llamaindex

BLIP-2 is a vision-language framework that connects a frozen image encoder with a large language model for multimodal tasks. Use it for zero-shot image captioning, visual question answering, or image-text retrieval without task-specific fine-tuning. It's ideal for developers needing to add state-of-the-art visual understanding to LLM-based applications.

SGLang is a high-performance LLM serving framework that uses RadixAttention for automatic prefix caching, enabling significantly faster structured generation. It's ideal for developers needing JSON/regex outputs, constrained decoding, or building agentic workflows with tool calls. Use it when you require up to 5× faster inference than alternatives like vLLM in scenarios with shared prefixes.

This skill enables text-to-image generation and image manipulation using Stable Diffusion via HuggingFace Diffusers. It supports image generation from prompts, image-to-image translation, inpainting, and custom pipeline creation. Developers should use it when building applications requiring AI-powered visual content generation or editing.

This Claude Skill provides text-to-music and text-to-audio generation using Meta's AudioCraft PyTorch library. It enables developers to generate music from descriptions, create sound effects, and perform melody-conditioned music generation. Key capabilities include using the MusicGen and AudioGen models for controllable, high-quality stereo audio output.