Image & Video Generation

This skill helps generate and edit images using the Nano Banana 2 model through the poyo.ai service, supporting various resolutions and reference images.

This skill helps users write book manuscripts and academic essays by structuring arguments into modular units.

This skill allows you to generate and edit AI images, videos, and music using various online services through a unified API.

This skill helps you generate and edit images using the Seedream 5.0 Lite model via the poyo.ai API.

This skill gives your AI agent emotions, memory, and a personality that persists between conversations.

This skill helps developers generate code for defining form input fields, validation rules, and localized messages in Swift projects, ensuring consistency across different parts of an application.

This skill helps you generate images using your local ComfyUI software by sending prompts and workflows to a running ComfyUI server on your network.

This skill allows you to manage your Ghost blog posts, including creating, updating, deleting, listing, and uploading images, using its Admin API.

This tool extracts the main content from web articles, such as blog posts and news, and outputs it as clean text.

This skill is designed to help founders, indie developers, and tech professionals with their systematic operations on Twitter.

This skill aims to help AI agents evaluate the health and performance of cryptocurrency resources.

This skill helps you generate and edit images using the Gemini Image API.

This skill helps you generate professional product images for e-commerce platforms by allowing you to specify styles, scenes, and platform requirements.

This skill helps developers generate unit tests, integration tests, and end-to-end tests for React and Next.js applications, analyze code coverage, and set up testing tools like Playwright and Jest.

This skill helps manage your V2Ray proxy, automatically starting, stopping, and configuring it based on your network conditions.

This skill generates AI images from text descriptions using the Labnana API, allowing users to customize the model, resolution, and aspect ratio.

This skill helps you track which services are using specific network ports on your computer and can free up ports if needed.

This skill allows you to adjust the settings for your TradingView trading strategies directly on the chart.

This skill allows you to generate short videos using AI models like Veo3 and Sora2, and check your account credits by connecting to the Vidau service.

This skill helps users design and analyze system architecture by generating diagrams, analyzing dependencies, and assessing project structure.

This skill helps you generate an app store package for a Flutter app, including feature documents, UI design images, and an app icon.

This skill helps you track your mistakes and lessons learned over time to improve your performance.

This skill allows you to generate or edit images using AI models through the OpenRouter service, saving the results to a designated folder.

This skill uses the Kling 3.0 Omni model to generate high-quality videos from text, images, or other videos, supporting various features like audio syncing and editing.