self play.

开源 Codex Skill，用于严谨的社会科学综述与双语学术写作工作流。Open-source Codex skills for rigorous social-science review and bilingual academic writing workflows.

ThesisAI 是一个高性能的自主研究 Agent（自主研究代理），旨在简化学术写作流程。它能将你提供的知识库中的复杂信息合成为结构化、格式规范的学术文本。ThesisAI is a high-performance Autonomous Research Agent designed to streamline academic writing. It synthesizes complex information from your provided knowledge base into structured, properly formatted academic prose.

用于科学论文写作的 AI agents，可在评论中给出修正意见，使科学写作准确、流畅、无误，适合在科学期刊上发表。AI agents for Scientific Manuscript Writing comments, giving out correction comments to make scientific writing accurate polished without errors and suitable for publications in scientific journals.

基于 Google Gemma 4 31B 的多 Agent 系统，用于辅助学术文献综述A multi agent system to aid academic literature review powered with Google's Gemma 4 31B

与你的 coding agent 语音对话，它会回复。为 Claude Code、Cursor 及任何 MCP 客户端提供 local-first 语音 I/O（MCP tools + Agent Skill）。🎙️ Talk to your coding agent. It talks back. Local-first voice I/O (MCP tools + Agent Skill) for Claude Code, Cursor and any MCP client.

面向飞书/Lark 的开源 AI 辅助入职方案：可配置工作流、文档 OCR 与审阅、Bitable 同步、提醒功能，以及零凭证 Demo。Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-credential demo.

MCP 服务器：将 YouTube 字幕与公开统计数据暴露为工具MCP server exposing YouTube transcripts and public statistics as tools. Transcripts need no API key; statistics use the YouTube Data API v3 with local Pacific-time quota tracking.

CI 验证的科学领域 Agent Skill——69 个研究级 Skill，覆盖科学写作、机器学习、数据分析、量子计算与研究数据库。无死链、无虚假 Skill、无厂商广告。兼容 Claude Code / Cursor / Codex。CI-validated Agent Skills for science - 69 research-grade skills for scientific writing, ML, data analysis, quantum computing, and research databases. No dead links, no phantom skills, no vendor ads. Claude Code / Cursor / Codex compatible.

用于检索 PROSPERO 系统综述注册库的 MCP serverMCP server for searching the PROSPERO systematic review register

可复用的 Agent skill，用于有证据支撑的科研写作、发表级图表生成以及安全的 DOCX 修订。Reusable agent skills for evidence-grounded scientific writing, publication-ready figures, and safe DOCX revision.

AI 驱动的学术与职业助手，帮助留学生优化简历、学术写作与研究申请An AI-powered academic and career assistant designed to help international students improve resumes, academic writing, and research applications.

研究问题系统Research Question system

AI 驱动的学术写作AI-powered academic writing

Cold email MCP server + agent-native 发送基础设施 — 完全由你的 coding agent（Claude Code / Codex / Cursor）运行。一个 token，17 个 MCP tools + CLI：品牌域名、邮箱、预热、序列、回复。内测中。Cold email MCP server + agent-native sending infrastructure — run entirely by your coding agent (Claude Code / Codex / Cursor). One token, 17 MCP tools + CLI: branded domains, mailboxes, warmup, sequences, replies. Early access.

面向任意 QMK/VIA 键盘的 MCP server，通过原始 HID 读写灯光、键位映射与宏，无需厂商白名单。MCP server for any QMK/VIA keyboard. Read and change lighting, key mappings, and macros over raw HID — no vendor allowlist.

可配置、可审计的六 Agent 系统性文献综述工作流Configurable, auditable six-agent systematic literature review workflow

Agent 中立的自主、协作与能力编排 harness。Agent-neutral autonomy, collaboration, and capability orchestration harness.

本地化 MCP 数据平台。自然语言问题按规则分派到向量搜索、NL2SQL、知识图谱三条通道并行查询，通过 RRF 融合后由本地 LLM 基于证据作答。无需调用外部 API。온프렘 MCP 데이터 플랫폼. 자연어 질문을 벡터검색·NL2SQL·지식그래프 3레인으로 규칙 기반 분기해 병렬 조회하고 RRF로 융합, 로컬 LLM이 근거 기반으로 답한다. 외부 API 호출 없음.

一道 Python 守门机制：在不分类提示词的前提下，阻止不可信的 agent 数据去构造敏感的工具调用参数。A Python gate that prevents untrusted agent data from authoring sensitive tool-call arguments—without classifying prompts.

面向 Claude Code / Codex 的 Agent Skill：为系统评价与 Meta 分析构建可复现、可按 PRISMA-S 报告的检索策略 —— 通过 NCBI API 获取 MeSH、主题词+自由词检索式、单行记录数、召回率校验、多数据库语法。Agent Skill for Claude Code / Codex: build reproducible, PRISMA-S-reportable search strategies for systematic reviews & meta-analyses — MeSH via NCBI API, subject-heading + free-text lines, per-line record counts, recall check, multi-database syntax. 系统评价/Meta分析检索策略构建 skill

基于 Google ADK 的多智能体文献综述系统，并行扫描预印本/同行评审/实现仓库，自评估覆盖循环，代码层面强制引文不变性Multi-agent literature review system on Google ADK — parallel preprint/peer-reviewed/implementation sweep, self-evaluating coverage loop, and a citation invariant enforced in code.