Agent skill · nvidia
tao-setup
One-time session setup and orchestration map for the TAO skill bank. Run this first when the TAO skills were installed individually (e.g. from a public skills catalog) so the session gets the cross-skill discovery flow, credential checks, and host preflight that the bundled plugin hook would otherwise inject automatically. Trigger phrases include "set up TAO skills", "TAO session setup", "prepare TAO environment", "TAO getting started".
What it needs
About 5k tokens when loaded.
What this skill does
TAO Setup One-time session bootstrap for the TAO skill bank. TAO skills are standalone — each model, data, and platform skill carries its own pinned container image and instructions — but multi-skill workflows chain them (data prep, train, evaluate, deploy). This skill provides the session-level pieces that make that chaining work when skills are installed individually: the discovery flow, the credential conventions, and the host preflight. When the full skill bank is installed as a plugin from this repository, a SessionStart hook injects this guidance automatically and you do not need to run this skill. When skills were installed one-by-one from a skills catalog, run this skill first. Quick Start Individual skill installs do not include the shared scripts/ helpers. Obtain a complete TAO skill bank checkout at the same release ref as the installed skills, then verify it before using any shared helper. If the checkout is elsewhere, set TAOSKILLBANKPATH to its root. Reuse a plugin-provided path when present. If no checkout exists, obtain it with user approval, for example git clone --branch <installed-release-ref> --single-branch https://github.com/NVIDIA-TAO/tao-skill-bank.git <bank-dir>. Point TAOSKILLBANKPATH at that checkout and stop if the helper check fails. If Docker or the NVIDIA host runtime is missing, use the tao-setup-nvidia-gpu-host skill — it checks and (with approval) installs NVIDIA driver 580 or newer, CUDA Toolkit 13.0 or newer, and NVIDIA Container Toolkit 1.19.0 or newer, and can install Docker itself on Debian/RHEL/SUSE-family hosts. These are TAO-wide minimums. If the selected model's references/skillinfo.yaml declares runtimerequirements.gpuhost, pass those model-specific minimums to the host setup skill instead. Credentials Load a user-approved env file with set -a; source /path/to/.env; set +a in the same bash call as the command that consumes the variable. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/tao-setup