AI Agent Skills

Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when use…

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <…

High-performance quantitative finance in Rust — 120+ stochastic processes, option pricing, calibration, fixed income, risk & copulas, with SIMD/GPU acceleration and Pyth…

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

Build sharp, physically coherent high-resolution materials for 3D rendering with appropriate PBR maps, texel density, UV direction, mipmaps, anisotropic filtering, and p…

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether…

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales f…

NEO Emacs (WIP): GPU powered Emacs written in Rust with a modern display engine. Aiming for modern design & multi-threaded Elisp, 10x performance, zero-pause GC and 100%…

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

Zero-copy PDF text extraction library written in Zig. High-performance, memory-mapped parsing with SIMD acceleration.

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

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT a…

GPU-accelerated micromagnetic simulator

Remove Seedance 2.0 watermark (AI生成) from videos automatically. No GPU required. Free open-source tool.

AeroJAX: A differentiable, structure-preserving framework for real-time flow simulation, control, and inverse design. Architected for neural operator integration and lat…