local-llm-expert

This skill enables AI agents to persistently index and intelligently query video content from platforms like YouTube and TikTok using Memories.ai's LVMM. It's designed for building searchable video knowledge bases, analyzing social media trends, or summarizing lectures and meetings. Developers should use it when their applications require deep, reusable analysis of video content rather than one-time processing.

This skill provides expert guidance on deploying and optimizing local LLMs using tools like Ollama, llama.cpp, and vLLM. It helps developers select models, manage VRAM, and apply quantization formats (GGUF, EXL2) for efficient local inference. Use it when planning hardware requirements or implementing privacy-focused AI solutions on local hardware.

This skill enables AI agents to persistently search, import, and analyze video content from platforms like YouTube and TikTok using Memories.ai's Large Visual Memory Model. It's designed for building searchable video knowledge bases, summarizing recordings, or researching social media trends. Developers should use it when their Claude agent needs to query indexed video content repeatedly rather than performing one-time analysis.

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.