原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

video-search-and-summarization Skill

代码仓库 ↗

作者:NVIDIA-AI-Blueprints★ 2,000 (整个仓库)26 个 skill

★ 星标是整个仓库的,不是每个 Skill 的

选择要安装的 Skill

能做什么

此仓库是合集,包含 26 个 Skill

  • 连接方式 供 AI 读取的指令文件
  • 账号或密钥 尚未确认(还没读 README)
  • 分类 设计与网页
作者的原始说明
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…
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/nvidia-ai-blueprints-video-search-and-summarization.svg)](https://mcp.popnx.com/en/skills/nvidia-ai-blueprints-video-search-and-summarization)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

Next AI Draw.io

draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand

作者:DayuanJiang广泛使用↓ 2.2万/周★ 3.7万 整个仓库的星标6天前更新

MCP · 连接服务在你的电脑上运行

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

作者:pascalorg广泛使用↓ 1037/周★ 2.6万 整个仓库的星标前天更新

MCP · 连接服务电脑或云端✓ 服务方 · pascal.app

Semiotic

Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.

作者:nteract广泛使用↓ 8456/周★ 2717昨天更新

MCP · 连接服务电脑或云端

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
video-search-and-summarization
impeccablediagram-designfrontend-slidesguizang-ppt-skill
作者NVIDIA-AI-Blueprintspbakauscathrynlaveryzarazhangruiop7418
Skill 数261111
GitHub 星标2,000113,04268,29632,57930,091
最近代码更新2026年11月19日2026年11月19日2026年11月19日2026年6月24日2026年10月30日
许可证Apache-2.0Apache-2.0MITMITAGPL-3.0

NVIDIA-AI-Blueprints 提供的 26 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

选择要安装的 Skill

只安装你真正会用的。点开名称查看该 Skill 的安装方法

安装整套(26 个)

