NVIDIA Model Config Skill

Overview

This skill packages three reusable pieces:

1. A script (scripts/merge_nvidia_config.py) that inserts the NVIDIA provider block into any openclaw.json file and configures apiKey as a SecretRef by default.
2. Model entries for Mixtral, Moonshot Kimi, Kimi K2.5, Nemotron Super (1M ctx), Llama 3.1 Nemotron Ultra 253B (128K ctx), and MiniMax M2.5 (204.8K ctx) — delete extras or add more from openclaw models list --provider nvidia --all.
3. Instructions for backups, secrets, and where NVIDIA_API_KEY must be set so the gateway can resolve it (this is not only openclaw.json).

Use the skill whenever you want to replicate the NVIDIA models.providers.nvidia entry without guessing which keys or nested objects to copy.

Quick start

1. Copy or download this skill (e.g., rsync -av skills/nvidia-model-config /path/to/other/workspace/skills/).
2. Obtain your NVIDIA API key and keep it secret (do not commit it).
3. Run the script from the target workspace: