What is tao-run-automl?

A container-based workflow for automatically testing different settings for NVIDIA TAO machine-learning models and comparing their results.

Use it to run hyperparameter optimisation, track experiments with Weights & Biases, launch model jobs, and interpret or evaluate the results.

It handles repeated experiments and only starts them after the model, platform, data, credentials, container, and computing resources are checked.

tao-run-automl — Skill for Claude Code by NVIDIA-TAO

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add NVIDIA-TAO/tao-skill-bank --skill tao-run-automl

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bank

Made for: Claude Code.

Or install tao-skills, the plugin that ships this one along with the rest of its 76 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-automl/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-automl)

Your own site

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-automl"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-automl/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-automl"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-automl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 235 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,449 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00235	$0.04449
Opus 5	$0.00118	$0.02225
Sonnet 5	$0.00047	$0.00890
Haiku 4.5	$0.00023	$0.00445

Measured 8d ago against content hash 0a2c969473b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tao-run-automl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (references/best_rec_adapter.py, references/tests/test_best_rec_adapter.py, scripts/resolve_automl_session.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/applications/tao-run-automl/SKILL.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

The selected model skill under skills/models/<model_skill>/.
The selected platform skill under skills/platform/<platform>/.
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 automl-examples.md for conversation examples; and automl-common-pitfalls.md for recurring safety checks. detailed-guide.md is only the map.
skills/models/<network>/SKILL.md: model-specific dataset requirements, metrics, HPO notes, checkpoint handoff, and known failures.
skills/models/<network>/references/skill_info.yaml: action contract, container image, inputs, outputs, upload exclusions, and mode.
skills/platform/<platform>/SKILL.md: selected platform preflight, credentials, resource shape, monitoring, and cancellation.
skills/core/tao-launch-workflow/SKILL.md: shared intake pattern for platform, credentials, dataset visibility, image confirmation, and user confirmation.

Read the full file on GitHub · 407 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago Changed · +1 lines 0a2c969473b7
12d ago First seen · 406 lines · 235 tokens per session scan A 52d9e29977c6

Subscribe to this mod's changes

tao-run-automl is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 235 tokens to every session and 4,449 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI LLM Optimization Training automl hpo workflow

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens

ml-training-recipes

OpenRaiser/NanoResearch · 88 tokens

ml-training-recipes

TTAWDTT/elegant-researcher-skill · 88 tokens

trulens-evaluation-workflow

Systematically evaluate your LLM application with TruLens.

truera/trulens · 18 tokens

using-model-endpoint

Call a registered model endpoint over its native HTTP API from the endpoint's scoped inference kernel (BASEURL preloaded). Load once a task needs predictions from a registered model endpoint.

UnicomAI/wanwu · 40 tokens

managed-model-endpoints

Register a model service in the managed family — a local model server container the daemon starts/stops on demand, or a remote upstream model API (https). Read the runbook, allocate a port (local only), compose idempotent start/stop scripts (local only), register once. Load when the user wants a model service…

UnicomAI/wanwu · 83 tokens

tao-run-automl

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

TAO AutoML

Execution Runtime — Hard Gate

Reference Map

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

ml-training-recipes

ml-training-recipes

ml-training-recipes

trulens-evaluation-workflow

using-model-endpoint

managed-model-endpoints