Repository
NVIDIA-AI-Blueprints/video-search-and-summarization agent skills
- skills
- 22
- GitHub stars
- 1.9k
GitHub description: “NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.”
- Stars
- 1,919 (408 forks)
- Licence
- Unknown
- Last push
- Oct 2026
- Created
- Oct 2024
- rag
- vlm
- skills
- video-analytics
- video-search
- computer-vision
- generative-ai
- long-video-understanding
- model-context-protocol
- multimodal-ai
- natural-language-search
- nvidia-nim
- retrieval-augmented-generation
- video-agent
- video-rag
- video-summarization
Install all skills
npx skills add NVIDIA-AI-Blueprints/video-search-and-summarizationAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in NVIDIA-AI-Blueprints/video-search-and-summarization, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Measure retrieval quality and latency of a deployed VSS search profile by ingesting a labelled dataset and running the vss CLI across retrieval paths. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 2 | A skill your agent uses when a user wants to search archived VSS video that is already registered in a configured deployment — by natural-language, similarity, attribute, object-ID, or lexical tag… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Plan, run, and diagnose reproducible RT-VLM GPU performance canaries and benchmarks. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~8.6k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 4 | Add agent-ready vision capabilities — dense captioning, detection, search, alerting, summarization — to an agent or application through a customizable, self-contained vision stack built on the… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~15k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 5 | Measure whether an RT-VLM configuration change altered caption quality — capture paired baseline and candidate captions for a set of videos, score both against a ground truth with an LLM judge, and… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~2.1k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 6 | A skill your agent uses when adding, debugging, or validating a bring-your-own VLM in VSS RT-VLM, including custom Hugging Face or NGC checkpoints, vLLM adapters or plugins, model shims, and… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 7 | A skill your agent uses when operating VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, verification verdicts, on-demand verification, always-on operation, Slack… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~11k | Automated safety check: Warn | Apache-2.0 | yesterday |
| 8 | A skill your agent uses 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… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~5.1k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 9 | A skill your agent uses when the user asks to deploy, upgrade, or size the VSS warehouse blueprint (2D / 3D / MV3DT) on Kubernetes via Helm — as opposed to Docker Compose, which is covered by… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | A skill your agent uses to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). | NVIDIA-AI-Blueprints/ | 1.9k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 11 | A skill your agent uses to deploy the vss-video-analytics-api REST service standalone with its Elasticsearch ingest-pipeline, selectable Kafka/Redis stream type, and Kafka-topic readiness gates when… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 12 | Configure the Docker Compose webhook receivers required by the VIOS webhook notification BDD tests, including the custom body template cases. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~1.4k | Automated safety check: Pass | Unknown | yesterday |
| 13 | A skill your agent uses when answering a question about previously analyzed or freshly scoped VSS video, or when reading a stored VSS memory job or record by id, or whenever a question should be… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 14 | Benchmark video Q&A accuracy and latency of a deployed RT-VLM (Cosmos Reason 3) via vss vlm run, using questions and videos from the DSS vss-devx-base dataset. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 15 | A skill your agent uses when running AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, or when deploying vss-auto-calibration. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~5.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 16 | A skill your agent uses when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics, Mode C SOP compliance via the SOP tools. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 17 | A skill your agent uses to drive vss vios for sensor list, timelines, clips, snapshots, and add/delete of video or stream sources, and the VIOS REST API only for what that CLI does not cover (sensor… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~6.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 18 | A skill your agent uses for read-only incident, occupancy, speed, place, and analytics-sensor questions through the project-local VSS CLI. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 19 | Profile vLLM and RT-VLM inference to identify and remove GPU-idle gaps, underfilled batches, transfer stalls, serialized multimodal work, scheduler gaps, or KV pressure. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 20 | A skill your agent uses when deploying, operating, integrating, or customizing the VSS RT-Embed Video Embedding microservice. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~2.3k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 21 | Update the BDD test container image when its dependencies or runtime change. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~1.2k | Automated safety check: Pass | Unknown | yesterday |
| 22 | A skill your agent uses when summarizing a recorded video through HITL-gated LVS, falling back to vss vlm run when LVS is not ready. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~5.3k | Automated safety check: Warn | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill in NVIDIA-AI-Blueprints/video-search-and-summarization?
Benchmark Video Search from NVIDIA-AI-Blueprints/video-search-and-summarization ranks first of the 22 skills in NVIDIA-AI-Blueprints/video-search-and-summarization listed here, with the highest score: its repository has 1.9k GitHub stars, its SKILL.md loads about 4.3k tokens and it passes the automated safety check with no findings. Next come Vss Search Archive and Rtvi Vlm Perf Testing.
Are the skills in NVIDIA-AI-Blueprints/video-search-and-summarization official?
None yet. All 22 skills in NVIDIA-AI-Blueprints/video-search-and-summarization listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from NVIDIA-AI-Blueprints/video-search-and-summarization?
Run npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.