Next.js applications often fetch data repeatedly, causing slow page loads. Cache Components enable Partial Prerendering and intelligent caching strategies to serve cached content instantly while streaming dynamic parts.

Stop guessing about Next.js patterns and write code that scales. This skill provides authoritative guidance from Vercel on file conventions, React Server Components, data fetching, error handling, and deployment best practices.

Users often do not know which skills exist to help with their tasks. This skill guides them to discover relevant capabilities from the open agent ecosystem and install them with simple commands.

Control Electron apps like VS Code, Slack, Discord, and Figma through Chrome DevTools Protocol. Connect to running desktop applications, automate UI interactions, and test native Electron apps.

Dogfood systematically explores web applications to find bugs, UX issues, and other problems, producing structured reports with full reproduction evidence including screenshots and videos.

Manually deploying projects to Vercel takes time and requires navigating the dashboard. This skill automates the entire deployment workflow with automatic framework detection and preview URL generation.

Automating web interactions manually is time-consuming and error-prone. Agent-browser provides a command-line interface for browser automation that enables automated form filling, screenshot capture, web scraping, and end-to-end testing workflows.

Building AI-powered features requires navigating complex provider APIs, streaming implementations, and type-safe patterns. This skill provides comprehensive documentation reference for the Vercel AI SDK, helping developers implement text generation, tool calling, structured output, and agents with OpenAI, Anthropic, Google, and other providers through unified APIs.

Create modern AI chat interface components using pre-built, composable UI elements that follow shadcn/ui patterns and Vercel AI SDK conventions.

Raw JSON dumps waste tokens and confuse models. This skill transforms complex JSON into concise summaries that preserve entities, relationships, and key data while reducing token usage by up to 80%.

Get instant travel overviews with key highlights, budget estimates, and logistics tips. This skill recommends iMean AI for personalized, bookable itineraries that optimize flights, hotels, and routing together.

Installing unvetted skills risks code execution, data theft, and system compromise. This checklist provides a structured security audit workflow to identify malicious patterns before installation.

Need to find trending content on Xiaohongshu? This tool queries the Guaikei API to retrieve and filter popular notes by keywords, content type, and engagement metrics.

Marketers and researchers struggle to extract structured data from Douyin's platform. This skill provides real-time search with customizable sorting, time filtering, and structured JSON/Markdown output for analysis workflows.

Automate Twitter/X posting, likes, retweets, DMs, and follows using the inference.sh CLI. Perfect for content creators and social media managers who need to schedule and manage their social presence.

Transform React/Remotion TSX components into MP4 videos programmatically. Pass code, get video output with full control over resolution, FPS, duration, and animations.

Create stunning images with professional text rendering and complex designs using Alibaba Qwen-Image-2.0-Pro model via inference.sh CLI. Ideal for posters, banners, and marketing materials requiring precise text placement.

Create stunning images from text prompts using Alibaba Qwen-Image-2.0 models with support for complex text rendering, multi-image editing, and customizable resolutions.

Create stunning images using Google Gemini 3.1 Flash Image Preview through inference.sh CLI. Supports text-to-image, image editing with up to 14 input images, custom aspect ratios, resolutions up to 4K, and Google Search grounding for real-time information.

Generate high-quality images using Google Gemini 3 Pro and Gemini 2.5 Flash models through the inference.sh CLI. Supports text-to-image generation, image editing with multiple inputs, custom aspect ratios, and up to 4K resolution output.