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-finetune-clipgit 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-finetune-clip)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-finetune-clip"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-clip/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-finetune-clip"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-clip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00104 | $0.03844 |
| Opus 5 | $0.00052 | $0.01922 |
| Sonnet 5 | $0.00021 | $0.00769 |
| Haiku 4.5 | $0.00010 | $0.00384 |
Grade A, and why
tao-finetune-clip 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLIP
Standalone install? If this session was not initialized by the TAO skill bank plugin, run the
tao-setupskill first (host preflight, credentials, cross-skill discovery).
Contrastive Language-Image Pre-training model for zero-shot and fine-tuned image classification, image-text retrieval, and embedding extraction. Fine-tuning adapts CLIP's shared image-text embedding space to domain-specific image-caption data.
No default NGC pretrained checkpoint is required for spec construction, but unset checkpoint behavior is action-specific. In the validation-fixes PyTorch image, export.checkpoint: null exports the selected CLIP architecture and may initialize weights when pretrained weights are unavailable. Do not assume inference.checkpoint: null loads pretrained weights: clip inference currently calls the checkpoint loader with None and fails before embedding extraction. For PyTorch inference, checkpoint-backed evaluation/export, resume, and retrain flows, resolve and pass an exact checkpoint from the parent train output. For trusted TAO checkpoints produced by the current run or a known parent job, set TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1 on checkpoint-dependent PyTorch actions so PyTorch 2.6 can load the Lightning checkpoint metadata; do not set this for untrusted checkpoints.
Supported actions: train, evaluate, inference, export, gen_trt_engine.
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.
What ships with it
18 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.
- BENCHMARK.md 3.8 KB
- evals/evals.json 764 B
- references/error-patterns.md 3.9 KB
- references/skill_info.yaml 4.9 KB
- references/spec_template_deploy.yaml 616 B
- references/spec_template_evaluate.yaml 1.4 KB
- references/spec_template_export.yaml 1.5 KB
- references/spec_template_train.yaml 1.3 KB
- references/spec_template.yaml 2.0 KB
- references/spec-param-inference.md 2.5 KB
- references/tao-deploy-clip.md 5.8 KB
- references/tao-deploy-clip.skill_info.yaml 2.1 KB
- schemas/evaluate.schema.json 26 KB
- schemas/export.schema.json 27 KB
- schemas/manifest.json 4.6 KB
- schemas/train.schema.json 24 KB
- skill-card.md 3.8 KB
- skill.oms.sig 7.8 KB
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 · 206 lines · 104 tokens per session scan A a2ca51b27d97
tao-finetune-clip is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 104 tokens to every session and 3,844 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.
Other skills, from other repositories
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
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.
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.