Data & Analysis ✓ NVIDIA · Official video-qnavideo-understandingvlmvssvstvisual-analysis

VSS Video Q&A

Answers visual questions by having an agent inspect a recorded video clip.

FollowSkills review · FSRS-2.0
Not recommended
52/ 100 5-point scale 2.6 / 5
Trust16 / 25 · 3.2/5

The skill restricts itself to fresh visual questions, requires VSS probing and sensor listing, and requires confirmation before upload. These provide scope control and partial data-flow transparency. Points are deducted because upload creates an external write, while authentication, privacy/sensitive-video handling, privilege isolation, and complete rollback guidance are absent; curl may transmit local video data to the service.

Reliability8 / 20 · 2.0/5

SKILL.md specifies probing, sensor checks, upload, /generate invocation, and agent-think removal, and defines stop-or-ask behavior when probing fails. Points are deducted for limited handling of non-2xx responses, timeout diagnostics, upload conflicts, malformed responses, and missing dependencies; BENCHMARK.md also records insufficient connection/error guidance. Static evidence cannot justify a score above 10.

Adaptability9 / 15 · 3.0/5

Activation scenarios, exclusions, accepted clip identifiers, and VSS profile prerequisites are reasonably clear, distinguishing visual questions from metadata or existing-result questions. Points are deducted because Chinese interaction/localization is not documented and mainland-China network reachability is unverified; ambiguity handling for URLs, sensor IDs, and filename stems remains incomplete.

Convention8 / 15 · 2.7/5

The material includes a name, description, Apache-2.0 license, version 3.2.0, product repository link, cross-references, output contract, and an evaluation report, with generally readable structure. Points are deducted for missing metadata.author, missing recommended Instructions and Examples sections, absent changelog and explicit maintenance/update path, and incomplete troubleshooting and limitation disclosure; repository license metadata is NOASSERTION, so governance evidence is not fully consistent despite the skill-level Apache-2.0 declaration.

Effectiveness6 / 15 · 2.0/5

The skill supplies a directly usable VSS agent /generate request pattern, sensor preflight, and final-text extraction procedure, so it plausibly completes ad-hoc visual Q&A for one clip. Points are deducted because the benchmark has only one task, correctness and effectiveness are both 50%, and static review cannot verify answer quality, timestamp accuracy, or coverage of video content; human review remains necessary.

Verifiability5 / 10 · 2.5/5

Committed benchmark material, eval configuration, and reported security, correctness, discoverability, and efficiency signals provide limited auditable evidence. Points are deducted because coverage is one task with no negative cases, there is no skill-specific reproducible test suite, and no independent third-party corroboration; static evidence caps this at 5.

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
  • Before execution, confirm that the VSS profile, VST, and video_understanding tool are available, and validate HOST_IP, sensor-id, and video path.
  • Video upload is an external write; check for sensitive content, conflicts, and authorization before transmitting data.
  • Do not treat VLM output as guaranteed fact, especially for safety judgments and timestamps; retain human review.
  • Mainland-China network reachability is not demonstrated in the source material, and deployment dependencies may require locally reachable configuration.
See the full review method →

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

VSS Video Q&A calls the VSS Agent’s video_understanding tool for a fresh visual question about a recorded clip. It is intended for questions about people, objects, actions, colors, timing, safety, and other facts that require inspecting video frames. It requires a running VSS profile that serves video_understanding and a matching VST sensor. Version 3.2.0 is declared under Apache-2.0.

It probes the VSS Agent, lists VST sensors, and checks that the requested sensor or filename stem exists. If it is missing, it can upload the video after interactive confirmation and verify the sensor again. It then posts a request to the VSS Agent’s /generate endpoint containing the sensor and question, asks the agent to call video_understanding, reads the response value, removes any agent-think sections, and returns the remaining final answer.

  1. A video operator needs an answer about what happens in a specific recorded clip.
  2. A safety analyst needs to verify whether particular people, objects, actions, colors, or safety-relevant events appear in footage.
  3. A user has a coarse summary or report and needs a follow-up answer about visual content details.
  4. Existing search results, metadata, or prior tool output cannot answer a content question and the original pixels must be checked.

What are this skill's strengths and limitations?

Pros
  • The workflow is clearly scoped to fresh, frame-based video questions.
  • It specifies agent probing, sensor validation, upload confirmation, and response cleanup.
  • It prevents using the skill when metadata, search results, or prior output already answers the question.
  • The skill declares an Apache-2.0 license.
Limitations
  • It depends on a running VSS Agent, the video_understanding tool, and VST sensor services.
  • The sensor-list check is mandatory before every /generate call.
  • It is not intended for questions answerable from prior tool output, search hits, or metadata.
  • The supplied source provides no platform matrix, performance measurements, or skill-specific test results.

How do you install this skill?

Install the specific skill with the documented skills CLI command:

npx skills add nvidia/skills --skill vss-ask-video --yes

The README says cloning the repository or manually copying skill folders is not required.

