Create stunning AI-generated images using Google Gemini 3.1 Flash Image Preview model. This skill enables text-to-image generation, image editing, and multi-image composition through a simple CLI interface via inference.sh.

Users need an easy way to create AI images using Google Gemini models directly from their terminal. This skill provides commands and examples for generating images with Gemini 3 Pro and Gemini 2.5 Flash via the inference.sh CLI.

Creating professional videos is expensive and time-consuming. This skill enables instant video generation using 40+ AI models including Google Veo, Wan, and Grok through a simple CLI interface.

Create stunning visuals without switching between AI tools. Access 50+ professional image models through a single CLI interface optimized for Claude, Codex, and Claude Code workflows.

Create videos from text, images, or audio using 40+ AI models. Generate social media clips, marketing content, and explainer videos with tools like Veo 3.1, Grok Video, and Wan 2.5.

Creating videos programmatically is complex and requires specialized rendering infrastructure. This skill transforms React Remotion components into MP4 videos through cloud-based rendering, enabling developers to generate videos from code without managing rendering servers.

Create stunning images from text descriptions using Google Gemini 3.1 Flash Image Preview. Edit existing images, combine multiple inputs, and get real-time information grounding through Google Search integration.

Create professional images from text descriptions using Google Gemini native image models. Access high-quality image generation through a simple CLI interface with support for editing and customization.

Transform static images into animated videos using AI models. This guide provides model selection, motion prompting techniques, and camera movement strategies for professional video generation from still images.

Creating social media content across multiple platforms requires different formats, dimensions, and styles. This skill automates AI-powered image and video generation for TikTok, Instagram, YouTube, and Twitter with ready-to-use templates.

Transform text prompts and images into professional videos using cutting-edge AI models like Google Veo, Seedance, and Wan. No video editing skills required - generate marketing content, social media videos, and AI avatars in minutes.

Create professional AI images without complex setup or multiple subscriptions. Access FLUX, Gemini, Grok, Seedream and more through a unified CLI interface.

Creating professional videos requires expensive software and editing skills. This skill provides instant access to 40+ AI video models through simple CLI commands for content creation.

Create professional AI images without learning multiple platforms. Access FLUX, Gemini, Grok, Seedream, and Reve through one unified CLI interface.

Transform React and Remotion TSX code into MP4 videos programmatically. Perfect for developers who want to generate animations, motion graphics, and data-driven videos through code.

Transform React TSX code into professional MP4 videos using Remotion. Programmatic video generation for developers, content creators, and automation workflows.

Creating video animations requires learning specialized video production software and complex rendering pipelines. HyperFrames lets you write HTML to define video compositions, use GSAP for animations, and render professional videos with captions, transitions, and audio.

Design teams spend hours creating UI mockups manually. The Stitch Design skill automates high-fidelity screen generation from text descriptions while maintaining design system consistency.

Teams need fast, consistent walkthrough videos for app screens, but manual editing is slow. This skill automates screen retrieval and Remotion composition to produce ready to render videos with transitions and overlays.

Transform ideas into visual diagrams without manual drawing. Generate professional flowcharts, mind maps, and architecture diagrams as editable Excalidraw files.