Data & Analysis ✓ NVIDIA · Official action-recognitionvideo-classificationoptical-flowtao-toolkitautomldocker-gpu

TAO Video Action Recognition

Train, evaluate, export, and run inference for RGB, optical-flow, and multi-stream video action models with NVIDIA TAO.

FollowSkills review · FSRS-2.0
Not recommended
46/ 100 5-point scale 2.3 / 5
Trust14 / 25 · 2.8/5

The skill limits declared tools to Read and Bash and clearly names data directories, checkpoints, and output paths; no malware, credential theft, or covert exfiltration is evident. However, it requires Docker/GPU infrastructure, may download and extract datasets, defaults Weights & Biases to enabled, and lacks user-confirmation rules, network/telemetry disclosure, sensitive-video handling, permission isolation, and rollback guidance, so points are deducted.

Reliability8 / 20 · 2.0/5

The documentation covers train, evaluate, inference, export, AutoML, checkpoint handling, and several error patterns, with deterministic-training defaults. There are no executable tests or failure-output examples, AutoML depends on an external tao-run-automl skill, and “single-node oriented” conflicts with schemas that permit num_nodes greater than one. Edge-case and dependency-failure feedback is incomplete, so the score is conservatively limited by static calibration.

Adaptability8 / 15 · 2.7/5

Trigger phrases, RGB/optical-flow/joint inputs, action boundaries, GPU requirements, and dataset expectations are reasonably clear. Non-fit cases, TAO/container versions, dataset-format boundaries, Chinese-language use, and mainland-China network reachability are not documented; Docker, NVIDIA Container Toolkit, external images, and possible downloads may be operational constraints, so points are deducted.

Convention7 / 15 · 2.3/5

The skill includes structured schemas, templates, skill_info, an evaluation report, and a version field. It lacks dedicated Instructions, Examples, FAQs, changelog, and a clear maintenance/update path. The skill declares Apache-2.0 while the supplied metadata says NOASSERTION and repository documentation describes Apache/CC-BY dual licensing, leaving governance and licensing ambiguity, so points are deducted.

Effectiveness6 / 15 · 2.0/5

The skill provides concrete data paths, spec overrides, checkpoint selection rules, action mappings, and AutoML routing that could reduce configuration effort. Static evidence does not verify directly usable outputs; examples depend on fixed catch/smile data and an unspecified environment. The benchmark has one task, 0% discoverability, and 20% Codex correctness, so only limited effectiveness credit is justified.

Verifiability3 / 10 · 1.5/5

A fixed revision, structured schemas, templates, skill_info, evals.json, and a benchmark report provide some auditability. There is no committed executable test suite, CI coverage, execution log, or independently reproducible artifact; the benchmark covers only one task and cannot be fully verified from static files, so the score remains low.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • wandb.enable defaults to true, so runs may send experiment metadata to an external service; confirm telemetry, network, and data-compliance requirements before processing sensitive video.
  • Before execution, verify Docker, NVIDIA Container Toolkit, the TAO image, GPU memory, and dataset-download availability, especially on mainland-China networks.
  • Checkpoint paths, label_map, sequence lengths, and directory paths must match training; no executable preflight validation or automatic rollback is documented.
  • Clarify how Apache-2.0, CC-BY-4.0, and the NOASSERTION metadata relate to this skill's licensing.
See the full review method →

What does this skill do, and when should you use it?

This skill guides NVIDIA TAO Toolkit workflows for temporal action classification from video clips. It supports RGB, optical-flow, and joint multi-stream inputs, covering training, evaluation, inference, and ONNX export. Training is routed through AutoML by default when the packaged schemas and templates are available, with a per-run option to disable it. It is suited to users who already have video data and a Docker-based TAO environment.

Reads the packaged TAO schemas, templates, and skill configuration to resolve training AutoML policy; constructs required training, validation, evaluation, and inference directory paths; runs TAO training, evaluation, inference, or export workflows; handles label maps, checkpoints, pretrained weights, resume training, and ONNX output paths; and explains common failures such as sequence-length mismatches and missing label maps.

  1. A computer-vision engineer wants to train temporal classifiers for actions such as catch and smile from RGB video.
  2. A model developer wants to use optical flow or joint RGB-plus-optical-flow inputs.
  3. An ML engineer wants AutoML to select training settings while minimizing val_loss.
  4. A deployment engineer needs to export a trained action-recognition checkpoint to ONNX.
  5. An evaluator needs to run TAO evaluation or inference against an existing action-recognition model.

What are this skill's strengths and limitations?

Pros
  • Covers training, evaluation, inference, and ONNX export workflows.
  • Supports RGB, optical-flow, and joint multi-stream inputs.
  • Documents AutoML routing, dataset-directory requirements, checkpoint inference, and common failure modes.
  • Supports Lightning-managed single-node multi-GPU training.
Limitations
  • Requires Docker, nvidia-container-toolkit, and an NVIDIA GPU; 16GB or more of VRAM per GPU is recommended.
  • The scope is action recognition; it does not provide video collection, annotation, or archive-download tooling.
  • Dataset archives must be extracted into directories rather than passed as .tar.gz paths to the action-recognition entry points.
  • The provided SKILL.md does not include an independent test suite, performance benchmark, or cross-platform validation report.

