Locate photo origins with the Geo Sleuth agent skill
Install a cross-runtime agent skill that geolocates photos using EXIF, image preparation, OCR, OpenStreetMap geometry, elevation skylines, satellite imagery, and browser-backed reverse image search.
npx skills add agentskillexchange/skills --skill locate-photo-origins-with-the-geo-sleuth-agent-skill
npx skills add Oldcircle/geo-sleuth -g -a claude-code -a codex -a cursor -a gemini-cli -a opencode -a github-copilot -y, then ask the agent to run the installed scripts/doctor.py checks and address missing dependencies before analyzing photos.Use Geo Sleuth when an agent needs to investigate where a supplied photo was taken and return evidence rather than a blind guess. The workflow is to install the standard SKILL.md package with the skills CLI, run the bundled doctor checks, hand the agent an image, and let it coordinate the provided Python scripts for metadata inspection, image preparation, OCR, reverse image search, OpenStreetMap and elevation lookups, skyline or geometry scoring, and evidence image creation. Invoke this instead of using map or image-search products manually when the operator wants one reproducible photo-geolocation investigation with the agent showing intermediate evidence and uncertainty. The scope boundary is photo-origin research on images the operator is allowed to analyze; it is not a general OSINT platform, surveillance workflow, or ordinary image-search product card.
What this skill actually does
Inputs and prerequisites: Agent runtime that reads SKILL.md, Node/npm skills CLI, Python 3.10+, uv, curl, Google Chrome or Playwright Chromium.
Setup notes: Install with npx skills add Oldcircle/geo-sleuth -g -a claude-code -a codex -a cursor -a gemini-cli -a opencode -a github-copilot -y , then ask the agent to run the installed scripts/doctor.py checks and address missing dependencies before analyzing photos.
Source and verification boundary: use https://github.com/Oldcircle/geo-sleuth as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.