AI Agent Skills

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

A hardware-aware Codex skill for local MiniMax H3 video generation through ComfyUI

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic…

Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs

Libva is an implementation for VA-API (Video Acceleration API)

Self-host the ultra-lightweight Kitten TTS model with this enhanced API server with an intuitive Web UI, large text processing for audiobooks, and GPU acceleration.

The self-hosted AI workstation. Autonomous screen agents, 3-tier neural routing, parallel agent swarms, video generation, 4K/8K upscaling, RAG, voice interface, 70+ tool…