tao-generate-image-embeddings

tao-generate-image-embeddings is a skill for Claude Code from NVIDIA-TAO/tao-skill-bank. It costs 81 tokens per session (1,960 once invoked), scanned A, original, Apache-2.0.

An image-processing workflow that turns a Parquet file of image paths into a Parquet file of numeric image embeddings. Embeddings are values that represent image content so software can compare images.

In plain words
What is it for?
Computing embeddings with CLIP, SigLIP, or a TAO checkpoint, then passing the results to nearest-neighbor or unique-image mining workflows.
Why use it?
It prepares image data for later similarity searches or for finding unusual or distinct images.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the tao-skills plugin — 76 skills shipped together , and of tao-skill-bank

Good fit Computing embeddings with CLIP, SigLIP, or a TAO checkpoint, then passing the results to nearest-neighbor or unique-image mining workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings
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-generate-image-embeddings
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.

agentmods badge for tao-generate-image-embeddings

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings)
Your own site
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings/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.

agentmods 80×15 button for tao-generate-image-embeddings

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,960 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 warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 82
    Potential security issue detected. Manual review is recommended.
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • high Privilege Escalation · line 90
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 95
    Potential security issue detected. Manual review is recommended.
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • medium MCP Rug Pull · line 82
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium MCP Rug Pull · line 95
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium MCP Rug Pull · line 148
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01960
Opus 5 $0.00041 $0.00980
Sonnet 5 $0.00016 $0.00392
Haiku 4.5 $0.00008 $0.00196

Measured 13d ago against content hash 0d1b38cf3d32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tao-generate-image-embeddings 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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify_image_embeddings_spec.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/data/tao-generate-image-embeddings/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TAO Generate Image Embeddings

Use this skill to run TAO Data Services image embedding. The skill consumes a parquet of image filepaths and writes a parquet with an embedding column. Downstream mining skills (tao-mine-od-images, tao-mine-nearest-neighbors) consume its output.

The container entrypoint is:

embedding image_embeddings -e /absolute/path/to/image_embeddings.yaml

Inputs

The user can provide either an existing spec or the fields needed to generate one.

Required spec fields:

Field Meaning
input_parquet Absolute path to a parquet containing image filepaths.
output_parquet Absolute path where the embedding parquet is written.
model CLIP or SigLIP.
model_path HuggingFace model id, local HF snapshot directory, or a TAO .pth/.ckpt checkpoint. Must match model. SigLIP: google/siglip-base-patch16-224 (768-dim, the template default). CLIP: openai/clip-vit-base-patch32 (512-dim). The validator rejects a recognizable model/path mismatch before launch.

Common optional fields:

Field Default Meaning
model_config_path "" TAO experiment spec path. Required only when model_path is a TAO checkpoint.
batch_size 64 Number of images processed in parallel. Lower it if the GPU runs out of memory.

The input parquet must contain a filepath column. Any additional columns are carried through to the output verbatim, so metadata such as label survives into the embedding parquet.

The default template is assets/default_image_embeddings.yaml.

Encoder Consistency

When embeddings feed a mining step, every parquet compared against another must be produced with the same model and model_path. Embedding dimensionality follows the encoder — 768 for the SigLIP default, 512 for CLIP ViT-B/32 — and nothing in the output parquet records which encoder wrote it. Embeddings from different encoders are not comparable, and mismatched encoders are the most common cause of mining output that looks unrelated to the targets. Reuse one spec across every parquet in a mining run and override only input_parquet / output_parquet.

Read the full file on GitHub · 181 lines

Files

What ships with it

5 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.

  1. 13d ago First seen · 181 lines · 81 tokens per session scan A 0d1b38cf3d32

Subscribe to this mod's changes

tao-generate-image-embeddings is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 1,960 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 2026-08-30.

Related

Other skills, from other repositories

arrowspace

Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.

sickn33/agentic-awesome-skills · 28 tokens

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/windags-skills · 82 tokens

arrowspace

Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.

iradoweck/antigravity-awesome-skills · 28 tokens

arrowspace

Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.

26BB/agentic-awesome-skills-mcp · 28 tokens

arrowspace

Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.

STELIORD/agentic-awesome-skills · 28 tokens

sentence-transformers

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…

davila7/claude-code-templates · 67 tokens