AI Agent Skills

Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch,…

A fully self-contained, offline AI image generation studio for Windows. Runs Stable Diffusion (Safetensors/GGUF) locally with zero manual setup. Auto-configures CUDA for…

Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process i…

Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux or Windows, then applies a low-risk fix with consent or hands back the e

Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions. Detects 10…

Setup Ubuntu 18.04, 16.04 and 14.04 with machine learning and robotics software plus user configuration. Includes ceres tensorflow ros caffe vrep eigen cudnn and cuda pl…

Run an arbitrary Hugging Face safetensors model on an Intel GPU using **upstream PyTorch** (>= 2.8) with the built-in `torch.xpu` device. Covers loading from the Hub, pi…

Launch a Docker container with Intel GPU access on Linux. Encodes the correct combination of `--device /dev/dri`, render-group access, `--ipc=host`, `ZE_AFFINITY_MASK` p…