Browse skills

Liquid Glass creates stunning, realistic reflections and refractions for images, enhancing depth and visual appeal like real glass surfaces.

Generates SVG images from text prompts using the Moai AI model – ideal for creating scalable vector graphics quickly and easily.

Extracts text, tables, and images from PDF documents with high accuracy using advanced visual recognition.

Tuzi Xhs Images — provides AI agent assistance for software development workflows.

Analyzes images to identify artistic style, composition elements, and potential emotional impact using qodex-ai's visual understanding.

Extracts text, tables, and images from PDF documents with high accuracy for writing projects.

Veo Use allows you to generate images based on detailed descriptions of scenes and objects, offering creative visual content generation.

This skill generates diverse variations of images based on Midjourney prompts using Replicate's Flux model, offering rapid creative exploration.

Automatically creates website images, logos, and basic graphics based on text prompts and specified styles.

Enhance blurry or low-resolution images to higher quality using davepoon's specialized AI image upscaling techniques.

Extracts text, tables, images, and metadata from PDFs with high accuracy for seamless content integration.

This AI generates engaging Xiaohongshu cover images quickly, boosting your content's visibility and attracting more followers.

Accurately identifies and extracts project logos from webpages or images using advanced image recognition technology.

Extracts Vault Protocol logos from images or web pages, providing clean assets for marketing and branding purposes.

This skill automatically adds a watermark logo to generated images for branding and copyright protection – a simple way to safeguard your content.

Converts WebP images to JPG format for broader compatibility and easier sharing across different platforms and devices.

Generates unique images from text prompts in various artistic styles using advanced AI models.

Extracts text, tables, and images from Microsoft Word (.docx) files for analysis and content generation.

Extracts text, tables, and images from PDF documents accurately and reliably using advanced OCR technology.

Helps with code generation, Firebase, AI as part of software development workflows workflows.

Generates diverse content formats – text, images, code, music – based on detailed prompts from users.

Gemini Designer generates creative visuals like images and art based on your prompts, boosting design workflows and sparking imaginative concepts.

This skill applies various mantel decor styles to images, instantly elevating their aesthetic appeal and creating visually stunning compositions.

Extracts text, tables, and images from PDFs; summarizes content, answers questions, and converts to other formats.