A bundle of TAO skills covering model training, data preparation, deployment, and related applications. TAO is NVIDIA’s toolkit for adapting and running computer-vision and AI models.

Use it for TAO-based model, dataset, platform, and application workflows. The input does not specify the exact commands or models included.

It groups many specialized skills in one install, so an agent can find the relevant TAO workflow without adding each model or data skill separately.

tao-skills — Plugin 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.

Clone the repo

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

Made for: Claude Code.

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

Your own site

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

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 76 skills cost 8,352 tokens a session between them.

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

Origin original No closer match found in the catalogue.

Security

Grade A, and why

tao-skills 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 yesterday.

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.

.claude-plugin/marketplace.json#tao-skills · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "tao-skills",
  "description": "Full TAO skill bank — every model, data, platform, and application skill in one bundle. Install this for the standard agentic-fine-tuning experience.",
  "source": "./",
  "strict": true,
  "skills": [
    "./skills/data/tao-generate-anomalies",
    "./skills/data/tao-prepare-anomalygennext-inputs",
    "./skills/data/tao-finetune-anomalygennext",
    "./skills/data/tao-generate-od-defects",
    "./skills/applications/tao-run-automl-deft-pipeline",
    "./skills/applications/tao-train-single-step",
    "./skills/applications/tao-analyze-changenet-rca",
    "./skills/applications/tao-run-automl",
    "./skills/applications/tao-run-inference-service",
    "./skills/applications/tao-finetune-huggingface-model",
    "./skills/applications/tao-port-huggingface-model",
    "./skills/applications/tao-run-deft-aoi",
    "./skills/applications/tao-run-deft-aoi-cosmos3",
    "./skills/applications/tao-run-deft-pas",
    "./skills/applications/tao-run-deft-cr-its-mining",
    "./skills/applications/tao-validate-recipe-transfer",
    "./skills/applications/tao-run-deft-object-detection",
    "./skills/applications/tao-run-deft-od-aoi",
    "./skills/data/tao-mine-nearest-neighbors",
    "./skills/data/tao-mine-aoi-images",
    "./skills/data/tao-analyze-gaps-visual-changenet",
    "./skills/data/tao-analyze-gaps-od-map",
    "./skills/data/tao-route-visual-changenet-samples",
    "./skills/data/paidf-cosmos-predict",
    "./skills/data/tao-generate-video-reasoning-annotations",
    "./skills/models/tao-train-action-recognition",
    "./skills/models/tao-train-bevfusion",
    "./skills/models/tao-train-centerpose",
    "./skills/models/tao-train-image-classification",
    "./skills/models/tao-finetune-clip",
    "./skills/models/tao-finetune-cosmos-reason",
    "./skills/models/tao-train-codetr",
    "./skills/models/tao-train-deformable-detr",
    "./skills/models/tao-train-fast-foundation-stereo",
    "./skills/models/tao-train-depth

Read the full file on GitHub · 84 lines

Contents

What it installs

The manifest is a name and a version. 76 skills travel with it, and installing the plugin installs all of them — 8,352 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

2 files beside marketplace.json#tao-skills 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.

yesterday Changed · +4 lines 89f534874650
7d ago First seen · 80 lines scan A 7e632d010da2

Subscribe to this mod's changes

tao-skills is a plugin published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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

clip-aware-embeddings

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…

curiositech/some_claude_skills · not measured

tao-skills

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

How it starts

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

clip-aware-embeddings

classifier

databricks

torch-air marketplace

sql-database-pipeline

vmware-privateai