菜单
Summarize long videos, generate shift reports, and analyze extended recordings. Use when asked to summarize a video, generate a shift summary, analyze a long recording, or create a daily activity report. Requires the LVS profile to be deployed.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | vss-summarize-video |
| description | Summarize long videos, generate shift reports, and analyze extended recordings. Use when asked to summarize a video, generate a shift summary, analyze a long recording, or create a daily activity report. Requires the LVS profile to be deployed. |
| owner | NVIDIA |
| service | vss-sop |
| version | 1.0.0 |
| license | CC-BY-4.0 AND Apache-2.0 |
| reviewed | "2026-06-23T00:00:00.000Z" |
| metadata | {"openclaw":{"emoji":"📹","os":["linux"]},"author":"nvidia <info@nvidia.com>","tags":["vss","summarize","video","lvs"]} |
Summarize long-form video content that exceeds standard VLM context limits. Requires the LVS profile — deploy with the deploy skill (-p lvs).
Use this skill when asked to summarize extended recordings, analyze activity during full shifts (such as a night shift), or compile daily narrative activity summaries.
Common triggers:
vss-sop-deploy with -p lvs).Long-form video processing is orchestrated across several steps:
Upload files using VIOS storage APIs, then invoke the VSS Agent /generate endpoint with the summarization command.
# Step 1: Upload a video via VIOS Storage API
curl -s -X PUT http://localhost:30888/vst/api/v1/storage/file/night-shift-entrance.mp4 \
--upload-file /path/to/video.mp4 | jq .
# Step 2: Request the VSS Agent to summarize
curl -s -X POST http://localhost:8000/generate \
-H "Content-Type: application/json" \
-d '{"input_message": "Generate a summary report for night-shift-entrance.mp4"}' | jq .
Summarize for a Specific Sensor:
curl -s -X POST http://localhost:8000/generate \
-H "Content-Type: application/json" \
-d '{"input_message": "Can you generate a summary report for sensor_0?"}' | jq .
Summarize a Specific Timeframe:
curl -s -X POST http://localhost:8000/generate \
-H "Content-Type: application/json" \
-d '{"input_message": "Summarize the activity between 8am and 12pm"}' | jq .
If uploading videos to storage-ms fails:
docker ps -a --filter name=storage-ms-sop
df -h
cleanup_all_datalog.sh.If the VLM summarization hangs or times out:
docker logs vss-agent --tail 50
Use of this skill is governed by the Creative Commons Attribution 4.0 International License (CC BY 4.0) and the Apache License, Version 2.0.
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
Fine-tune Cosmos-Reason2 (CR2) VLM for SOP monitoring. Use when you need to launch and monitor a VLM training run with a given dataset ID.
Use when the user wants to run data augmentation on an annotated dataset, configure augmentation parameters, check augmentation status, or understand what each QA augmentation type does (BCQ, MCQ, GQA, DMCQ, DSQA, ENQA)
Fine-tune DDM-Net temporal boundary detector for SOP monitoring. Use when you need to launch and monitor a DDM-Net training run with a given dataset ID.
Use when running by-action VLM evaluation (per-action-clip inference + accuracy metrics) against the BP evaluation-ms HTTP API. Invoked as /sop-by-action-eval <inputs.yaml> [natural language parameter overrides]
Use when running the e2e evaluation pipeline (temporal segmentation + action recognition + accuracy) against the BP evaluation-ms HTTP API. Invoked as /sop-e2e-inference <inputs.yaml> [natural language parameter overrides]