仓库/Skill 库

企业知识智能平台：基于权限感知的搜索、助手与 agent，覆盖公司现有工具栈。Enterprise knowledge intelligence platform. Permission aware search, assistant and agents over the tools a company already runs.

面向金融分析师的 Agentic Jupyter Notebook。Agentic Jupyter Notebook for financial analysts

基于 Codex CLI、MCP 与 AppServer 协议的 Swift 原生接口。Swift-native interfaces backed by Codex CLI, MCP, and AppServer protocols.

一个为 Model Context Protocol 提供策略执行能力的 gateway。聚合 MCP server，强制工具调用策略，扫描结果中的 prompt injection 与凭证泄露，并审计一切。Rust 实现。A policy-enforcing gateway for the Model Context Protocol. Aggregates MCP servers, enforces tool-call policy, scans results for prompt injection and leaked credentials, and audits everything. Rust.

一套面向 LLM-based RTL 验证开放研究问题的架构：分块多表征记忆（BM25 / HNSW / 结构化事实）、基于本地 7B LLM 的多 Agent 编排器，以及具备漂移保护的反馈驱动优化。An architecture answering open research questions on LLM-based RTL verification: chunked multi-representation memory (BM25 / HNSW / structured facts), a multi-agent orchestrator over a local 7B LLM, and feedback-driven refinement with drift protection.

AI 驱动的研究助手，自动检索、分析、总结、评审并格式化学术论文，生成带 APA 引用与 PDF 输出的结构化系统文献综述AI-powered research assistant that automatically searches, analyzes, summarizes, reviews, and formats academic research papers into structured systematic literature reviews with APA citations and PDF output.

Composio AI 产品运营案例研究：可复现的研究 Agent 与 100 个应用集成的就绪数据集。Composio AI Product Ops case study: reproducible research agent and 100-app integration readiness dataset.

通过隔离的 worktree、GitHub PR 交接和清单驱动的审计日志来规划、分发、评审与合并 AI 编码 Agent 的工作。Plan, dispatch, review, and merge AI coding-agent work with isolated worktrees, GitHub PR handoffs, and manifest-backed audit trails.

CreditFlow AI Agent——小商户贷款预审与自动小额放款 Agent（Google Cloud AI × Solana 实现的下一代 AI Agentic 黑客松项目）CreditFlow AI Agent - 소상공인 대출 사전심사 및 자동 소액대출 집행 에이전트 (Google Cloud AI × Solana로 구현하는 차세대 AI Agentic 해커톤)

一个结合 Web 搜索与 API 增强的 Agent，用于构建研究论文知识图谱，突破文献综述瓶颈。An agent that combines web search and API enrichment to build a knowledge graph of research papers for literature review bottlenecks

一款个人知识引擎，注重综合而非简单转录——每个声明都附带回到原始来源的引用。为 LLM agent 提供写入时综合 + 带引用的检索能力。A personal knowledge engine that synthesizes instead of transcribes — every claim carries a citation back to its source. Write-time synthesis + cited retrieval for LLM agents.

面向开源库的机器可读错误知识库——MCP server、REST API 与静态数据集，将每条错误消息映射到抛出该错误的源代码行。Machine-consumable error knowledge base for open-source libraries — MCP server, REST API, and static dataset mapping every error message to the source line that raised it

面向空间 LLM 与地理空间 AI Agent 的生产工程模式——验证优先架构、地理空间 RAG、prompt-to-spatial-SQL、tool routing 与评估。Production engineering patterns for spatial LLMs and geospatial AI agents — validation-first architecture, geospatial RAG, prompt-to-spatial-SQL, tool routing, and evaluation.

多语言 AI agent 服务 — 基于单一 schema 驱动的 WebSocket 协议，提供知识对话、工具调用、持久检查点、人机协同与多方会话。基于 smooth-operator-core 引擎构建（5 种语言特性一致）。可部署到 Kubernetes、AWS serverless 或本地运行。托管于 lom.smoo.ai。Polyglot AI agent service — knowledge chat, tools, durable checkpoints, human-in-the-loop, and multi-participant conversations over one schema-driven WebSocket protocol. Built on the smooth-operator-core engine (5-language parity). Deploy to Kubernetes, AWS serverless, or run locally. Hosted at lom.smoo.ai.

让编码 Agent 在需要你介入时通知你。Smoke Signal Codex & Claude 插件。Let your coding agent notify you, when you are needed. Smoke Signal Codex & Claude plugin.