How do you install this skill?

Install the specific skill with the skills CLI flow documented by the repository README:

npx skills add nvidia/skills --skill tao-train-action-recognition --yes

After installation, place the skill in the target agent's skill directory; the README does not specify a skill-specific manual-copy path. The runtime also requires Docker, nvidia-container-toolkit, and an NVIDIA GPU.

How do you use this skill?

After installation, prompt the agent with phrases such as “train action recognition” or “train an RGB + optical flow action model with TAO.” Provide extracted dataset directories and dataset.label_map for training, evaluation, and inference. AutoML is enabled by default for training when the packaged schema and template are available; request “disable AutoML” or set automl_policy: off for a direct run. If using TAO sample archives, download and extract train.tar.gz, test.tar.gz, or test/smile.tar.gz before launching the container. For export, provide a concrete training checkpoint and an ONNX output path.

FAQ

What hardware is required?
At least one NVIDIA GPU is required. Two GPUs are recommended, with 16GB or more of VRAM per GPU; actual memory use depends on sequence length and input resolution.
Can AutoML be disabled?
Yes. Set automl_policy: off for the individual training run or explicitly ask to disable AutoML. This does not change the model metadata.
Why might evaluation or inference fail to load a checkpoint?
Evaluation and inference need the same dataset.label_map used during training. Without it, model construction can fail before the checkpoint is validated.
Does the workflow require network access?
If TAO sample data is supplied as archives, the archives must be downloaded and extracted. The source material does not provide a specific download command.

More skills from this repository

All from NVIDIA/skills

Data & Analysis ✓ NVIDIA · Official

TAO Standard Training Workflow

Run a controlled TAO train, evaluate, and export workflow on labeled data.

Data & Analysis ✓ NVIDIA · Official

TAO MAL Weakly Supervised Segmentation

Train segmentation models from point or box annotations and produce masks with minimal labeling.

Data & Analysis ✓ NVIDIA · Official

TAO NVPanoptix3D

Train and run 3D panoptic reconstruction with occupancy completion from posed RGB images.

Data & Analysis ✓ NVIDIA · Official

TAO Optical Inspection Training

Train and deploy Siamese-network models for manufacturing defect inspection.

Data & Analysis ✓ NVIDIA · Official

TAO DINO Object Detection

Run NVIDIA TAO workflows for training and deploying DINO 2D object detectors.

Data & Analysis ✓ NVIDIA · Official

TAO CenterPose Pose Estimation Skill

Guides agents through training, evaluation, export, and deployment of CenterPose models for 6-DoF object pose estimation.

Data & Analysis ✓ NVIDIA · Official

TAO Person Re-Identification

Train and deploy TAO ReID models for cross-camera person matching.

Dev & Engineering ✓ NVIDIA · Official

TAO Skill Bank Capability Discovery

Query TAO Skill Bank workflows, models, platforms, and AutoML support from packaged manifests.

Data & Analysis ✓ NVIDIA · Official

TAO RT-DETR Object Detection

Guides NVIDIA TAO workflows for training and deploying real-time RT-DETR detectors.

Data & Analysis ✓ NVIDIA · Official

TAO Pose Classification

Classify pose-keypoint sequences into action categories with ST-GCN.

Dev & Engineering ✓ NVIDIA · Official

TAO Sparse4D Training Skill

Guides agents through training, evaluation, export, quantization, and inference for multi-camera temporal 3D detection and tracking.

Automation & Ops ✓ NVIDIA · Official

TAO on Brev GPU Instances

Run and manage TAO training, evaluation, and inference on Brev GPU instances.

Data & Analysis ✓ NVIDIA · Official

TAO BEVFusion Training

Train, evaluate, and run inference on BEV 3D detection models that fuse LiDAR and camera data with TAO.

Automation & Ops ✓ NVIDIA · Official

TAO Local Docker Runner

Run TAO jobs on a local or remote single-node Docker host with NVIDIA GPU support.

Data & Analysis ✓ NVIDIA · Official

TAO Visual ChangeNet Inspection

Train paired-image classifiers and change-segmentation models for PCB defect inspection.

Data & Analysis ✓ NVIDIA · Official

TAO Video Reasoning Annotation Pipeline

Convert raw videos into chain-of-thought training data.

Data & Analysis ✓ NVIDIA · Official

TAO Deformable DETR Object Detection

Guides end-to-end training, evaluation, export, quantization, and deployment of lightweight Deformable DETR detectors in NVIDIA TAO.

Data & Analysis ✓ NVIDIA · Official

TAO Grounding DINO Open-Vocabulary Detection

Train and deploy text-guided object detectors without a fixed class vocabulary.

Automation & Ops ✓ NVIDIA · Official

TAO on SLURM

Run TAO training, evaluation, and inference on a remote GPU cluster through SSH, SLURM, and Pyxis/Enroot.

Data & Analysis ✓ NVIDIA · Official

TAO FastFoundationStereo Real-Time Stereo Depth

Run TAO FastFoundationStereo workflows that produce low-latency disparity maps from stereo images.

Related skills