Browse skills

Automatically optimizes expo website assets (images, bundles) for faster loading and improved user experience.

Transforms images into fun, stylized stickers with customizable text and backgrounds using stvlynn's unique aesthetic.

Automatically generates engaging video presentations from text prompts, images, and data using professional templates.

This skill restores old or damaged photos using AI, bringing back cherished memories and improving image quality effortlessly.

The Visualizer skill generates images based on textual descriptions, offering a quick and intuitive way to create visuals for your projects.

Helps with OpenAI, image processing as part of software development workflows workflows.

Generates brand-aligned images and graphics automatically, ensuring a unified visual identity across all platforms for seamless branding.

Authkit generates unique, high-quality image tokens from your existing images for seamless AI art generation and content creation.

Automatically generates RedBook-style lifestyle content based on provided keywords and image assets for UX testing.

Analyzes ideogram generation prompts & outputs to identify errors, biases, and areas for improvement in AI image creation.

Helps with API, OpenAI, image processing as part of software development workflows workflows.

Analyzes image flux data to infer subtle changes and predict future states using advanced statistical modeling.

This skill manages container registries, streamlining deployment by storing and versioning your Docker images for easy access and updates.

Helps with OpenAI, image processing as part of building AI and machine learning applications workflows.

Forge-Town's generate-preview quickly creates realistic image previews of your town designs based on textual descriptions.

Provides image processing guidance and assistance for software development workflows.

Helps with image processing, optimization as part of agent workflows workflows.

This skill generates CLIP-aware embeddings for images and text, enabling powerful semantic search and similarity matching across diverse content.

This tool analyzes images for sufficient color contrast to ensure accessibility and readability, improving visual content quality.

Provides image processing guidance and assistance for software development workflows.

Generates creative images from text prompts, offering diverse artistic styles and detailed visual representations for various needs.

Helps with OpenAI, image processing as part of software development workflows workflows.

Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs. Works with Gemini, GPT Image, Midjourney, DALL-E, Flux, and Stable Diffusion.

Z-Image Manga/Illustration Generation using local ComfyUI. High-quality anime/manga art with quick preview and high-res upscale modes. No cloud API needed.