Beacon Threat Intelligence
Security intelligence for the agent supply chain
Every MCP server and agent skill the public registries list, matched to its source repository, with Beacon's rating of what it can do to your agent and your machine.
| Name | Risk |
|---|---|
| skill-refiner Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill qua... | |
| Zai Usage Monitor Z.AI GLM Coding Plan usage and quota limits. Track token consumption, view reset times, and check subscription status. | |
| viewprinter-social-manager Use ONLY for work that goes through a connected ViewPrinter account: scheduling or publishing a post to TikTok, Instagram, Facebook, YouTube or X; uploading, describing, listing or PERMANENTLY DELETING media held in ViewPrinter; amending or | |
| AMG Azure Subscription Cost Analysis Run only when the user explicitly asks for a monthly Azure subscription cost analysis — lists all accessible subscriptions, lets the user choose which to ana... | |
| AMG Cosmos DB for MongoDB (RU) Health Check Run only when the user explicitly asks for a fleet-wide Cosmos DB for MongoDB (RU) health check — scans NormalizedRU consumption, service availability, serve... | |
| AMG Key Vault Health Check Run only when the user explicitly asks for a fleet-wide Azure Key Vault health check — pulse check for availability, API latency, throttling (429s), auth fai... | |
| AMG PostgreSQL Flexible Server Health Check Run only when the user explicitly asks for a fleet-wide PostgreSQL Flexible Server health check — scans CPU, memory, storage, IOPS, disk bandwidth, and conne... | |
| AMG Storage Account Health Check Run only when the user explicitly asks for a fleet-wide Azure Storage Account health check — pulse check for availability, latency, transactions, and error r... | |
| Claw-Net Ask a question in plain English, get data from 13,000+ APIs in one call. Crypto prices, social data, market intelligence. Every response is cryptographically... | |
| Context Mode Efficiently research and analyze multiple sources by fetching, indexing, batch processing, and searching without loading raw data into context. | |
| Dalong Session Logs Search and analyze your own session logs (older/parent conversations) using jq. | |
| Dalong Video Frames Extract frames or short clips from videos using ffmpeg. | |
| MINIMAX TEAM RULES Shared MiniMax / MMX CLI operating rules for XiaoMei, DaLong, YuanQi, and the main coordinator. Trigger this skill whenever the task involves MiniMax, minima... | |
| System Inspection 大龙系统巡检 SOP — 低打扰式定期检查 OpenClaw 运行时状态、Gateway、Channel、Tasks 与错误日志。只整理值得行动的问题，格式输出「结论 / 原因 / 建议」。由「大龙-系统巡检」cron 任务触发。 | |
| Taskflow Inbox Triage Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some... | |
| YiHui Agent Swarm Multi-agent orchestration framework for OpenClaw. Define roles, route tasks, manage state, and coordinate agent teams using structured YAML configs and a pro... | |
| YiHui CONTEXT MODE context-mode is an MCP server that saves 98% of your context window by sandboxing tool outputs. It routes large file reads, shell outputs, and web fetches th... | |
| YiHui GIT MONITOR 通用 Git 项目监控工具。支持 GitHub、GitLab、Gitee 等所有 Git 平台。可以添加、删除、检查任意 Git 仓库的更新，自动拉取代码并生成变更摘要。 | |
| YiHui GITHUB MONITOR Monitor multiple GitHub repos with configurable alert policies for releases, PRs, and security, sending low-noise notifications via scheduled cron jobs. | |
| YiHui Healthcheck Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, r... | |
| node-connect Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi w... | |
| Session Logs (YiHui) Search and analyze your own session logs (older/parent conversations) using jq. | |
| taskflow Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under... | |