How do you use this skill?

After installation, ask the agent a fresh visual question tied to a specific sensor, for example: "Call video_understanding to answer whether anyone enters the restricted area in sensor warehouse_safety_0001."

Before the request:

  1. Confirm that a VSS profile serving video_understanding is running; base is recommended and lvs is also listed.
  2. List VST sensors and confirm the sensor ID or filename stem exists.
  3. If it does not exist, obtain interactive confirmation before uploading the video, then list sensors again.
  4. Ask the VSS Agent to answer through /generate.

The source does not document a complete deployment command or all upload semantics; those are delegated to vss-deploy-profile and vss-manage-video-io-storage.

FAQ

Can it answer questions about filenames or metadata directly?
That is outside its intended scope. It should be used when the answer requires inspecting video frames; metadata, database, MCP, search, or prior output should be preferred when they already provide the answer.
Does a VSS profile have to be running?
Yes. A profile serving video_understanding is required. The source recommends base and also names lvs as an option; a failed probe should trigger a deployment question.
What if the video is not listed as a VST sensor?
List sensors first. If there is no match, obtain user confirmation before uploading the file, then list sensors again to verify the new sensor.
What part of the /generate response should be shown to the user?
Read value, remove every agent-think...</agent-think> section, and return only the remaining final-answer text.

More skills from this repository

All from NVIDIA/skills

Automation & Ops ✓ NVIDIA · Official

VSS Video Analysis Reports

Generates structured reports from recorded video clips or incident time ranges.

Automation & Ops ✓ NVIDIA · Official

VSS Video Summarizer

Creates timestamped narrative summaries of recorded videos through LVS, with a VLM fallback.

Automation & Ops ✓ NVIDIA · Official

VSS Alert Management

Operate NVIDIA VSS real-time alerts, subscriptions, incident queries, Slack notifications, and camera onboarding.

Data & Analysis ✓ NVIDIA · Official

TAO Image Referring Expression Pipeline

Turns images and KITTI boxes into grounded referring-expression annotations.

Data & Analysis ✓ NVIDIA · Official

i4H Dataset Annotation Workflow

Use a vision-language model to verify task success and filter episodes for fine-tuning.

Automation & Ops ✓ NVIDIA · Official

RT-VLM Dense Captioning Deployment

Deploy and operate NVIDIA RT-VLM to generate dense video captions and manage live streams through a REST API.

Automation & Ops ✓ NVIDIA · Official

VSS Standalone Video Analytics API

Deploy and verify NVIDIA’s VSS video analytics REST API without the full warehouse stack.

Data & Analysis ✓ NVIDIA · Official

TAO VLM Binary Gap Analyzer

Extract false-positive and false-negative cases from VLM yes/no predictions for downstream root-cause analysis.

Automation & Ops ✓ NVIDIA · Official

VSS Video Auto-Calibration

Run end-to-end AutoMagicCalib calibration for local videos, RTSP cameras, or the bundled sample dataset.

Automation & Ops ✓ NVIDIA · Official

VSS Archive Video Search

Search archived video with natural language and ingest files or RTSP streams into a searchable index.

Data & Analysis ✓ NVIDIA · Official

TAO DEFT AOI Improvement Loop

Automates evaluation, defect augmentation, mining, retraining, and deployment gating for PCB inspection models.

Data & Analysis ✓ NVIDIA · Official

TAO Video Reasoning Annotation Pipeline

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

Data & Analysis ✓ NVIDIA · Official

TAO ChangeNet Root Cause Analyzer

Uses image evidence to identify why NVIDIA TAO Visual ChangeNet classification experiments fail.

Automation & Ops ✓ NVIDIA · Official

VSS Profile Deployment Assistant

Select, deploy, verify, and troubleshoot NVIDIA VSS Compose profiles for video search and summarization.

Dev & Engineering ✓ NVIDIA · Official

cuPyNumeric Migration Readiness

Assess whether NumPy code is ready to scale on GPUs before committing to a substantial cuPyNumeric port.

Dev & Engineering ✓ NVIDIA · Official

NeMo MBridge MoE VLM Training Guide

Guides FSDP and 3D-parallel choices and tuning for MoE vision-language model training.

Automation & Ops ✓ NVIDIA · Official

VSS Video Embedding Deployment

Deploy and operate NVIDIA’s video embedding service for files, text, and live streams.

Data & Analysis ✓ NVIDIA · Official

cuOpt Multi-Objective Explorer

Map Pareto tradeoffs between competing objectives with cuOpt.

Dev & Engineering ✓ NVIDIA · Official

NeMo MBridge Sequence Packing

Configure and validate sequence packing and long-context training in Megatron-Bridge.

Automation & Ops ✓ NVIDIA · Official

VSS Multi-Camera 3D Detection and Tracking

Deploy multi-camera 3D perception with DeepStream and BEV Fusion.

Related skills