Back to Details

report

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Report

报告

Build timestamped video analysis reports by querying the VSS agent for a description of the video using 
POST …/generate
. The agent runs 
video_understanding
 (and related tools) internally. Take the agent’s caption-style text with timestamps and paste it into the Video Analysis Report template below.
通过调用VSS Agent的
POST …/generate
接口获取视频描述，构建带时间戳的视频分析报告。该Agent内部运行**
video_understanding
（及相关工具）。将Agent返回的带时间戳的字幕式文本粘贴到下方的视频分析报告**模板中。

When to Use

使用场景

  • "Generate a report for this video" / "for 
    <sensor-id>
    "
  • "Create an analysis report"
  • "Report on what happens in the uploaded video"
  • "Give me a report"
  • "为这段视频生成报告" / "为
    <sensor-id>
    生成报告"
  • "创建一份分析报告"
  • "对上传的视频内容生成报告"
  • "给我一份报告"

Deployment prerequisite

部署前提

This skill requires the VSS base profile running on the host at 
$HOST_IP
. Before any request:
  1. Probe the VSS agent:
    bash
    curl -sf --max-time 5 "http://${HOST_IP}:8000/docs" >/dev/null
  2. If the probe fails, ask the user:
    "The VSS 
    base
    profile isn't running on 
    $HOST_IP
    . Shall I deploy it now using the 
    /deploy
    skill with 
    -p base
    ?"
    • If yes → hand off to the 
      /deploy
      skill. Return here once it succeeds.
    • If no → stop. Do not run this skill against a missing stack.
    (If your caller has granted explicit pre-authorization to deploy autonomously — e.g. the request says "pre-authorized to deploy prerequisites", or you are running in a non-interactive evaluation harness with that permission — skip the confirmation and invoke 
    /deploy
    directly.)
  3. If the probe passes, proceed.
此Skill要求VSS base配置文件在
$HOST_IP
对应的主机上运行。发起任何请求前，请执行以下步骤：
  1. 探测VSS Agent：
    bash
    curl -sf --max-time 5 "http://${HOST_IP}:8000/docs" >/dev/null
  2. 若探测失败，询问用户：
    "VSS的
    base
    配置文件未在
    $HOST_IP
    上运行。是否现在使用
    /deploy
    Skill并携带参数
    -p base
    进行部署？"
    • 若用户同意 → 转交至
      /deploy
      Skill。部署成功后返回此流程。
    • 若用户拒绝 → 终止流程。请勿在缺少相关组件的情况下运行此Skill。
    （若调用者已明确授权自主部署——例如请求中注明“已预授权部署前置依赖”，或您在具备该权限的非交互式评估环境中运行——则可跳过确认步骤，直接调用
    /deploy
    。）
  3. 若探测成功，继续执行后续步骤。

