仓库/Skill 库

AI Agent 的认知操作系统——浏览器与计算机智能、持久化任务、记忆、恢复、证据与受治理的真实世界行动。A cognitive operating system for AI agents — browser & computer intelligence, persistent missions, memory, recovery, evidence, and governed real-world action.

面向 AI Agent 的循证科学写作与修订 SkillEvidence scientific writing and revision skill for AI agents

面向 AI Agent 的低开销记忆后端 —— 单二进制，内存占用约 50MB，支持验证增强准确性Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy

Delta-9 MAW — 按严重程度（P0–P3）路由的多 Agent 异常处理流水线 + TOTP 操作面板，并配套线上 d9bkk.com 会员商店（KYC、D9-Wallet、PromptPay、TCG Lottery Pack）。Delta-9 MAW — severity-routed multi-agent anomaly pipeline (P0–P3) + TOTP operator panel, alongside the live d9bkk.com member storefront (KYC, D9-Wallet, PromptPay, TCG Lottery Pack).

LLM 的工作记忆。一个供 agent 钉存与更新的会话图，避免将所有内容倾倒到聊天中。Working memory for LLMs. One session graph that agents pin and update — without dumping everything into chat.

使用 YAML 声明式地定义并执行多 Agent AI 工作流，通过自动上下文处理简化编排并增强协作。🤖 Define and execute multi-agent AI workflows declaratively using YAML, simplifying orchestration and enhancing collaboration through automatic context handling.

Claude Code 的治理与可审计层：在 CEO 协议下运行由专业 Agent 组成的结构化团队——plan→debate→execute 门控、防篡改审计日志、跨 LLM 双重护栏。Governance & auditability layer for Claude Code: run a structured team of specialist agents under a CEO protocol — plan→debate→execute gating, tamper-evident audit log, cross-LLM pair-rail.

BuyWhere agent-native 商品目录 APIBuyWhere agent-native product catalog API

针对 AI Agent 的确定性审批、拒绝、取消、超时、重放及副作用安全测试 —— 无需 API key。Deterministic approval, rejection, cancellation, timeout, replay, and side-effect safety tests for AI agents—no API keys required.

论文 "Every Answer Has Its Own Path: Agentic Routing for Retrieval-Augmented Table Question Answering" (EMNLP 2026) 的官方代码。Official code for "Every Answer Has Its Own Path: Agentic Routing for Retrieval-Augmented Table Question Answering" (EMNLP 2026)

通过面向编码 Agent 的多 Agent Skill 工具包自动化论文写作，使用 PaperOrchestra 流水线将非结构化数据转换为 LaTeX 论文Automate research paper writing with this multi-agent skill pack for coding agents. Convert unstructured data into LaTeX papers using the PaperOrchestra pipeline.

Sago AI：数秒内从 Markdown 描述生成任意应用（2026）🚀 Sago AI: Generate Any App from a Markdown Description in Seconds (2026)

5dive 维护的 Claude Code 插件市场——包含 Telegram 桥接及相关 agent-channel 集成。Claude Code plugin marketplace maintained by 5dive — Telegram bridge and related agent-channel integrations.

专注后端的 fullstack 与 applied AI 开发。基于 LLMs 与 agents 构建有趣的项目，执着于 clean architecture 与零缺陷代码的生产部署。Backend-focused fullstack & applied ai dev. Building cool stuff with LLMs & agents. Obsessed with clean architecture & shipping no-bug code to prod.

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.

以证据为先的 Agent Skill：对抗性学术新颖性审计——最小先验集合、历史截止点与跨桥感知的先验工作分析。Evidence-first Agent Skill for adversarial scholarly novelty audits — Minimal Prior Sets, historical cutoffs, and bridge-aware prior-work analysis.

输入一个研究问题，获取阅读指南与持续更新的源信息地图 — 基于 Cloudflare Durable Objects 构建的公共研究花园，保留成长历史Seed a research question, get a reading guide and a living source map — public research gardens with saved growth history, on Cloudflare Durable Objects.

