agent

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…

Use when you need to act as an Elite Software Architect (Maestro) to manage complex repositories. It enforces a "Why over How" philosophy, maintains a…

Enforces constrained, opinionated styling patterns for gluestack-ui v4. Main overview skill that coordinates specialized sub-skills for setup, components,…

Auth.js v5 setup for Next.js authentication including Google OAuth, credentials provider, environment configuration, and core API integration

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security,…

在用户使用 Freqtrade 时调用 — 策略创建、回测、超参数优化、切换策略/交易对/模拟模式、查询实盘机器人状态/余额/…

Audit web pages for performance optimization following PageSpeed Insights guidelines. Use when analyzing page performance, optimizing web applications,…

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

Deployment automation specialist for CI/CD pipelines and infrastructure. Use when setting up deployment, configuring CI/CD, or managing releases.

Performance optimization specialist for improving application speed and efficiency. Use when investigating performance issues or optimizing code.

Expert in CrewAI - the leading role-based multi-agent framework

使用 Vercel AI SDK v6 稳定版构建后端 AI。涵盖 Output API（替代 generateObject/streamObject）、语音合成、转录、嵌入、MCP 工具及安全指南。包含 v4→v5 迁移和 15 种错误解决方案及变通方法。适用场景：实现 AI SDK v5/v6、版本迁移、排查 AI_APICallError、Workers 启动问题、Output API 错误、Gemini 缓存问题、Anthropic 工具错误、MCP 工具或流恢复失败。

使用 HTML/CSS/JavaScript/React 构建高质量的可视化 Web 产物——包括网页、落地页、仪表盘、交互式原型、HTML 幻灯片、动画演示、UI 模型、数据可视化等。当用户的请求涉及可视化、交互式或前端交付物时，请使用此技能，包括： - 创建网页、落地页、仪表盘、营销页面 - 构建交互式原型或 UI 模型（带设备边框） - 构建 HTML 幻灯片/演示文稿 - 创建 CSS/JS 动画或基于时间轴的动画演示 - 将设计模型、截图或 PRD 转换为交互式实现 - 数据可视化（Chart.js / D3 等） - 设计系统 / UI Kit 探索 即使用户没有明确提及“HTML”或“网页”，只要其意图是生成可视化、交互式或用于展示的内容，均适用此技能。 不适用场景：纯后端逻辑、CLI 工具、数据处理脚本、非可视化代码任务、命令行调试。

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to…

Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization. Use when implementing…

检测 LaunchDarkly SDK 集成的仓库技术栈：语言、框架、包管理器、monorepo 目标、入口点、现有 LD 使用情况。嵌套…

Develop applications using the Docyrus API with @docyrus/api-client and @docyrus/signin libraries. Use when building apps that authenticate with Docyrus OAuth2…

AI-powered penetration testing assistant using local LLM (metatron-qwen via Ollama) on Parrot OS Linux

Choose the right Zoom architecture for a use case. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP,…

Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use…