Browse skills

Official vercel-labs skill for software development workflows.

Ralph GPU accelerates complex computations by leveraging powerful GPUs, boosting performance for demanding tasks and data processing.

Provides optimization guidance and assistance for software development workflows.

Typegpu — provides AI agent assistance for software development workflows.

Gpui Kit — provides AI agent assistance for software development workflows.

PyTorch FSDP accelerates large model training by intelligently distributing data across multiple GPUs, boosting efficiency and reducing memory footprint.

Davila7's modal-serverless-gpu enables rapid deployment of GPU-accelerated workloads on Modal without server management.

This skill enables rapid prototyping of interactive 3D web applications using WebGPU, ThreeJS, and TypeScript for efficient rendering.

WebGPU enables developers to accelerate graphics and compute workloads on modern browsers using GPU hardware, boosting performance for demanding applications.

This skill provides detailed WebGPU specifications documentation for developers, aiding in understanding and implementing this cutting-edge graphics API.

Leverages Lambda Labs’ GPU cloud for accelerated computing tasks, offering scalable and cost-effective processing power.

This skill lets you seamlessly launch and manage RunPod cloud GPUs for AI development, accelerating your projects with powerful compute resources.

Analyzes GPU utilization and identifies performance bottlenecks during AI model training and inference tasks.

Helps with server, management as part of software development workflows workflows.

Typegpu — provides AI agent assistance for software development workflows.

Provides AI guidance and assistance for software development workflows.

Metal Gpu — provides AI agent assistance for software development workflows.

Typegpu — provides AI agent assistance for software development workflows.

Together Gpu Clusters — provides AI agent assistance for software development workflows.

Athola's cpu-gpu-performance analyzes system resource utilization to identify bottlenecks and optimize application performance.

Monitors GPU utilization across your infrastructure, providing real-time insights to optimize performance and resource allocation.

Leverages Lambda Labs' GPU cloud for accelerated AI model training and inference, boosting performance and accessibility.

Accelerates Rust code execution on GPUs using CUDA/Metal for computationally intensive backend tasks.

Provides Kubernetes guidance and assistance for software development workflows.