如果想要全部,可以让 AI 一次装好。安装前请先了解 2 点

  • 每个已安装 Skill 的说明都会载入每次对话。装得越多,AI 越容易选错 Skill
  • 有些 Skill 与 AI 自带的工具功能重复。只安装真正会用的更好
安装到哪里
请帮我从 https://github.com/nvidia-ai-blueprints/video-search-and-summarization 安装全部 26 个 Skill:bdd-container-update, benchmark-video-search, configure-webhook-bdd-test, profile-vllm-performance, rtvi-byom-porting, rtvi-vlm-perf-testing, vss-ask-video, vss-benchmark-video-summarization, vss-benchmark-vlm-qa, vss-build-vision-ai, vss-deploy-dense-captioning, vss-deploy-detection-tracking-2d, vss-deploy-detection-tracking-3d, vss-deploy-video-embedding, vss-deploy-warehouse-helm, vss-evaluate-caption-accuracy, vss-generate-video-calibration, vss-generate-video-report, vss-generate-video-report-rag, vss-manage-alerts, vss-manage-video-io-storage, vss-query-analytics, vss-search-archive, vss-setup-behavior-analytics, vss-setup-video-analytics-api, vss-summarize-video,供我所有项目使用,每个放在 ~/.claude/skills/<Skill 名称>(Codex 用 ~/.agents/skills/<Skill 名称>,Cursor 用 ~/.cursor/skills/<Skill 名称>)。各 Skill 在仓库中的文件夹:bdd-container-update = services/vios/.cursor/skills/bdd-container-update · benchmark-video-search = skills/benchmarking/benchmark-video-search · configure-webhook-bdd-test = services/vios/.cursor/skills/configure-webhook-bdd-test · profile-vllm-performance = skills/benchmarking/profile-vllm-performance · rtvi-byom-porting = skills/deployment/rtvi-byom-porting · rtvi-vlm-perf-testing = skills/benchmarking/rtvi-vlm-perf-testing · vss-ask-video = skills/operations/vss-ask-video · vss-benchmark-video-summarization = skills/benchmarking/vss-benchmark-video-summarization · vss-benchmark-vlm-qa = skills/benchmarking/vss-benchmark-vlm-qa · vss-build-vision-ai = skills/vss-build-vision-ai · vss-deploy-dense-captioning = skills/deployment/vss-deploy-dense-captioning · vss-deploy-detection-tracking-2d = skills/deployment/vss-deploy-detection-tracking-2d · vss-deploy-detection-tracking-3d = skills/deployment/vss-deploy-detection-tracking-3d · vss-deploy-video-embedding = skills/deployment/vss-deploy-video-embedding · vss-deploy-warehouse-helm = skills/deployment/vss-deploy-warehouse-helm · vss-evaluate-caption-accuracy = skills/benchmarking/vss-evaluate-caption-accuracy · vss-generate-video-calibration = skills/tools/vss-generate-video-calibration · vss-generate-video-report = skills/operations/vss-generate-video-report · vss-generate-video-report-rag = skills/operations/vss-generate-video-report-rag · vss-manage-alerts = skills/operations/vss-manage-alerts · vss-manage-video-io-storage = skills/operations/vss-manage-video-io-storage · vss-query-analytics = skills/operations/vss-query-analytics · vss-search-archive = skills/operations/vss-search-archive · vss-setup-behavior-analytics = skills/deployment/vss-setup-behavior-analytics · vss-setup-video-analytics-api = skills/deployment/vss-setup-video-analytics-api · vss-summarize-video = skills/operations/vss-summarize-video。请先让我看所有文件,告诉我是否有脚本或会修改电脑设置,再告诉我每个 Skill 安装的完整路径,等我同意后再安装。
请帮我从 https://github.com/nvidia-ai-blueprints/video-search-and-summarization 安装全部 26 个 Skill:bdd-container-update, benchmark-video-search, configure-webhook-bdd-test, profile-vllm-performance, rtvi-byom-porting, rtvi-vlm-perf-testing, vss-ask-video, vss-benchmark-video-summarization, vss-benchmark-vlm-qa, vss-build-vision-ai, vss-deploy-dense-captioning, vss-deploy-detection-tracking-2d, vss-deploy-detection-tracking-3d, vss-deploy-video-embedding, vss-deploy-warehouse-helm, vss-evaluate-caption-accuracy, vss-generate-video-calibration, vss-generate-video-report, vss-generate-video-report-rag, vss-manage-alerts, vss-manage-video-io-storage, vss-query-analytics, vss-search-archive, vss-setup-behavior-analytics, vss-setup-video-analytics-api, vss-summarize-video,装到这个对话当前打开的项目里(放在 .claude/skills/<Skill 名称>;Codex 用 .agents/skills/<Skill 名称>,Cursor 用 .cursor/skills/<Skill 名称>)。各 Skill 在仓库中的文件夹:bdd-container-update = services/vios/.cursor/skills/bdd-container-update · benchmark-video-search = skills/benchmarking/benchmark-video-search · configure-webhook-bdd-test = services/vios/.cursor/skills/configure-webhook-bdd-test · profile-vllm-performance = skills/benchmarking/profile-vllm-performance · rtvi-byom-porting = skills/deployment/rtvi-byom-porting · rtvi-vlm-perf-testing = skills/benchmarking/rtvi-vlm-perf-testing · vss-ask-video = skills/operations/vss-ask-video · vss-benchmark-video-summarization = skills/benchmarking/vss-benchmark-video-summarization · vss-benchmark-vlm-qa = skills/benchmarking/vss-benchmark-vlm-qa · vss-build-vision-ai = skills/vss-build-vision-ai · vss-deploy-dense-captioning = skills/deployment/vss-deploy-dense-captioning · vss-deploy-detection-tracking-2d = skills/deployment/vss-deploy-detection-tracking-2d · vss-deploy-detection-tracking-3d = skills/deployment/vss-deploy-detection-tracking-3d · vss-deploy-video-embedding = skills/deployment/vss-deploy-video-embedding · vss-deploy-warehouse-helm = skills/deployment/vss-deploy-warehouse-helm · vss-evaluate-caption-accuracy = skills/benchmarking/vss-evaluate-caption-accuracy · vss-generate-video-calibration = skills/tools/vss-generate-video-calibration · vss-generate-video-report = skills/operations/vss-generate-video-report · vss-generate-video-report-rag = skills/operations/vss-generate-video-report-rag · vss-manage-alerts = skills/operations/vss-manage-alerts · vss-manage-video-io-storage = skills/operations/vss-manage-video-io-storage · vss-query-analytics = skills/operations/vss-query-analytics · vss-search-archive = skills/operations/vss-search-archive · vss-setup-behavior-analytics = skills/deployment/vss-setup-behavior-analytics · vss-setup-video-analytics-api = skills/deployment/vss-setup-video-analytics-api · vss-summarize-video = skills/operations/vss-summarize-video。请先让我看所有文件,告诉我是否有脚本或会修改电脑设置,再告诉我项目名称和每个 Skill 安装的完整路径,等我同意后再安装。

上传到 Claude 网页版和应用:需要上传 26 次,每个 Skill 一个 ZIP 文件。打开下方列表中的各个 Skill 即可下载

Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • bdd-container-update

    Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in start_test.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mou…

  • benchmark-video-search

    Measure retrieval quality and latency of a deployed VSS search profile by ingesting a labelled dataset and running the vss CLI across retrieval paths. Use when the user asks to "benchmark video search", "compare search recall between builds", or "profile search latency" on a deployed VSS profile. A…

