event-template-mapping

Community

Map LLM visual observations to video monitoring Event Candidate semantics.

Authorbettercallfan
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps map LLM visual observations or method-level event results into final video monitoring Event Candidate semantics, streamlining the event recognition process.

Core Features & Use Cases

  • Visual Event Mapping: Converts visual observations into event candidates based on LLM output.
  • Event Candidate Semantics: Generates event type, confidence, severity, reason, and evidence frames.
  • Use Case: In a video surveillance system, this skill can be used to process and categorize events based on visual observations, enhancing the efficiency of security monitoring.

Quick Start

Run the event-template-mapping skill with the following command: `python event-template-mapping/scripts/run.py --method-results-json <method_results.json> --template-name <template_name> --camera-id <camera_id> --config <config.json> --output <event.json>

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: event-template-mapping
Download link: https://github.com/bettercallfan/deerflow/archive/main.zip#event-template-mapping

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.