Skill UI

This skill provides functionality to upscale and enhance the resolution of both images and videos using advanced Artificial Intelligence models. It is useful for improving visual quality, restoring detail, and increasing the clarity of low-resolution media assets for creative and professional use.

This framework analyzes foundational design principles—such as affordances, signifiers, and conceptual models—to create products that are highly intuitive and discoverable. It guides analysis by bridging the 'Gulf of Execution' and the 'Gulf of Evaluation.' Use this when diagnosing confusing user interfaces, poor usability, or needing to ensure a product is robustly human-centered and easy to understand.

A comprehensive skill for generating multimodal media content using fal.ai models. It supports text-to-image (Nano Banana), text/image-to-video (Veo, Kling, Seedance), and text/video-to-audio (CSM-1B, ThinkSound). Use this tool for any creative project requiring high-quality generated images, videos, or sound effects.

Expert skill for creating, editing, and optimizing marketing images using AI generation models (Flux, Midjourney, Ideogram, Gemini, etc.) and design tools. Covers blog heroes, social graphics, product mockups, banners, and brand assets with best practices for prompts, tool selection, and optimization.

This skill acts as an elite art director, generating highly structured, premium, and conversion-aware frontend design references. It is optimized for creating multi-section websites, landing pages, and marketing sites, ensuring consistency and visual appeal across every section. Output is designed to be immediately usable by developers or coding models, adhering to strict composition rules to avoid generic AI aesthetics.

This powerful script uses Nano Banana models to facilitate advanced image creation and manipulation. Users can generate high-quality images from simple text prompts, perform detailed image edits (inpainting/outpainting), or combine multiple images into a single collage. It supports various resolutions and aspect ratios, making it ideal for artists, designers, and anyone requiring advanced visual content generation.

A comprehensive workflow for advanced creative AI tasks, specializing in video and image manipulation. This tool enables image-to-video animation (turning static photos into motion), video-to-video style transfer (applying artistic styles to existing footage), and general creative content generation using models like Gen-3 Alpha Turbo. Ideal for professional video editors and digital artists.

Create marketing videos with AI generation models, AI avatars, and programmatic frameworks. Covers product demos, explainers, social clips, and ads using Remotion, Hyperframes, Veo, Runway, HeyGen, and Synthesia.

A skill designed to generate cinematic, short-form video clips (3-10 seconds) suitable for marketing reveals, product teasers, or ambient loops. It focuses on generating one cohesive shot per request, ensuring high quality and narrative focus for modern video models like Seedance, Kling, and Veo. Ideal for creating impactful, bite-sized visual content.

A sophisticated automated loop that uses vision or video models to evaluate subjective aesthetic quality (e.g., timing, color grade, layout). Instead of relying on numeric metrics, the system renders multiple parameterized variants into one artifact, asks the AI to rate them, and suggests optimal values, repeating the process until convergence. Ideal for design iteration where human judgment is the primary success criteria.

A comprehensive skill for generating multimodal media content using fal.ai models. It supports text-to-image (Nano Banana), text/image-to-video (Veo, Kling, Seedance), and text/video-to-audio (CSM-1B, ThinkSound). Use this tool for any creative project requiring high-quality generated images, videos, or sound effects.

This advanced skill extends standard morph-ppt capabilities by enabling the seamless integration of 3D models (.glb) and advanced visual design elements. It features a robust, intelligent model discovery flow that proactively helps users find compatible 3D assets based on their topic (e.g., product, nature, concept). The system guides the user through searching multiple sources (Sketchfab API, Poly Pizza, Khronos assets) to ensure the final presentation is visually rich, professional, and technically sound.