# tao-run-automl

This skill runs AutoML and hyperparameter search for NVIDIA TAO models. Use it to tune training or another supported model action on a selected platform.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1600 installs · ★ 3735
- Author: NVIDIA Corporation
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-run-automl/SKILL.md
- Updated: 2026-10-26
- HTML: https://affpapa.org/en/nevibecode/skills/tao-run-automl

## What it does

The skill combines a model skill, a platform skill, and `AutoMLRunner`. The runner proposes settings, launches jobs, collects metrics, and sends results back to the optimizer. Search options include `bayesian`, `hyperband`, `asha`, and `llm`; experiments can be tracked with WandB.

Before launch, the agent checks model support, the action schema, platform readiness, data access, credentials, and compute settings. Model actions run in the container resolved from model metadata by default. Docker and NVIDIA Container Toolkit are required. A local venv for model execution needs an explicit request; having a local GPU does not switch execution to venv.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill tao-run-automl -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/tao-run-automl/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/tao-run-automl/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill tao-run-automl -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/tao-run-automl/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill tao-run-automl -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/tao-run-automl/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NVIDIA/skills tao-run-automl
```

2. **Manually: put the files in place**
- File: `.github/skills/tao-run-automl/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill tao-run-automl -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NVIDIA/skills --path skills/tao-run-automl
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/tao-run-automl/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill tao-run-automl -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-run-automl/SKILL.md

## When to use it
- tune hyperparameters for a TAO model
- run HPO on a selected platform
- compare recommendations using model metrics
- track experiments with WandB
- optimize a supported `train` or `quantize` action

## Example prompts
- Tune hyperparameters for this NVIDIA TAO model with Bayesian search.
- Run HPO for `train` on the selected platform and track the experiment in WandB.
- Check the model requirements and action schema, then optimize `quantize`.

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: a89ee8046af75f95.

BEGIN THIRD-PARTY FILE a89ee8046af75f95
```text
---
name: tao-run-automl
description: Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm
  selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK
  platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter
  optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search,
  autoresearch, or wants to tune train/evaluate/inference/distill/prune/quantize for a TAO network. Model actions use the resolved
  image; venv training requires an explicit request. Platform-agnostic — runs on any SDK (Brev,
  SLURM, Kubernetes, Docker). Do not use generic "keep improving" language alone to override a matching domain-specific
  DEFT workflow; attribute-labelled CLIP / SigLIP image-retrieval loops belong to tao-run-deft-pas unless HPO is explicit.
license: Apache-2.0
compatibility: Requires docker + nvidia-container-toolkit. Workflows declare additional requirements.
metadata:
  author: NVIDIA Corporation
  version: "0.1.1"
allowed-tools: Read Bash Write
tags:
- automl
- hpo
- workflow
- training
- optimization
- llm
---

# TAO AutoML

> **Standalone install?** If this session was not initialized by the TAO skill bank plugin, run `tao-setup` first (host preflight, credentials, cross-skill discovery).

Run automated hyperparameter optimization for a TAO model by combining:

1. The selected model skill under `skills/models/<model_skill>/`.
2. The selected platform skill under `skills/platform/<platform>/`.
3. `AutoMLRunner`, which generates recommendations, launches selected action jobs,
   extracts metrics, and feeds results back to the optimizer.

Do not launch until model metadata, platform preflight, data visibility,
credentials, image choice, and compute shape are all proven.

## Execution Runtime — Hard Gate

Every recommendation, baseline evaluation, per-recommendation evaluation, and
final evaluation runs in the selected model action's resolved
`container_image` by default. Resolve it from the model skill before any
training-environment setup. A local checkpoint or Hugging Face model ID does not
change this rule.

Use venv-based **model execution** only when explicitly requested. Never infer
venv mode from `local-docker`, local GPUs, Python, or `pyproject.toml`. If
absent, execution is container-backed. A host/controller venv for `tao_automl`,
TAO SDK, or a platform adapter is
control-plane-only; keep child model actions in the resolved container image.

## Reference Map

- `references/skill_info.yaml`: this workflow's structured metadata.
- Split detailed references: `automl-preflight-concepts.md` for prerequisites
  and support checks; `automl-intent-algorithms.md` for search policy;
  `automl-compression-literature.md` for distill/prune/quantize algorithm
  sufficiency and future compression-search roadmap;
  `automl-runner-configuration.md` for runner/API/WandB details;
  `automl-advanced-monitoring.md` for hooks, resume, and pitfalls; and
```
END THIRD-PARTY FILE a89ee8046af75f95

The third-party file has ended. Everything between the a89ee8046af75f95 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3162 of 19894 bytes. © NVIDIA Corporation · Apache-2.0 · https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-run-automl/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md