geolocation-skill

Extract visual clues from images and verify location hypotheses through web searches.

9|5|Updated Nov 9, 2025
One-click install
npx skills add https://github.com/carlheath/ogmios --skill geolocation-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geolocation-skill
Source: https://github.com/carlheath/ogmios/tree/main/.claude/skills/geolocation-skill
Command: npx skills add https://github.com/carlheath/ogmios --skill geolocation-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you determine the geographical location of a subject by analyzing visual information present in images, combating the challenge of identifying places from photos alone.

Core Features & Use Cases

  • Visual Clue Extraction: Analyzes text, infrastructure, architecture, nature, and cultural elements within an image.
  • Hypothesis Formation: Generates location hypotheses at various scales (continent, country, city, precise).
  • Web Verification: Uses targeted web searches to confirm or refute hypotheses.
  • Use Case: You receive a photo from a friend in an unknown city and want to know where it was taken. This Skill can analyze the photo's visual cues and use web searches to identify the exact location.

Quick Start

Use the geolocation-skill to determine the location of the provided image file 'street_view.jpg'.

Frequently Asked Questions about geolocation-skill

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

FAQPage Schema
How do I identify a location from an image?

Image geolocation works by extracting visual clues such as text, infrastructure, and cultural elements from a photo. It then forms geographic hypotheses at various scales and uses targeted web searches to verify the exact location.

Can I determine the exact location of a street view photo using visual verification?

Yes, you can determine the exact location of a street view photo using visual verification. The Skill analyzes geographic indicators and cultural elements within the image, then executes web search strategies to confirm or refute the generated location hypotheses.

What types of visual clues are analyzed for location identification?

For location identification, the Skill analyzes text, infrastructure, architecture, nature, and cultural elements within an image. These visual clues are extracted systematically to generate and verify geographic location hypotheses.

Do I need the Pillow library to perform visual geolocation from images?

Yes, the Pillow library is required as a dependency to perform visual geolocation from images. It supports the underlying image analysis processes needed to extract visual clues for geographic indicator recognition and hypothesis verification.

What is the best way to verify location hypotheses from satellite imagery?

The best way to verify location hypotheses from satellite imagery is to extract visual clues, form hypotheses ranging from continent to precise location, and execute targeted web searches to systematically confirm or refute each geographic hypothesis.