全部能力

Home Assistant 集成、加载项、更新和系统操作。当用户询问配置条目、加载项、更新、重新加载/重启或……时使用。

Implement secure file upload handling with validation, virus scanning, storage management, and serving files efficiently. Use when building file upload features, managing file storage, and implementing file download systems.

Statistics, probability, linear algebra, and mathematical foundations for data science

Write comprehensive code documentation including JSDoc, Python docstrings, inline comments, function documentation, and API comments. Use when documenting code, writing docstrings, or creating inline documentation.

Use when connecting to Xcode via MCP, using xcrun mcpbridge, or working with ANY Xcode MCP tool (XcodeRead, BuildProject, RunTests, RenderPreview). Covers…

MindOS 是用户的本地知识助手，也是跨会话、跨 Agent 共享的知识库。它保存决策记录、会议纪要、SOP、 排错经验、架构选型、调研结论和偏好设置。 仅 mindRoot 知识库内任务。不用于：改代码仓库、项目源码、KB 外路径。 核心概念：空间、指令(INSTRUCTION.md)、技能(SKILL.md)；笔记可承载指令与技能。 触发场景：保存或记录任何内容、搜索历史笔记或上下文、更新或编辑文件、整理或重组文件结构、 执行SOP或工作流、捕获对话中的决策、复盘或总结经验、追加表格或CSV数据、跨Agent交接上下文、 提炼经验教训、同步关联文档、查找之前是否讨论过某事、查询历史决策、查找模板或SOP、 为会议准备上下文、快速暂存到暂存台、整理暂存台、知识健康检查、检测知识冲突或矛盾、 查找过期内容。 触发词：帮我记下来、搜一下我的笔记、更新知识库、整理文件、执行工作流、保存到知识库、 记录一下、整理笔记、复盘、提炼经验、同步文档、查一下之前的记录、有没有相关的笔记、 我之前写过什么、把这个存起来、总结一下保存、交接给其他Agent、追加到表格、 放到暂存台、整理暂存台、知识健康检查、检测知识冲突。 主动行为——不要等用户提到 MindOS： (1) 用户的问题暗示可能存在历史记录（过去的决策、之前的讨论、会议纪要）→ 先搜 MindOS， 即使没有明确提到知识库。 (2) 完成有价值的工作后（修了 bug、做了决策、总结了经验、选定了架构、开完了会）→ 主动提议保存到 MindOS，方便以后查阅。 (3) 经历了较长或多主题的对话后 → 建议把关键决策和上下文持久化。

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Expert Shopify theme development guidelines for Liquid, Online Store 2.0, CSS, JavaScript, and UX best practices

Diagnose and improve humor using systems thinking. Use when jokes fall flat, when humor feels forced, when punchlines don't land, or when you want to…

Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.

Guidelines for integrating Figma designs with development workflows using MCP servers and best practices

Design experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets,…

Best practices for scikit-learn machine learning, model development, evaluation, and deployment in Python

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types…

FinnHub financial data API integration for stocks, forex, crypto, news, and fundamentals. Use when fetching real-time quotes, company profiles, financial…

Monitor database performance and health. Use when setting up monitoring, analyzing metrics, or troubleshooting database issues.

Develop production-grade Django applications with models, views, ORM queries, authentication, and admin interfaces. Use when building web applications, managing databases with Django ORM, and implementing authentication systems.

Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities. Use when…

Expert data analysis covering SQL querying, data visualization, statistical analysis, business reporting, and data storytelling. Use when writing SQL queries, building dashboards, performing cohort or funnel analysis, running hypothesis tests, or presenting data-driven recommendations to stakeholders.

Connect Workers to PostgreSQL/MySQL with Hyperdrive's global pooling and caching. Use when: connecting to existing databases, setting up connection pools, using node-postgres/mysql2, integrating Drizzle/Prisma, or troubleshooting pool acquisition failures, TLS errors, or nodejs_compat missing. Prevents 11 documented errors.