vision

Extract structured travel details from images using the Vision API.

Updated Feb 13, 2026
One-click install
npx skills add https://github.com/JeffTermited/packgo-travel --skill vision-jefftermited
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vision
Source: https://github.com/JeffTermited/packgo-travel/tree/main/server/agents/_subskills/vision
Command: npx skills add https://github.com/JeffTermited/packgo-travel --skill vision-jefftermited

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Analyzes images and web screenshots using Vision API to extract structured information such as text, objects, layout cues, and key travel details, reducing manual data extraction and interpretation.

Core Features & Use Cases

  • Extracts OCR text, titles, prices, dates, and itinerary data from screenshots and photos.
  • Identifies landmarks, visual elements, and page layout to support automated itinerary assembly.
  • Performs basic image quality checks to flag unusable content for review.

Quick Start

Analyze a provided screenshot of a travel itinerary or webpage to generate structured data from visual content.

Frequently Asked Questions about vision

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and itinerary details from a travel screenshot?

To extract text and itinerary details from a travel screenshot, use this Skill to apply Vision API for OCR and object recognition. It identifies titles, dates, prices, and landmarks, converting visual page layouts into structured data.

What is the best way to automate data extraction from travel images?

Automating data extraction from travel images is best done by processing them through Vision API analysis. This automatically pulls out itinerary fields, visual elements, and captions, reducing manual interpretation and supporting automated itinerary assembly.

Can I use image analysis to identify landmarks and prices in photos?

Yes, you can use image analysis to identify landmarks and prices in photos. The Skill processes visual content with Vision API to extract structured information such as text, prices, dates, and landmark details from provided screenshots.

Does OCR work with any image format for travel itinerary extraction?

OCR for travel itinerary extraction requires input images to meet recommended formats and sizes. The Skill performs basic image quality checks to flag unusable content, ensuring the Vision API can successfully process the visual data.

Why does Vision API fail to extract text from my low quality screenshot?

Vision API may fail to extract text from a low quality screenshot due to poor image formats or sizes. The Skill includes basic image quality checks to flag unusable content and provides graceful fallbacks when OCR or recognition fails.