What is tao-train-mask-auto-encoder?

A guide for Masked Auto-Encoder training, a self-supervised method that hides parts of images and teaches a model to reconstruct them. It supports pretraining and later fine-tuning for a visual model backbone.

Use it to pretrain, fine-tune, evaluate, export, or run inference with a TAO MAE model. Inference means applying the trained model to new input.

It lets a model learn useful visual representations from images before adapting it to a specific task, reducing reliance on manually labelled data during pretraining.

tao-train-mask-auto-encoder — 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-train-mask-auto-encoder

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-train-mask-auto-encoder/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-train-mask-auto-encoder)

Your own site

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

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,758 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	$0.00103	$0.02758
Opus 5	$0.00051	$0.01379
Sonnet 5	$0.00021	$0.00552
Haiku 4.5	$0.00010	$0.00276

Measured 12d ago against content hash fbcf769eefbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tao-train-mask-auto-encoder 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 12d ago.

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/models/tao-train-mask-auto-encoder/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAE

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

MAE (Masked Autoencoder) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations. Supports pretrain and finetune stages.

Set train.pretrained_model_path for pretrained MAE weights when fine-tuning.

For TAO Deploy TensorRT actions (gen_trt_engine), read references/tao-deploy-mask-auto-encoder.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix.

The parent PyTorch mae CLI supports train, evaluate, inference, and export. Build TensorRT engines through the deploy workflow, not the model skill.

Dataclass Schemas

Generated TAO Core schemas are packaged in schemas/<action>.schema.json, with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. AutoML enablement is declared at the model layer in references/skill_info.yaml via automl_enabled. Runnable AutoML for an action requires schemas/<action>.schema.json and references/spec_template_<action>.yaml to exist and parse. Use the packaged selected-action schema for automl_default_parameters, automl_disabled_parameters, defaults, min/max bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect ~/tao-core at runtime; maintainers regenerate schemas/templates before packaging the skill bank.

Train Action Policy

This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skill_info.yaml and resolve the run override from either an explicit automl_policy value or the user's workflow request. Use automl_policy: on by default and only expose on / off in new launch prompts. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as automl_policy: off for this run only. When automl_policy: on, automl_enabled: true, and both schemas/train.schema.json and references/spec_template_train.yaml are packaged, route the train action through tao-skill-bank:tao-run-automl by default with this model's skill_dir. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and automl_policy. Use direct model training only when automl_policy: off or the packaged train schema/template is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.

Read the full file on GitHub · 199 lines

Files

What ships with it

19 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.

12d ago First seen · 199 lines · 103 tokens per session scan A fbcf769eefbe

Subscribe to this mod's changes

tao-train-mask-auto-encoder is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 103 tokens to every session and 2,758 once invoked, about $0.0005 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 learning self supervised

learning-notes-automation

A workflow for turning videos, podcasts, and articles into structured learning notes. It extracts key ideas and creates flashcards that can be imported into Anki, a spaced-repetition study app.

chubbyguan/chubbyskills · 58 tokens

adopt-pattern

Use when a developer wants to apply a low-level, systems, or concurrency design pattern in their own code, drawing on the Battle-Tested Patterns catalog of 46 production-proven patterns. Triggers three ways: they name a pattern (ring buffer, circuit breaker, actor model, LRU cache, rate limiter, trie, bloom filter…

Totoro-jam/battle-tested-patterns · 151 tokens

audit-pattern

Use when reviewing or auditing an existing codebase against production-proven implementation patterns — checking whether the patterns it already implements (actor model, rate limiter, circuit breaker, LRU cache, write-ahead log, semaphore, ...) actually honor the canonical invariants, whether any are mislabeled (a…

Totoro-jam/battle-tested-patterns · 149 tokens

ai-ml-v2

AI/ML Workflow Bundle workflow skill. Use this skill when the user needs AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features and the operator should preserve the upstream workflow, copied support files, and provenance…

diegosouzapw/awesome-omni-skills · 67 tokens

ml-training

Machine learning model training authority — classifier and regressor training with scikit-learn and PyTorch, feature engineering, cross-validation, hyperparameter tuning, fine-tuning transformer models with HuggingFace, dataset splits, loss functions, learning rate schedules, and reproducible training runs.

LuuOW/meridian-mcp · 58 tokens

ai-ml

diegosouzapw/awesome-omni-skills · 65 tokens