geo-sleuth is a skill for Claude Code. You hand Claude a photo and say find where this photo was taken. It works even when there is nothing to read: no sign, no plate, no landmark.
Here is what it does, how to set it up, and the catch.
What you get
- The camera position as coordinates with an error radius.
- The direction the camera was facing.
- A satellite evidence image with the camera's field of view drawn on it.
- A graded confidence, and every conclusion tied to a command that actually ran and the file it produced.
How it finds the spot
- It reads the photo like a detective: shadows become a compass bearing, a ridge line becomes a fingerprint, evenly spaced bridge pillars become a ruler.
- It pulls real map data (OpenStreetMap), elevation data, satellite tiles and street view to search the area.
- Scripts rank the candidates; Claude only judges between the top few.
- Its first case: a rice paddy and a railway bridge with no text in the frame. 27,335 bridge segments, then 171 sites, 22, 3, 1: about 2 meters from the real camera spot.
Free, for your email
Get the full setup steps + the copy-paste setup prompt
The rest of this guide (4 more sections, 2 copy-paste prompts) opens right here. The setup prompt, one paste into Claude that sets it all up, comes by email only. Use your real address.
50,000+ follow where these guides come from. No spam, unsubscribe in one click.