OpenClaw · Skills: AI & machine learning

NVIDIA skill for locking or capping Jetson CPU, GPU, and EMC clocks before flashing.

NVIDIA skill for taking a health snapshot of a Jetson without changing anything.

NVIDIA skill for choosing serving stacks and memory flags for LLMs on Jetson.

NVIDIA skill for benchmarking LLM and VLM serving speed on Jetson across three runtimes.

NVIDIA skill for launching LLM serving with SGLang or vLLM on Jetson.

NVIDIA skill to free Jetson DRAM by switching off unused subsystems.

NVIDIA skill for picking Jetson-compatible containers, vLLM images, and AI Lab package indexes.

NVIDIA example skill that prints details of a running Jetson.

NVIDIA skill for enabling speculative decoding with EAGLE-3 on a Jetson vLLM server.

NVIDIA skill for extending KERMT pretraining with your own SMILES data.

NVIDIA skill for extracting per-molecule embeddings from KERMT encoder checkpoints.

NVIDIA skill for training a pretrained KERMT encoder with your labeled CSV data.

NVIDIA skill for pretraining a brand-new KERMT model on a corpus you provide.

NVIDIA skill for bootstrapping the KERMT environment with Docker, GPU checks, and the image.

Researches a topic across social platforms and forums, ranking findings by engagement.

Researches a topic across social platforms and forums, ranking findings by engagement.

NVIDIA playbook for running NeMo-RL on Kubernetes, from launch through debugging.

AWS skill for operating MSK Provisioned clusters with Standard and Express brokers.

Creates and manages AI agent tasks through the Manus API.

Patterns for using the Mapbox MCP DevKit server inside AI coding assistants.