面向 Claude Code 的对抗式学术写作审阅工具包 — 包含 30+ 审计 Skill（LaTeX、文献、可读性、模拟同行评审）以及一个机械检查器的 MCP server。Adversarial academic-writing review toolkit for Claude Code — 30+ audit skills (LaTeX, bibliography, readability, simulated peer review) plus an MCP server of mechanical checkers.

通过单一 MCP 服务器，将任务分派给 Codex、Claude 与 OpenCode。Delegate work to Codex, Claude, and OpenCode through one MCP server

基于机器学习的计算机视觉 Agentic AI 系统，用于规模化树木作物育种项目Agentic AI system for machine learning-based computer vision to scale tree crop breeding programs

做一个合格的科研助手！

使用 AI agent 自动化文献综述，基于结构化协议实现全面研究与高质量报告生成📚 Automate literature surveys with AI agents using a structured protocol for thorough research and insightful report generation.

MonoCode Linux 桌面界面，专为代码 Agent 打造，仅限 Linux。MIT 许可。MonoCode Linux desktop interface for code agents, exclusively for Linux. MIT licensed.

AI 安全测试——发现 LLM 应用、聊天机器人、AI Agent、MCP 服务器与 RAG 系统中的安全漏洞。对齐 OWASP（LLM、Agentic、MCP）与 NIST AI RMFAI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.

插件化形态的 14-Agent 软件公司：在硬性预算上限内规划、构建并对每次变更进行对抗式评审。Markdown + POSIX shell，零运行时依赖。A 14-agent software company in a plugin: plan, build, and adversarially judge every change under hard budget caps. Markdown + POSIX shell, zero runtime deps.

证伪优先的引用核验:论文存在性 / 元数据 / 论点支撑三重检查,可被 Claude Code、Codex、Cursor 以 MCP 调用 · Skeptical citation auditor for agent writing workflows · PyPI: citationguard

面向可信 AI Agent 的开源基础设施，覆盖身份、权限、执行、证据、验证与 Agent 间组网。Open-source infrastructure for trusted AI agents — identity, permissions, execution, evidence, verification and agent-to-agent networking.

以安全为先、确定性合成的测试数据生成，基于 CSV 配置描述文件与白名单内的 Trino 元数据。Safety-first, deterministic synthetic test data generation from CSV profiles and allowlisted Trino metadata.

AgentServices — AI Agents 的 Premium APIs。加密数据、营销情报、争议解决。基于 Base 的 x402 micropayments。AgentServices — Premium APIs for AI Agents. Crypto data, marketing intelligence, dispute resolution. x402 micropayments on Base.

2026 终极 AI Coding Agent 连续性工具包——无缝交接与同步。Ultimate AI Coding Agent Continuity Toolkit 2026 - Seamless Handoff & Sync

用于论文推荐的 Claude botClaude bot for paper recommendation

🌐 通过这款高效的网页抓取 MCP server，从任意 URL（含 Cloudflare 防护站点）提取干净、可直接用于 LLM 的 markdown🌐 Extract clean, LLM-ready markdown from any URL, including Cloudflare-protected sites, with this effective MCP server for web scraping.

为 AI Agent 提供实时新闻上下文。发送一个话题和一个 cursor；可能返回空，或返回一包带引用的简明新闻。只读、无需密钥、MIT 许可。Real-time news context for AI agents. Send a topic and a cursor; get nothing, or a short pack of cited stories. Read-only, no key, MIT.

LabRelay 连接需要处理可管理研究任务（文献综述、数据录入、问卷外联）的教授与医生，以及寻求真实经验和入门途径的学生。LabRelay connects professors and doctors who need help with manageable research tasks — literature reviews, data entry, survey outreach — with students who want real experience and a way in.

现代化 LaTeX 写作环境，可将收集的思路与文献转化为论文。采用 Rust 内核，基于 Tauri v2、Svelte 5、CodeMirror 6，支持 Zotero 与 Obsidian 集成、TypeScript 插件，原生支持 x86_64 与 ARM64。A modern LaTeX writing environment that turns collected ideas and sources into papers. Rust core, Tauri v2, Svelte 5, CodeMirror 6. Zotero and Obsidian integration, TypeScript plugins, native on x86_64 and ARM64.