美国国会图书馆（Library of Congress）MCP server：检索扫描报纸、浏览目录、读取记录，无需 API key。MCP server for the Library of Congress. Search inside scanned newspapers, browse the catalogue, read records. No API key.

一个 Claude Managed Agent，可回答 SlideRule 研究问题并返回独立的 HTML 仪表板；每个用户需在其自己的 Anthropic 账号中部署专属 AgentA Claude Managed Agent that answers SlideRule research questions and returns a self-contained HTML dashboard. Each user provisions their own agent in their own Anthropic account.

macOS 菜单栏应用，监控 Claude Code 配额并自动开关其自主循环。macOS menu-bar app that watches Claude Code's quota and switches its autonomous loop on and off for you

2026 年 21-Agent 病毒式发布流水线——从 AI 研究到多渠道分发。21-Agent Viral Launch Pipeline 2026 – AI Research to Multi-Channel Delivery

使用工具研究问题并生成答案的 AI AgentAn AI agent that uses tools to research questions and generate answers.

本地优先求职工作站——抓取职位、筛选分流，通过自有 Codex CLI 定制简历与求职信，导出 LaTeX PDF，无需服务器端模型密钥。Local-first job-search workstation — fetch roles, triage, tailor CVs and cover letters through your own Codex CLI, export LaTeX PDFs. No server-held model keys.

macOS 菜单栏 App：统计各 AI Agent 工具的 token 用量与花费，显示订阅额度，并用状态灯实时反映任务运行状态。纯本地只读。

Claude Code skill：检索近 30 天 OpenAlex、Semantic Scholar、PubMed、arXiv 与 HuggingFace Hub 的科学文献。Claude Code skill that searches the last 30 days of scientific literature across OpenAlex, Semantic Scholar, PubMed, arXiv, and HuggingFace Hub

2026 年 8 大 AI 编码 Agent 防护面盘点 — Sigil Hook 与 Sandbox 评测8 Best AI Coding Agent Guard Surfaces 2026 – Sigil Hook & Sandbox Review

通用深度研究 Agent 团队：13 Agent 流水线，提供包含系统综述与 Meta 分析在内的 8 种模式。Universal deep research agent team: 13-agent pipeline, 8 modes incl. systematic review and meta-analysis

AI 驱动的 CORBA/IDL 接口自动化 —— 从自然语言规约到实时 ORB 绑定，无需手写 stub；MIT ORB core 基于开放 OMG wire 规范构建。AI-driven CORBA/IDL interface automation — from natural-language spec to a live ORB binding, with no hand-written stubs. MIT ORB core built on the open OMG wire specification.

面向苏格拉底式导师的 Hermes 人设：研究问题开发、文献综合与项目脚手架。属于 Bronx Science 社会科学研究课程的一部分。Hermes profile for Socratic mentorship: research question development, literature synthesis, and project scaffolding. Part of the Bronx Science Social Science Research curriculum.

从已发表图表到可复现研究工作流：借助 Codex 理解证据、重建方法并验证科学复现。From published figures to reproducible research workflows: understand evidence, reconstruct methods, and validate scientific reproduction with Codex.

受治理的、与 provider 无关的运行时，面向证据驱动的自主软件工程、研究和数据分析工作流。Governed, provider-neutral runtime for evidence-driven autonomous software engineering, research, and data-analysis workflows.

将混乱的需求转化为 coding agent 一次就能做对的 prompt。一个适用于 Claude Code、Cursor 以及任何能阅读 markdown 的 agent 的 skill。Turn a messy request into a prompt your coding agent gets right the first time. A skill for Claude Code, Cursor, and any agent that reads markdown.

面向多种 coding agent 的终端。会话跨窗口存活，侧边栏一目了然展示谁在做什么。A terminal for many coding agents. Sessions outlive the window; one sidebar says who is doing what.

通过查询条件超边预测，为 LLM agent 检索工具集合。Retrieve sets of tools for LLM agents using query-conditioned hyperedge prediction.

为每一个 Coding Agent 提供统一的全局开发环境。One global environment for every coding agent.

面向研究的 Skill 定义精选集合，覆盖文献综述、证据综合与研究空白分析；汇总多个社区驱动的 Skill，便于在 Codex 或 Copilot 工作流中对比、审阅与按需安装A curated collection of research-focused skill definitions for literature review, evidence synthesis, and research-gap analysis. It brings together multiple community-driven skills so they can be compared, reviewed, and selectively installed for use in Codex or Copilot workflows.