Create high-quality images quickly using Pruna's optimized AI models. This skill provides fast, cost-effective image generation and editing through the inference.sh CLI platform.

Create stunning images from text descriptions using Google's latest Gemini 3.1 Flash Image Preview model. Supports text-to-image generation, image editing, multi-image input, and real-time Google Search grounding for current information.

Quickly create images using Google Gemini native image models through a simple CLI interface. This skill provides a convenient wrapper for the inference.sh platform to generate photorealistic images, illustrations, and artwork from text prompts.

Integrate 150+ AI models into JavaScript/TypeScript applications with a unified SDK. Build agents, handle streaming responses, manage file uploads, and implement human approval workflows with full type safety.

Access cloud-based AI inference without managing GPU infrastructure. Execute image generation, video creation, LLM calls, and more through a unified command-line interface.

Create natural-sounding speech in 32 languages with 22+ premium AI voices. Perfect for voiceovers, audiobooks, podcasts, and accessibility without expensive recording equipment.

Creating background music and soundtracks traditionally requires musical expertise or expensive licensing. This skill uses ElevenLabs AI to generate royalty-free original music from simple text descriptions, enabling anyone to create custom audio for their projects.

Creating chat UIs from scratch requires significant time and design effort. This skill provides ready-to-use React components with shadcn/ui styling for rapid chat interface development.

Creating professional AI videos typically requires multiple tools and subscriptions. This skill provides unified access to 40+ video generation models through a single CLI interface.

Creating high-quality AI images often requires multiple tools and subscriptions. This skill provides unified access to 50+ models including FLUX, Gemini, Grok, and Seedream through a single CLI interface.

Stop building chat UIs from scratch. This drop-in Agent component provides streaming responses, tool approvals, and declarative widgets out of the box for Next.js applications.

Access 150+ AI models for image generation, video creation, LLMs, and search through a unified CLI interface. No GPU or API key management required - inference.sh handles cloud execution.

Enable AI assistants to interact with websites, fill forms, extract data, and perform web automation tasks programmatically. Control headless browsers through simple CLI commands with session management and video recording.

AI assistants cannot access current information from the internet. This skill enables web search and content extraction using Tavily and Exa APIs through the inference.sh CLI, allowing Claude, Codex, and Claude Code to gather real-time information and research any topic.

Managing social media accounts manually takes time. This skill automates Twitter/X posting, engagement, and user interactions via a simple CLI interface.

Creating videos from code is complex and time-consuming. This skill enables programmatic video generation by accepting React/Remotion TSX components and returning rendered MP4 files through the inference.sh API.

Need to process data, scrape websites, or generate images but lack local Python setup? This skill executes Python code in a secure sandboxed environment with 100+ pre-installed libraries including Pandas, NumPy, Matplotlib, and BeautifulSoup.

Developers need GPU-free access to AI models for image generation, video creation, and LLM calls. This skill provides a unified CLI interface to 250+ AI apps through inference.sh, enabling AI capabilities without local infrastructure.

Creating AI videos requires managing multiple model APIs and complex video generation workflows. This skill provides a unified CLI interface to generate videos using Google Veo, Seedance 2.0, HappyHorse, Wan, and 40+ other AI video models.

Creating custom images for projects requires expensive subscriptions or complex local setup. This skill connects Claude, Codex, and Claude Code directly to 50+ AI image models through the inference.sh CLI, enabling instant image generation without leaving your development environment.