Agent workflow

Agent工作流程

Run these steps in order:
  1. Sensor / clip — Confirm which sensor id or video the user means. If unclear, ask before proceeding. If the sensor or video is not mentioned directly in the user request, the user may be referring to a video they mentioned previously.
  2. VSS agent deployment — Resolve the agent HTTP base URL. Read 
    VSS_AGENT_PORT
    , 
    EXTERNAL_IP
    / 
    HOST_IP
    , or compose / deployment docs for the machine where the stack runs. Typical pattern: 
    http://<host>:<port>
     with port from env (often 
    8000
     for the agent API).
  3. Query the agent — 
    POST ${VSS_AGENT_BASE_URL}/generate
     with JSON 
    {"input_message": "<prompt>"}
    . Ask for a captioned summary with timestamps (chronological segments, seconds from clip start), e.g. describe scenes and events with time ranges. The sensor / file name must be included in the input message to the agent.
    • DO NOT mention a report to vss agent
  4. Report template — Copy the agent’s final text (timestamped caption/summary) into Analysis Results and fill Basic Information; return that markdown to the user. 0l
按顺序执行以下步骤：
  1. 传感器/视频片段 — 确认用户所指的传感器ID或视频。若信息不明确，需先询问用户再继续。若用户请求中未直接提及传感器或视频，用户可能指的是之前提到过的视频。
  2. VSS Agent部署 — 解析Agent的HTTP基础URL。读取**
    VSS_AGENT_PORT
    、
    EXTERNAL_IP
    / 
    HOST_IP
    ，或查看组件运行所在机器的编排/部署文档。典型格式为：
    http://<host>:<port>
    ，端口来自环境变量（Agent API通常为
    8000
    **）。
  3. 调用Agent — 向**
    POST ${VSS_AGENT_BASE_URL}/generate
    发送JSON请求体
    {"input_message": "<prompt>"}
    。请求获取带时间戳的字幕摘要**（按时间顺序分段，以片段开始后的秒数为单位），例如描述场景和事件的时间范围。请求消息中必须包含传感器/文件名。
    • 请勿向VSS Agent提及报告相关内容
  4. 报告模板 — 将Agent返回的最终文本（带时间戳的字幕/摘要）复制到分析结果部分，并填写基本信息；将该Markdown文档返回给用户。

Query VSS agent (
/generate
)

调用VSS Agent（
/generate
）

bash
undefined
bash
undefined

Set from deployment (compose / .env / host where vss-agent listens)

从部署配置中获取（编排文件/.env/VSS Agent监听的主机）

export VSS_AGENT_BASE_URL="http://localhost:8000"
curl -s -X POST "${VSS_AGENT_BASE_URL}/generate"
-H "Content-Type: application/json"
-d '{"input_message": "Describe in detail what happens in the video for sensor <sensor-id>, with timestamps (start–end in seconds from clip start) for each segment or event."}' | jq .

---
export VSS_AGENT_BASE_URL="http://localhost:8000"
curl -s -X POST "${VSS_AGENT_BASE_URL}/generate"
-H "Content-Type: application/json"
-d '{"input_message": "详细描述<sensor-id>传感器对应的视频内容，为每个片段或事件添加时间戳（以片段开始后的秒数为单位的开始-结束时间）。"}' | jq .

---

Video Analysis Report template

视频分析报告模板

Paste the agent’s timestamped summary under Analysis Results. Fill the table fields (timestamps, source, request).
markdown
undefined
将Agent返回的带时间戳的摘要粘贴到分析结果下方。填写表格字段（时间戳、来源、请求内容）。
markdown
undefined

Video Analysis Report

视频分析报告

Basic Information

基本信息

FieldValue
Report Identifiervss_report_<YYYYMMDD_HHMMSS>
Date of Analysis<YYYY-MM-DD>
Time of AnalysisHH:MM:SS
Reporting AI Agent<e.g. your label>
Video Source<sensor_id or filename>
Analysis Request<description of user's request to you>
字段值
报告标识vss_report_<YYYYMMDD_HHMMSS>
分析日期<YYYY-MM-DD>
分析时间HH:MM:SS
报告生成AI Agent<例如：您的标识>
视频来源<sensor_id或文件名>
分析请求内容<用户向您提出的请求描述>

Analysis Results

分析结果

<agent output: timestamped caption / summary>

---
<Agent输出：带时间戳的字幕/摘要>

---

Cross-Reference

交叉引用

  • vios — VST sensors, storage, and clip URLs if you need to upload a video overify the video exists before calling the agent.
  • video-understanding for follow up questions that cannot be answered directly by the generated report or conversation history.
  • video-summarization / incident-report — other 
    /generate
     patterns; this skill focuses on timestamped captions → report template.
  • vios — 若您需要上传视频或在调用Agent前验证视频是否存在，可参考VST传感器、存储及视频片段URL相关内容。
  • video-understanding — 用于处理无法直接通过生成的报告或对话历史回答的后续问题。
  • video-summarization / incident-report — 其他**
    /generate
    调用模式；本Skill专注于带时间戳的字幕→报告模板**的流程。