仓库/Skill 库

脚手架搭建生产级 AI Agent 项目最快的方式。The fastest way to scaffold production-ready AI Agent projects

通过 MCP 为协作型 AI agent 提供基于 PostgreSQL 的共享记忆。Shared PostgreSQL-backed memory for collaborating AI agents via MCP

织光 WeaveMind V1.0 — 看得见、会记忆、会自我进化的多智能体 AI 团队。多用户鉴权、结构化数据适配器、验收溯源、报告分享/PDF/通知，本地运行数据私有。

自动化 git-worktree 工作流：通过 Claude Code 或 GitHub Copilot CLI 从 diff 中提取意图，执行构建/lint/测试，开启 GitLab MR 或 GitHub PR，并自动修复失败的 pipeline。Automated git-worktree workflow that captures intent from diffs via Claude Code or GitHub Copilot CLI, runs build/lint/test, opens GitLab MRs or GitHub PRs, and auto-fixes failing pipelines.

自托管 Docker 栈，用于跨平台 AI Agent 工作区（Claude Code + ChatGPT + 任意 LLM）。MIT 许可。Self-hosted Docker stack for cross-platform AI agent rooms (Claude Code + ChatGPT + any LLM). MIT.

🤖 DeepTutor 是一款 AI 驱动的学习助手，可根据个人需求定制教育内容，提供个性化资源与支持🤖 Enhance learning with DeepTutor, an AI-powered assistant that personalizes education to fit your needs. Discover tailored resources and support.

基于环境凭证的 CrewAI scaffold 与 Streamlit kickoff-client 学习。CrewAI scaffold and Streamlit kickoff-client study with environment-only credentials.

Claude-Code-Skill-Set：从任意知识源生成可打印的学习卡片（A4，每页 8 张，支持双面打印）Claude-Code-Skill-Set: aus beliebigen Wissensquellen druckfertige Lernkarten (A4, 8 Karten/Seite, duplexfähig)

Model Context Protocol（MCP）的 Apache-2.0 安全扩展提案。包含对象级签名、新鲜度/重放保护、mTLS 传输、委托授权以及普通 MCP 服务器的 sidecar 保护。Rust workspace；安全审计发布于 docs/security/Apache-2.0 security extension proposal for the Model Context Protocol (MCP). Object-level signing, freshness/replay protection, mTLS transport, delegated authorization, sidecar protection of ordinary MCP servers. Rust workspace; published security audits under docs/security/.

将 GitHub Copilot CLI 转变为资深队友的 CLI + TUI：安装精选的 skill 目录、自定义 Agent、教学人格、跨会话记忆，以及原生 Spec-Driven Development 引擎。纯 Go 实现，内部不含 LLM；capiko 负责指挥，Copilot 负责执行。CLI + TUI that turns the GitHub Copilot CLI into a senior teammate: installs a curated catalog of skills, custom agents, a teaching persona, cross-session memory, and a native Spec-Driven Development engine. Pure Go — no LLM inside; capiko directs, Copilot executes.

面向 B5G/6G NOMA RIS/STARS 无线通信研究的 IEEE 规范学术写作、润色与评审 Agent Skills。IEEE-compliant academic writing, polishing, and reviewing Agent Skills — tailored for B5G/6G NOMA RIS/STARS wireless communications research.

面向本地优先应用与 AI Agent 的嵌入式双时态记忆引擎，采用混合检索——进程内运行，无需服务器。Embedded bitemporal memory engine with hybrid retrieval for local-first applications and AI agents — in-process, no server.

🚀 零配置将 LangChain Agent 暴露为服务；以简单包装把脚本变为 Web 服务，无需任何基础设施🚀 Expose your LangChain agents as services with zero configuration; turn scripts into web services using simple wrappers and no infrastructure setup.

面向 AI 编程 agent 的平台无关工作编排，基于 MCP + CLI，提供跨提供商的统一面板（issues、scm、ci、deploy、notify）。Platform-agnostic work-orchestration for AI coding agents — one pane of glass (issues, scm, ci, deploy, notify) across providers, via MCP + CLI.

🛡️ Agent 原生的 AI 工具安全扫描器。扫描 MCP/Skill/GPT/Prompt 的安全风险。四维评分。认证徽章。Guardrail MCP 提供自动防护。🛡️ Agent-native AI tool security scanner. Scan MCP/Skill/GPT/Prompt for security risks. 4-dimensional scoring. Certified badges. Guardrail MCP for auto-protection.

面向全国大学生数学建模竞赛（CUMCM）的 Claude Code 全流程自动化 Skills：赛题分析→建模→编程绘图→论文撰写（LaTeX/Typst）→验证验收。内置国赛论文写作模板、LaTeX 模板、模型选择库、方法知识库与 Python 实现。

Logic Writing：面向 Codex 的证据驱动调查与学术写作编排。Logic Writing: evidence-first investigation and academic writing orchestration for Codex

12 个写作 skill—— SEO 博客、邮件营销、销售文案、学术写作。12 writing skills - SEO blog, email marketing, sales copy, academic writing.

