Skill UI

Accelerate wraps PyTorch scripts with a four-line integration so you can launch DDP, DeepSpeed, FSDP, Megatron, or mixed-precision training on any hardware via a single command, handling device placement, sharding, and automatic config generation.

Automates Ollama installation, model selection, and integration so you can run self-hosted LLMs offline on macOS, Linux, or Docker with curated hardware guidance, Python/Node.js clients, and REST API verification.

Provides the official Opentrons Protocol API v2 guidance for writing, loading hardware, and executing automated liquid-handling protocols on OT-2 and Flex robots, including module control, labware setup, and advanced pipetting flows.

PennyLane is a hardware-agnostic quantum ML framework that lets you train parametrized quantum circuits with automatic differentiation, build hybrid quantum-classical models, and switch between simulators and hardware with tight PyTorch/JAX/TensorFlow integration.