| Yinyo Liuyao 六爻断卦引擎(野鹤先生法)。基于《增删卜易》全文蒸馏,120条经验规则 + 412个应验卦例 + 64卦纳甲常量表。 【何时触发】 - 用户说"帮我断一卦""解卦""占卜""六爻""起卦""问卦" - 用户给出卦象信息(卦名/六爻装卦/动爻)并问吉凶/应期/成败 - 用户问"这件事能不能成""什么时候出结果"且手... | |
| Cc Log Viewer 实时 Log Viewer，捕获 Claude Code 终端输出，通过 WebSocket 推送到浏览器页面实时显示。用于远程/移动设备上观察 CC 执行任务的过程，或者将 CC 终端嵌入监控面板。同时也提供 CC 进程管理和命令行发送功能。 | |
| Soilkworks自动化控制 用于控制SolidWorks软件，实现零件自动创建、草图绘制、特征生成、工程图导出、文件保存等自动化操作，通过Python的pywin32库调用SolidWorks官方COM接口执行指令。 | |
| Gitlab Mr Review Pipeline 自动化 GitLab MR 代码审核流水线。使用 AI 对 MR 进行代码审查，生成报告并邮件发送给提交人。 | |
| Markdown to PDF Advanced Convert Markdown files to PDF with multiple backend options (WeasyPrint, Pandoc, wkhtmltopdf). Supports syntax highlighting, tables, images, custom CSS theme... | |
| ClawFight Raise and battle a unique lobster pet with evolving personality. Hatch, feed, patrol, fight other lobsters in PvP. Each lobster has a soul with distinct pers... | |
| SeedDrop Community engagement assistant that monitors platforms, generates valuable replies referencing your product naturally, and supports approve or auto modes. | |
| skill-feedback-collector Human-in-the-loop MCP feedback collector with task queue. Pauses to collect human input via browser UI before continuing. Use when completing tasks, encounte... | |
| SocialVault 社交平台账号凭证管理器。提供登录态获取、AES-256-GCM 加密存储、定时健康监测和自动续期。Use when managing social media account credentials, importing cookies, checking login status, or automating... | |
| agent-crew Creates and manages persistent multi-agent teams with standardized configs and team structures for progressive memory and private skill sets. | |
| usability-interviewer 可用性测试访谈助手。基于出声思考法（Think-Aloud Protocol）引导主持人设计任务脚本、记录用户行为与困惑点，并在测试后生成结构化观察笔记。当用户需要开展可用性测试、设计任务情境、记录被试表现或整理测试笔记时使用。 | |
| 用户反馈情感与痛点分析 用户反馈情感与痛点分析助手。批量分析用户评论、问卷开放题，做情感极性判断与痛点分类，输出设计评审洞察。 | |
| test_skill Collects public key, private key, and API key via pop-up dialogs and saves them to a JSON file, returning success status. | |
| winson-anchor-deep-skill 判断你站的位置是真锚还是流水。三重检验诊断流动化处境，给出从流动物质沉淀出系统搬不走之物的加固方向。 | |
| winson-cognitive-positioning-skill 诊断你在AI时代的认知资产是在积累还是持续失血，定位唯一不可被掠夺的积累路径（信任资本），输出三种资产容器对照图与个人突破方案。 | |
| winson-make-what-lasts-skill 用三本账诊断框架帮builder识别注意力陷阱，从build in public转向in public, build。五问自检+类别偷换检测+什么能留下评估矩阵，让作品、故事、商业各归其位，MAKE WHAT LASTS。
灵感资料来源：Superlinear Academy 立正 | |
| winson-seedance-prompt-skill 把你的创意想法变成即梦 Seedance 2.5 可直接发车的视频提示词。七大场景公式+九种转场技法，从一句话意图到完整提示词，让创作表达不走弯路。 | |
| winson-truth-anchor-skill 拆解任何行业的信任管道，把验证锚点从权威迁移到物理规律。从诊断"打假悖论"到设计消费者自主验证体系，让"信谁"变成"怎么不信"。 | |
| Cursor Prd Generator 当用户说"帮我写 PRD"、"生成需求文档"、"我想做一个功能"、"Cursor 用的 spec"、"cursor-prd"、"生成 FEATURE_SPEC"等时，触发此 skill。接收用户1-3句话的小功能需求，引导澄清后生成结构化 PRD 文件（FEATURE_SPEC.md）和 Cursor 规则片段（... | |
| Paper To Table Extract structured data from academic papers (PDF/DOCX/TXT) into literature review tables (XLSX/CSV) with fidelity, batch support, and multi-domain handling. | |
| Psychology Daily 当用户说"今日心理学动态"、"今日心理学新闻"、"心理学界新闻"、"脑科学新研究"、"神经科学进展"、"心理学前沿"、"最新心理学研究"等时，搜索并整理当日心理学与脑科学领域最新研究发现和新闻，输出10条结构化结果（中英文权威来源结合）。仅输出当日内容。 | |
| Windows Host UI Bridge Bridge: Cross-OS UI automation for Windows Host | |
| Configure File Write And Recovery 如何在网关重启后保持配置文件的修改。TRIGGER 当用户提到配置文件写入、网关重启、配置文件还原、模型添加、多模型配置、配置管理机制、自动还原等问题时。 | |
| Convert Memory Files Between Systems 如何将 memory-lancedb-pro 的记忆文件转换为原版 markdown 格式，并导入到 memos-local-openclaw-plugin 系统中。TRIGGER 当用户提到记忆文件转换、markdown 文件导入、配置文件修改、数据库导入、记忆插件更换、或任何涉及将记忆数据从一个系统迁移到另一... | |
| Create Educational Subagent 如何创建一个教务子 agent 来记录和追踪各个班级的上课进度。TRIGGER 当用户提到创建子 agent 记录课程进度、管理班级上课情况、追踪教学进度、或任何涉及长期记录和追踪任务的需求时。 | |
| Agent Harness Construction Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. | |
| Data Analyst SQL, pandas, and statistical analysis expertise for data exploration and insights. Use when: analyzing data, writing SQL queries, using pandas, performing st... |
6,951–7,000 of 108,824