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-video-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-video-clip)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-finetune-video-clip"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-video-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-video-clip"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-video-clip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 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 91 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 57 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 114 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 115 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 118 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 160 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 126 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 133 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 140 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 147 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 163 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 | $0.00111 | $0.03698 |
| Opus 5.5 | $0.00044 | $0.01479 |
| Sonnet 5.5 | $0.00022 | $0.00740 |
| Haiku 4.5 | $0.00011 | $0.00370 |
Grade A, and why
tao-finetune-video-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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InternVideo2-CLIP (TAO video_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).
TAO task video_clip wraps OpenGVLab InternVideo2-CLIP L14. The PyTorch image provides train, evaluate, inference, export, and default_specs. TAO Deploy provides gen_trt_engine, TensorRT evaluate, and TensorRT inference.
Container images and per-action commands are in references/skill_info.yaml and references/tao-deploy-video-clip.skill_info.yaml. Starting specs are in references/spec_template_*.yaml.
Release note: The pinned PyTorch image is the TAO 7.2 release-candidate build validated for Video-CLIP. It includes PyAV 17.1.0 as the primary decoder and ONNXScript 0.7.1 for export, with decord absent. The TAO Deploy image is pinned independently because
gen_trt_engineand TensorRT-backed actions do not run in the PyTorch image.Known-broken images: interim builds cut before tao-pytorch commit
0cc31de4ship avideo_clippackage with nomodel.backbonessubmodule, sotrain/evaluate/inferencedie at import whilevideo_clip --helpstill exits 0. Images without PyAV also fail at data loading. Run both import checks in the preflight below before pulling data or launching a run.
Train Action Policy
AutoML is not packaged for this model skill. Always use direct video_clip actions even when a higher-level request mentions AutoML. Non-train actions stay in this skill.
Quick Start (local Docker)
Use the pinned TAO container declared in references/skill_info.yaml. Pull with NGC_KEY when the image is not cached locally.
VIDEO_CLIP_IMAGE_DEFAULT="nvcr.io/nvidia/tao/tao-toolkit:7.3.0-pyt" # versions-key: images.tao_toolkit.pyt
VIDEO_CLIP_IMAGE="${VIDEO_CLIP_IMAGE:-$VIDEO_CLIP_IMAGE_DEFAULT}"
docker pull "$VIDEO_CLIP_IMAGE"
Expected workspace layout (host paths bind-mounted into the container):
What ships with it
12 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.
- eval.config 9.7 KB
- evals/evals.json 4.8 KB
- references/skill_info.yaml 2.6 KB
- references/spec_template_deploy_evaluate.yaml 378 B
- references/spec_template_deploy_inference.yaml 379 B
- references/spec_template_evaluate.yaml 1.2 KB
- references/spec_template_export.yaml 792 B
- references/spec_template_gen_trt_engine.yaml 395 B
- references/spec_template_inference.yaml 1.2 KB
- references/spec_template_train.yaml 1.8 KB
- references/tao-deploy-video-clip.md 4.0 KB
- references/tao-deploy-video-clip.skill_info.yaml 2.7 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 Changed 39110badaeb2
- 1mo ago Changed 4398fc9e6dc9
- 1mo ago First seen · 270 lines · 111 tokens per session scan A f1a7f41793f7
tao-finetune-video-clip is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (97 stars, last pushed 5d ago), licensed Apache-2.0. It adds 111 tokens to every session and 3,698 once invoked, about $0.0004 per session on Opus 5.5. 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
kilocode-multimodal
Verify tool execution using text, audio, and VLM checks across PMOVES services on the KiloCode GLM lane. Use when validating multimodal outputs, capturing verification evidence, or binding verification to task/run IDs.
minimax-multimodal
Verify tool execution using text, audio, and VLM checks across PMOVES services. This skill should be used when validating multimodal outputs, capturing verification evidence, or binding verification to task/run IDs.
fine-tuning-openvla-oft
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying…
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
huawei-cloud-cloudrobo-train
Manage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks — create pretrain (TRAINFROMSCRATCH) and finetune (MODELTUNING) tasks with FFT/SFT/LORA/QLORA/DEEPSPEED methods; manage the full task lifecycle (create/read/update/delete/stop/restart/resume/draft); save and resubmit draft…
seedance-2.0-prompter
Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.