What is tao-train-oneformer?

An image-segmentation tool that labels image regions for three common tasks: separating objects and their parts, identifying each individual object, and assigning a class to every pixel.

Train, evaluate, export, compress, optimize, and run image models for semantic, instance, and panoptic segmentation.

It provides one model workflow for different ways of understanding which pixels belong to which objects or categories.

tao-train-oneformer — 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-oneformer

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

Your own site

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

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,813 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	$0.00084	$0.04813
Opus 5	$0.00042	$0.02406
Sonnet 5	$0.00017	$0.00963
Haiku 4.5	$0.00008	$0.00481

Measured 8d ago against content hash 6dc114a6df53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tao-train-oneformer 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.

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-oneformer/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OneFormer

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).

OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries.

Set train.pretrained_backbone and/or train.pretrained_model.

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

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 · 325 lines

Files

What ships with it

23 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 First seen · 325 lines · 84 tokens per session scan A 6dc114a6df53

Subscribe to this mod's changes

tao-train-oneformer is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 4,813 once invoked, about $0.0004 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 2026-09-03.

Data and AI segmentation

yolo-master-agent

Use when the user wants to train, validate, predict, track, export, benchmark, tune, inspect, or orchestrate YOLO-Master / Ultralytics experiments in this repository, including LoRA, MoE, multimodal inference/evaluation, and solutions workflows.

Tencent/YOLO-Master · 60 tokens

computer-vision

Computer vision engineering covering object detection (YOLO, RT-DETR), instance and semantic segmentation (SAM, Mask R-CNN), image classification, OCR (Tesseract, PaddleOCR), video understanding, OpenCV pipelines, PyTorch/torchvision, ONNX export, and edge deployment via TensorRT and CoreML.

LuuOW/meridian-mcp · 69 tokens

spatial-histology

Python API skill for histology image analysis linked to spatial transcriptomics workflows, including tissue segmentation and nuclei/cell detection.

ShangBioLab/SpatialClaw · 30 tokens

yolo-pipeline

YOLO detection, segmentation, classification, and pose estimation setup, training workflow, evaluation metrics, and XAI verification.

aeren23/image-processing-skills · 28 tokens

data-cloud-calculated-insights

Guides creation, design, and maintenance of Calculated Insights in Data Cloud: SQL authoring, dimension/measure definition, scheduling, streaming insights, and insight configuration tradeoffs. Trigger keywords: calculated insight, CI SQL, insight measure, insight dimension, streaming insight, insight schedule, Data…

BanibrataChatterjee/AwesomeSalesforceSkills · 99 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens