Skills your agents can run

Conduct pure research for YouTube video topics by analyzing competitors, identifying content gaps, and documenting strategic insights. Use when you need to research a video topic before planning. Produces concise, insight-focused research documents that identify the biggest opportunities for video performance.

Draft high-performing LinkedIn posts using learnings from tweet performance data and 0 Finance messaging guidelines

Anthropic Claude API 的 Python 和 TypeScript 使用模式。涵盖 Messages API、流式处理、工具使用、视觉功能、扩展思维、批量处理、提示缓存和 Claude Agent SDK。适用于使用 Claude API 或 Anthropic SDK 构建应用程序的场景。

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Security standards for Flutter applications based on OWASP Mobile. Use when applying OWASP Mobile security standards or when securing a Flutter application.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides a comprehensive security checklist and proven patterns.

Master Next.js 14+ App Router with Server Components, streaming, parallel routes, and advanced data fetching. Use when building Next.js applications, implementing SSR/SSG, or optimizing React Server Components.

100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.

Provides comprehensive guidance for Axure prototyping tool including wireframing, interactions, dynamic panels, and prototyping. Use when the user asks about Axure, needs to create interactive prototypes, design wireframes, or build complex interactions.

Implement real-time features using WebSockets (Socket.io, ws), Server-Sent Events (SSE), Supabase Realtime, Firebase, or Pusher. Covers presence indicators, live cursors, CRDT-based collaborative editing (Yjs, Automerge), notifications with offline delivery, chat with optimistic rendering, and Redis Pub/Sub backplane for multi-node scaling. Use when adding live updates, chat, collaboration, or any server-to-client or bidirectional communication.

Use when adding interactive 3D scenes from Spline.design to web projects, including React embedding and runtime control API.

Security scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors. Works immediately with zero setup. Optional AST dataflow analysis traces how your data moves through code.

Automate OAuth login flows with user confirmation via Telegram. Supports 7 providers: Google, Apple, Microsoft, GitHub, Discord, WeChat, QQ. Features: - Auto-detect available OAuth options on login pages - Ask user to choose via Telegram when multiple options exist - Confirm before authorizing - Handle account selection and consent pages automatically

Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.

Efficiently extract data from X (Twitter) post URLs. Runs Playwright in headless mode and is designed to minimize memory usage and browser context consumption.

微信公众号文章内容提取工具。使用 agent-browser 从微信公众号文章页面（mp.weixin.qq.com）提取标题、正文、截图等完整内容，支持导出为 Markdown 文档并下载图片到本地。当用户需要访问微信公众号链接、提取微信文章内容、获取微信文章全文、导出微信文章为 Markdown、保存微信文章图片时使用此 skill。

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Product-driven planning with 5 phases - Discover, Specify, Design, Tasks, Implement+Validate+Measure. Creates atomic tasks with verification criteria and maintains persistent memory across sessions. Stack-agnostic. Use when starting projects, planning features, implementing with verification, tracking decisions across sessions. Triggers on "initialize project", "map codebase", "discover", "specify feature", "design", "tasks", "implement", "validate", "measure", "pause work", "resume work".