全部能力

使用 Node/TypeScript SDK 构建 MCP 服务器 — 工具、资源、提示词、Zod 验证、stdio 与 Streamable HTTP。使用 Context7 或官方 MCP 文档获取最新…

JetBrains Exposed ORM 模式，包括 DSL 查询、DAO 模式、事务、HikariCP 连接池、Flyway 迁移和 repository 模式。

Playwright modern end-to-end testing framework with cross-browser automation, auto-wait, and built-in test runner

全面的代码审查，重点关注安全性、性能和最佳实践。适用场景：审查代码、执行安全审计、检查代码质量、审查 pull request，或用户提及代码审查、PR 审查、安全漏洞、性能问题时。

Multi-engine web search — aggregate results from multiple search providers

在创建或增强任何 ADK agent 项目之前必须阅读。当用户想要构建新 agent（例如"帮我构建一个搜索 agent"）或增强现有项目（例如"为我的项目添加 CI/CD"、"添加 RAG"）时使用。

部署任何 ADK 智能体之前必读。ADK 部署指南 — 涵盖 Agent Engine、Cloud Run、GKE、CI/CD 流水线、密钥管理、可观测性及生产工作流。适用于将智能体部署到 Google Cloud 或排查部署问题。不适用于 API 代码模式（请使用 adk-cheatsheet）、评估（请使用 adk-eval-guide）或项目脚手架（请使用 adk-scaffold）。

Essential tools and frameworks for modern product management, from discovery to delivery.

Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that…

经实战检验的 Playwright 模式，用于编写、调试和扩展可靠的测试套件。适用于需要 E2E、API、组件、视觉等测试指导的场景。

Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.

设计测试策略和测试计划。通过“how should we test”、“test strategy for”、“write tests for”、“test plan”、“what tests do we need”触发，或在……时触发。

Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.

Use when building Next.js 14+ applications with App Router, server components, or server actions. Invoke to configure route handlers, implement middleware, set…

优化智能体上下文设置。适用于以下场景：启动新会话、智能体输出质量下降、在不同任务间切换，或需要配置…

Go 数据库访问全面指南。涵盖参数化查询、结构体扫描、NULLable 列处理、错误模式、事务、隔离级别……

(Mobile-First · Touch-First · Platform-Respectful)

通过评估驱动开发改进AI应用。定义评估标准、为应用埋点、构建黄金数据集、观测并评估应用运行情况、分析结果，并制定具体的改进行动计划。当用户要求为任何调用LLM模型的Python项目设置QA、添加测试、添加评估、执行评估、基准测试、修复错误行为、提升质量或进行质量保证时，务必使用此技能。

运行事件响应工作流——分诊、沟通并撰写事后复盘。可通过“我们有故障”、“生产环境宕机”、或需要处理的警报来触发……

Game development orchestrator. Routes to platform-specific skills based on project needs.