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.
npx skills add NVIDIA-TAO/tao-skill-bank --skill tao-generate-image-embeddingsgit clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bankWrote 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.
[](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-generate-image-embeddings)<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.
<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>- NVIDIA SkillSpector warn
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
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 | $0.00081 | $0.01960 |
| Opus 5 | $0.00041 | $0.00980 |
| Sonnet 5 | $0.00016 | $0.00392 |
| Haiku 4.5 | $0.00008 | $0.00196 |
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.
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.
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.
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.
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.
- 13d ago First seen · 181 lines · 81 tokens per session scan A 0d1b38cf3d32
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.
Other skills, from other repositories
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
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…
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
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…