  • configure-webhook-bdd-test

    Configure the Docker Compose webhook receivers required by the VIOS webhook notification BDD tests, including the custom body template cases. Use when preparing deployment/stream-processing/docker-compose/configs/notification_config.json for test_webhook_notifications.py or test_webhook_custom_body…

  • profile-vllm-performance

    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. Use this skill when GPU utilization is unexpectedly low or bursty, capacity trails another runtime, TTFT or ITL regresses, or mul…

  • rtvi-byom-porting

    Use when adding, debugging, or validating a bring-your-own VLM in VSS RT-VLM, including a custom Hugging Face or NGC checkpoint loaded with configuration only (VLM_MODEL_TO_USE=vllm-compatible), plus adapters, plugins, shims, and model-specific runtime dependencies. Not for ordinary catalog-preset…

  • rtvi-vlm-perf-testing

    Plan, run, and diagnose reproducible RT-VLM GPU performance canaries and benchmarks. Use this skill when running fresh-container stream-capacity, semantic-isolation, latency, throughput, or regression experiments against an RTVI microservices checkout.

  • vss-ask-video

    Use this skill 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 answered by running the `vss memory introspect` command. Route through hot context, agent Markdown notes, `vss me…

  • vss-benchmark-video-summarization

    Benchmark a deployed LVS instance — set up test media, run single-file latency and burst-throughput tests, analyze GPU and latency metrics, and get configuration recommendations to improve performance.

  • vss-benchmark-vlm-qa

    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. Replaces the deprecated nat eval / vss-agent QA path. Not for tool-calling or trajectory evaluation, and not for LVS summarization throughp…

  • vss-build-vision-ai

    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 VSS Blueprint. Use this skill when a developer or agent wants to give their app vision: pick capabi…

  • vss-deploy-dense-captioning

    Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.

  • vss-deploy-detection-tracking-2d

    Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. N…

  • vss-deploy-detection-tracking-3d

    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…

  • vss-deploy-video-embedding

    Use this skill when deploying, operating, integrating, or customizing the VSS RT-Embed Video Embedding microservice. Covers standalone Docker Compose deployment, the `/v1` REST API for text/video embeddings and live streams, Redis/Kafka/OTel integration, troubleshooting, and bring-your-own-model (B…

  • vss-deploy-warehouse-helm

    Use 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 vss-build-vision-ai's warehouse reference. Handles GPU-aware NUM_STREAMS capping so the deployment matches what the perception…

  • vss-evaluate-caption-accuracy

    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 emit an accuracy and processing-time table. Use when changing frame selection, decode, or model setti…

  • vss-generate-video-calibration

    Use this skill when running or tuning AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, or when deploying vss-auto-calibration. Do not use for non-AMC calibration or runtime analytics.

  • vss-generate-video-report

    Use this skill 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. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.

  • vss-generate-video-report-rag

    Generates VSS video summary reports with LVS HITL and optional Enterprise RAG document grounding. Trigger when the user asks for a frag/RAG-assisted video report, knowledge-enhanced analysis, or Enterprise RAG context in a video summary.

  • vss-manage-alerts

    Use this skill when operating VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, verification verdicts, on-demand verification, always-on operation, Slack notifications, incident queries, or camera onboarding. Not for non-alert analytics.

  • vss-manage-video-io-storage

    Use 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 info/status/settings, storage and recorder status, WebRTC, the RTSP proxy, network scan, device settings, bytes to dis…

  • vss-query-analytics

    Use this skill for read-only incident, occupancy, speed, place, and analytics-sensor questions through the project-local VSS CLI. Not for live VLM, incident-range narrative reports, deployment, or alert-rule management.

  • vss-search-archive

    Use this skill 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 query. Not for fresh clip Q&A, live captioning, video summarization, deployment, or source ingestion/deletion.

  • vss-setup-behavior-analytics

    Use this skill to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.

  • vss-setup-video-analytics-api

    Use 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 Kafka is selected. Not for full warehouse deploy.

  • vss-summarize-video

    Use when summarizing a recorded video through HITL-gated LVS, falling back to `vss vlm run` when LVS is not ready. Not for reports, archive search, or live RTSP captioning.

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor

安装

请先选择 Skill

此仓库有 26 个 Skill。请从上方列表选一个,该 Skill 的页面有完整安装方法,包括让 AI 安装和 ZIP 文件

让 AI 帮你安装
上传到 claude.ai

前往 Skill 列表 ↑

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
2,000
星标是整个仓库的,不是每个 Skill 的
开发者
NVIDIA-AI-Blueprints
许可证
Apache-2.0
最近代码更新
2026年11月19日
repo 中的 SKILL.md 文件(含译本和模板)
26
主题
computer-vision, generative-ai, long-video-understanding, model-context-protocol, multimodal-ai, natural-language-search, nvidia-nim, rag, real-time-video-analytics, retrieval-augmented-generation, skills, video-agent