NVIDIA AI Blueprint for Video Search and Summarization (VSS) is a reference architecture for applications that use AI to search, analyze, question, and summarize live or recorded video. It is intended for building video analytics agents with vision-language models, language models, retrieval-augmented generation, and NVIDIA NIM microservices. The catalogue entries provide coding-agent rules, skills, commands, agents, instructions, and settings associated with the project.
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-AI-Blueprints/video-search-and-summarization --skill vss-generate-video-calibrationgit clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarizationWrote 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-ai-blueprints/video-search-and-summarization/vss-generate-video-calibration)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-generate-video-calibration"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-generate-video-calibration/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-ai-blueprints/video-search-and-summarization/vss-generate-video-calibration"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-generate-video-calibration.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 | $0.00055 | $0.05874 |
| Opus 5.5 | $0.00022 | $0.02350 |
| Sonnet 5.5 | $0.00011 | $0.01175 |
| Haiku 4.5 | $0.00006 | $0.00587 |
Grade A, and why
vss-generate-video-calibration scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Worked end-to-end examples are kept under `evals/` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl` blocks below. Run a Tier-3 evaluation with `nv-base validate <this-skill-dir> How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VSS Generate Video Calibration
Run AutoMagicCalib over one of three input sources and drive the calibration through the microservice REST API. For normal single-run calibration, input-resolution work differs per source and shared work from verify_project onward lives in this file. Pair selected input-mode reference with Shared Calibration Tail; explicit tuning uses its own routed workflow below.
When to Use This Skill
Run or tune AutoMagicCalib end-to-end on local files, RTSP streams, or the bundled sample dataset and (when needed) deploy the AMC microservice.
Do not use for non-AMC camera calibration or runtime analytics.
Workflow
Resolve tuning intent before input mode, then follow the applicable routing table and workflow below. Each section that ends in workflow, quick start, or flow is intended to be executed top-to-bottom. Detailed reference material lives in references/; load only the references needed for the selected intent and input mode.
Examples
Worked end-to-end examples are kept under evals/ (each *.json manifest contains a runnable scenario) and inline in the per-workflow curl blocks below. Run a Tier-3 evaluation with nv-base validate <this-skill-dir> --agent-eval to replay them.
Limitations
- Requires the matching VSS profile / microservice to be deployed and reachable from the caller.
- NGC-hosted models and NIMs may be subject to rate-limits, GPU memory requirements, and license restrictions.
- Concurrency, GPU memory, and storage limits depend on the host hardware and the profile's compose file.
Shared helper references are loaded only when needed:
- Read
references/common-steps.mdwhen a mode reference needs the sharedcreate_project, video-upload, or handoff snippets. - Read
references/calibration-tail.mdwhen you need the reusable Python implementation of the stage-linear-media → verify → VGGT/post-process → AMC/post-process → compare-results tail. - Read
references/tuning.mdfirst when the user explicitly asks to tune, optimize, or find AMC settings. It owns tuning project names and the multi-attempt lifecycle; do not run the ordinary shared calibration tail for that request. - Read
references/calibration-parameters.mdonly when tuning evidence requires a numeric AMC configuration change.
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.
- BENCHMARK.md 3.8 KB
- evals/auto-calibration.json 11 KB
- evals/evals.json 7.8 KB
- references/calibration-parameters.md 10 KB
- references/calibration-tail.md 9.0 KB
- references/common-steps.md 2.1 KB
- references/deploy-auto-calibration-service.md 31 KB
- references/rtsp.md 19 KB
- references/sample-dataset.md 18 KB
- references/tuning.md 20 KB
- references/videos.md 15 KB
- skill-card.md 4.4 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 · +16 lines · +2 tokens per session 5549bb942965
- 28d ago Changed 96793fb16bfd
- 1mo ago Changed · +3 lines a362896ac929
- 1mo ago Changed fc91a61a8502
- 1mo ago Changed · +6 lines 2bdaffa061ab
- 1mo ago Changed · +21 lines 0d208aa73c21
- 1mo ago First seen · 263 lines · 53 tokens per session scan A 8e4d22366e5d
vss-generate-video-calibration is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,953 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 5,874 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyze-tensegrity-system
Analyze a tensegrity system by identifying compression struts and tension cables, classifying type (class 1/2, biological/architectural), computing prestress equilibrium, verifying stability via Maxwell's rigidity criterion, and mapping biological tensegrity (microtubules, actin, intermediate filaments). Use when…
analyze-magnetic-levitation
Analyze magnetic levitation systems by applying Earnshaw's theorem to determine whether passive static levitation is possible, then identifying the appropriate circumvention mechanism (diamagnetic, superconducting, active feedback, or spin-stabilized). Use when evaluating maglev transport, magnetic bearings…
design-acoustic-levitation
Design an acoustic levitation system that uses standing waves to trap and suspend small objects at pressure nodes. Covers ultrasonic transducer selection, standing wave formation between a transducer and reflector, node spacing and trapping position calculation, acoustic radiation pressure analysis, and phased array…
analyze-magnetic-field
Calculate and visualize magnetic fields produced by current distributions using the Biot-Savart law, Ampere's law, and magnetic dipole approximations. Use when computing B-fields from arbitrary current geometries, exploiting symmetry with Ampere's law, analyzing superposition of multiple sources, or characterizing…
sdr-satellite
Software-defined radio (SDR) and satellite reception toolkit — what to install, what you can hear from space, and how to compose the open-source stack (SatDump, SatNOGS, GNU Radio, rustradio, satkit). Covers hardware abstraction (SoapySDR, rtl-sdr-rs), DSP frameworks (GNU Radio, liquid-dsp, rustradio, radiorust)…
math-explainer
A skill for creating animated math explanations with Manim, a Python tool for mathematical animations, and interactive web pages.