Creating programmatic videos from React code requires specialized tooling and rendering infrastructure. This skill wraps the inference.sh service to accept TSX code and return MP4 videos, enabling Claude Code to generate animated graphics without manual video editing.

Need to execute Python scripts but lack local environment setup? This skill lets Claude execute Python code in a secure sandbox with 100+ pre-installed libraries, handling data processing, web scraping, image manipulation, and automation tasks without requiring local configuration.

Running AI models locally requires expensive GPUs. This skill provides CLI access to 250+ AI apps including image generation, video creation, and LLMs through inference.sh.

Creating professional AI-generated videos requires navigating multiple APIs and model providers. This skill simplifies video generation by providing ready-to-use commands for Google Veo, Seedance, Wan, and dozens of other AI video models through the inference.sh CLI.

Creating AI-generated images requires working with multiple model APIs and complex parameters. This skill provides a unified CLI interface to FLUX, Gemini, Grok, and other image generation models through the belt tool.

Creating professional AI avatar videos requires combining multiple tools and services. This skill provides CLI commands and workflows for generating talking head videos using inference.sh, enabling AI presenters, explainer videos, and dubbing workflows.

Access hundreds of AI models for image generation, video creation, text processing, and automation without managing GPU infrastructure or API integrations.

AI agents need to interact with web pages but lack browser capabilities. This skill provides headless browser automation through simple shell commands, enabling web scraping, form filling, and automated testing workflows.

This skill provides access to the inference.sh CLI platform, which lets you run over 150 AI applications without requiring local GPU resources. Generate images with FLUX, create videos with Veo, query LLMs like Claude and Gemini, perform web searches, and automate Twitter posts through simple bash commands.

Manual browsing workflows are slow and error prone. This skill automates navigation, form entry, and capture so teams can repeat web tasks consistently.

Agents struggle to render complex user interfaces. This skill lets Claude generate rich interactive React components from simple JSON structures.

Finding accurate information online and extracting relevant content from web pages is time-consuming. This skill connects Claude to powerful AI search engines like Tavily and Exa for instant research and content extraction.

Managing Twitter/X presence requires repetitive posting and engagement tasks. This skill automates tweets, likes, retweets, DMs, and follows through the inference.sh CLI platform.

Building AI agents that call tools requires clear UI feedback for users. These React components provide ready-made interfaces for showing tool lifecycle states from pending through results.

Creating videos programmatically requires complex rendering infrastructure. This skill transforms your React/Remotion TSX components into MP4 videos instantly via the inference.sh platform.

Create high-quality images with accurate text display using Alibaba's advanced Qwen-Image-2.0-Pro model. Perfect for marketing materials, posters, and designs requiring precise text control.

Create AI-generated images and edit existing photos using Alibaba's Qwen-Image-2.0 models through Claude Code. Generate artwork, product photos, posters, and complex text overlays directly from natural language descriptions.

Integrate 150+ AI models into your Python applications with a unified SDK. Build agents, run inference, and automate workflows with sync, async, and streaming support.

Running Python code locally requires setting up environments and managing dependencies. This skill provides instant access to a pre-configured Python environment with 100+ libraries ready to use.

Create high-quality videos from text prompts or images using optimized AI models. Pruna's optimized P-Video and WAN models deliver fast inference without quality loss.