vss-deploy-detection-tracking-3d SKILL.md skillA
vss-deploy-detection-tracking-3d from nvidia-ai-blueprints/video-search-and-summarization is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-3d@v3.3.0-rc0Pins v3.3.0-rc0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia-ai-blueprints/video-search-and-summarization
- Path
skills/deployment/vss-deploy-detection-tracking-3d/SKILL.md- Versions recorded
- 3
- Latest version
- v3.3.0-rc0, committed Sep 29, 2026
- First version recorded
- Sep 1, 2026
- Size
- 20,355 bytes
- Repository stars
- 1,968
- License
- Apache-2.0
Use when deploying or operating standalone RTVI-CV-3D / MV3DT multi-camera 3D tracking for calibrated MP4/file inputs and live RTSP streams: missing-calibration handoff to AMC skills, the 4-camera sample dataset, camera config, BEV Fusion, live OSD or saved grid/BEV outputs, bundled brokers, basic external MQTT/Kafka brokers, verification, and teardown. Trigger for generic MV3DT, RTVI-CV-3D, multi-view 3D tracking, multi-cam tracking, or sample MV3DT dataset requests. Explicit warehouse…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# VSS Deploy Detection And Tracking 3D ## When to Use This Skill Deploy the standalone RT-CV-3D MV3DT stack from `services/rtvi/rt-cv-3d/rt-cv-mv3dt`. This is the default path for MV3DT / RTVI-CV-3D / multi-camera tracking requests. Do not derive MV3DT services from the warehouse blueprint for this skill. Use `vss-build-vision-ai` only when the user explicitly asks for warehouse MV3DT, the warehouse blueprint, a `bp_wh*` profile, warehouse compose files, or the combined warehouse application stack. When routing an explicit warehouse MV3DT request, also state the boundary: generic MV3DT uses standalone RT-CV-3D, while warehouse MV3DT uses warehouse/profile deployment. For single-camera 2D detection or tracking, use the 2D tracking or DeepStream skills instead. Public docs: https://docs.nvidia.com/vss/latest/object-detection-tracking.html. ## Examples Example operation prompts: - "Deploy MV3DT on my calibrated four-camera MP4 dataset and save output." - "Deploy MV3DT on the sample dataset." - "Enable multi-camera tracking on the 4-cam example dataset." - "Run RTVI-CV-3D on these RTSP streams after calibration." …
Read the whole file at its exact version.
How to install
mdr add nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-3d@sha256:59f0d9dbbb4ed87dThe line at the top of this page pins the label v3.3.0-rc0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ysagqs3hkga2ue4n)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 1, 2026 and Sep 29, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v3.3.0-rc0 latest | 2026-09-29 | 7ccc5db | 20,355 B | A | view · diff |
| v3.3.0 | 2026-09-14 | 4ac059f | 20,351 B | A | view · diff |
| v3.3.0 | 2026-09-01 | fdf50ba | 20,348 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (20355 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nvidia-ai-blueprints/video-search-and-summarization · 1,968 stars · license Apache-2.0 · pushed 2026-11-07 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_ysagqs3hkga2ue4n GET https://markdownregistry.com/api/v1/resolve?ref=nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-3d GET https://markdownregistry.com/api/v1/blob/59f0d9dbbb4ed87db2f58c0029ef8416fc5cdf33c4b79088327e6223755261ce
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from nvidia-ai-blueprints/video-search-and-summarization
Every file in nvidia-ai-blueprints/video-search-and-summarization