Generate and query incident reports from VSS — look up incidents in Elasticsearch, analyze incident patterns, generate narrative reports. Use when asked about incidents, incident reports, PPE violations, safety events, or "what happened". Requires the alerts profile to be deployed.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Instruções da origem · Visualização somente leitura
name
vss-generate-video-report
description
Generate and query incident reports from VSS — look up incidents in Elasticsearch, analyze incident patterns, generate narrative reports. Use when asked about incidents, incident reports, PPE violations, safety events, or "what happened". Requires the alerts profile to be deployed.
Query incidents from Elasticsearch, analyze patterns, and generate reports. Requires the alerts profile — deploy with the deploy skill (-p alerts).
Overview
Use this skill when you need to query incidents, evaluate safety violations (such as PPE compliance), or compile visual/narrative incident reports. This covers requests like:
"Show me incidents from today"
"Generate an incident report"
"How many PPE violations this week?"
"Summarize incidents for sensor X"
"What happened at the loading dock?"
Prerequisites
Alerts Profile Deployed: Ensure that the alerts profile has been successfully configured and started (vss-sop-deploy with -p alerts).
Elasticsearch Access: Port 9200 must be accessible.
VA-MCP Access: Port 9901 must be reachable.
Instructions
1. Querying Incidents via VA-MCP
To query incidents, you must follow the two-step MCP JSON-RPC pattern on port 9901:
Initialize Session: Fetch a session ID from the response header.
Call Get Incidents: Invoke video_analytics__get_incidents with desired filters (sensor source, time range, VLM verdict).
2. Pattern Analysis
To identify peaks or compute metrics, invoke video_analytics__analyze with parameters like max_min_incidents or avg_num_people.
3. Report Generation
To generate a full narrative report, make a POST request to the VSS Agent at port 8000. This triggers a Human-in-the-Loop (HITL) prompt-editing workflow.