12 项研究 AI Skills —— LaTeX 论文、统计分析、文献综述、会议投稿12 research AI skills - LaTeX papers, statistical analysis, literature review, conference submission.

为 Codex 及 AI 编程 Agent 提供的持久化项目记忆与智能层。Persistent project memory and intelligence layer for Codex and AI coding agents.

面向 WHOOP API v2 的只读 MCP server——可从任意 MCP 客户端查询并分析你自己的恢复、睡眠、负荷与训练数据。本地运行，凭据不离开本机。Read-only MCP server for the WHOOP API v2 — query and analyse your own recovery, sleep, strain and workout data from any MCP client. Runs locally; credentials never leave your machine.

部署一支完整的 AI 工程团队 2026——带自动化质量 Hook 的 Claude 12-Agent 系统。Deploy a Full AI Engineering Team 2026 - Claude 12-Agent System with Automated Quality Hooks

提供提案撰写、医学影像文献综述与论文报告幻灯片的工具，自动化学术研究工作流。Automate academic research workflows with tools for proposal writing, medical imaging literature reviews, and paper presentation slides.

基于架构决策记录（ADR）理念的 Memory Framework，用于 AI agent（Claude Code、Codex、Antigravity……）之间的知识共享。支持 agent 安装，vector（Postgres + pgvector）+ graph（Neo4j）双骨干，通过本地 gateway 管理，支持多种本地 LLM 后端，具备完整 provenance、合并、遥测等能力。Memory Framework based on the idea of Architectural Decision Records, shared knowledge between AI agents (Claude Code, Codex, Antigravity ...). Agent installable, vector (Postgres + pgvector) + graph (Neo4j) backbone, managed through a local gateway, supporting multiple local LLM backends, with full provenance, consolidation, telemetry and more

用于 Zotero 文献综述自动化和双语可视化仪表盘的 Codex skillCodex skill for Zotero literature review automation and bilingual visual dashboards

一个只读 MCP 服务器，根据研究问题或参考图像，为 Claude 和 Codex 推荐真实可复现的 R/Python 科学图表案例。Read-only MCP server that recommends real, reproducible R/Python scientific figure cases to Claude and Codex — by research question or reference image.

给系统一个复杂的研究问题，它可自主搜索你的知识库和 Web，检索相关来源，分析与交叉验证证据，并生成结构化、带引用的研究报告。Give the system a complex research question, and it autonomously searches your knowledge base and the web, retrieves relevant sources, analyzes and cross-checks evidence, and produces a structured, citation-backed research report.

Scholar Support：面向 Claude Code 的 APA 7 学术写作插件——起草、编辑、评分与引用 2026。Scholar Support: APA 7 Academic Writing Plugin for Claude Code – Draft, Edit, Grade & Cite 2026

PaperForge v2026 是一款基于浏览器的学术写作自动化系统，通过 LLM 引导的工作流完成论文生成、引用处理、迭代与校验。PaperForge v2026 is a browser-based academic writing automation system with LLM-guided workflows for paper generation, citation handling, iteration, and validation.

开源的全流程演示文稿平台——构建、演示、发布与协作。自托管、原生支持 MCP、完全可定制主题。The open-source, end-to-end presentation platform - build, present, publish, and collaborate. Self-hosted, MCP-native, fully themeable.

本地优先、由 LLM 驱动的系统文献综述 (SLRs) 平台，以人机协同方式自动完成筛选与提取Local-first, LLM-powered platform for Systematic Literature Reviews (SLRs)—automating screening and extraction with human-in-the-loop precision.

codegraph 是一个 local-first 的代码上下文引擎和面向代码仓库的 MCP server。它将源代码增量索引到轻量级 SQLite 图中，然后提供高信噪比的 tools，支持符号查找、调用图遍历、影响分析、相关测试发现和语义搜索。使用 Go 构建，单二进制工作流，专为……而设计。codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work

本地优先的量化投资平台，支持可复现研究、证据约束决策、风险控制、论文/影子验证以及人工监督执行Local-first quantitative investing platform for reproducible research, evidence-bound decisions, risk controls, paper/shadow validation, and human-supervised execution.

面向私有仓库与本地模型的自托管、厂商中立编码 Agent。TUI 优先，支持 16 家提供商的 BYOK 或通过 Ollama/LM Studio 完全离线运行。每个 Agent 操作均经过沙箱隔离、日志记录与签名——构建为可验证，而非仅可信任。Self-hosted, vendor-neutral coding agent for private repos and local models. TUI-first, BYOK across 16 providers or fully offline with Ollama/LM Studio. Every agent action is sandboxed, logged, and signed — built to be verified, not just trusted.

Haven 42 是一款证据门控、本地优先的 AI 工作台，支持 Windows、Linux 和 macOS 上的编码、聊天与媒体处理。Haven 42 is an evidence-gated, local-first AI workbench for coding, chat, and media on Windows, Linux, and macOS.

AI 构建，你决定是否上线 —— AI agent 工作的审核关卡。AI builds it. You decide if it ships. — review gates for AI-agent work.