---
type: "post"
id: "geo-sleuth-is-an-open-source-agent-skill-2ee5ec"
slug: "geo-sleuth-is-an-open-source-agent-skill-2ee5ec"
title: "Geo-sleuth is an open-source agent skill that locates photos with no GPS or landmarks"
description: "Geo-sleuth makes photo geolocation a portable agent capability rather than a one-off model prompt."
retrieval_nugget: "Geo-sleuth makes photo geolocation a portable agent capability rather than a one-off model prompt."
published_at: "2026-10-18"
updated_at: "2026-10-18"
record_date: "2026-10-18"
date_kind: "published_at"
topics: ["skills","agents","open-source"]
source_urls: ["https://github.com/Oldcircle/geo-sleuth"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:geo-sleuth-is-an-open-source-agent-skill-2ee5ec"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:35f9ac503ab5e25893d09d52f4594accfca2a7057139c502bd960a42824b0348","reviewed_at":"2026-10-18T18:00:13.644Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"A useful agent skill can package a multi-source workflow and expose evidence for inspection, not merely return an answer.","observed_facts":[{"text":"The repository describes a photo-geolocation skill using OpenStreetMap geometry, elevation skylines, satellite imagery, and street view.","source_urls":["https://github.com/Oldcircle/geo-sleuth"]},{"text":"The README lists Claude Code, Codex, Cursor, and Gemini CLI as compatible environments and gives three example cases with reproduction conditions and checkpoints.","source_urls":["https://github.com/Oldcircle/geo-sleuth"]}],"mechanism":"Reproducible checkpoints let a reader compare divergent runs rather than treating a location guess as self-validating.","why_now":"The project is presented as a cross-agent skill, while its examples make that capability inspectable across runs.","implications":["Portable skills may be more useful when they package procedures together with evidence checkpoints.","The workflow is a concrete example of an agent capability whose intermediate work can be reviewed."],"evidence_boundary":"The evidence is the project's GitHub repository and its own examples; it does not independently establish accuracy, robustness, or operational safety.","watch_conditions":["Whether future versions publish broader, independently assessable evaluations of accuracy and failure modes."],"related_records":[],"new_branch_reason":"No prior New Runtime analytical record was supplied for this project, so this records its portable, evidence-bearing skill design as a distinct case."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/geo-sleuth-is-an-open-source-agent-skill-2ee5ec/","markdown":"https://newruntime.com/posts/geo-sleuth-is-an-open-source-agent-skill-2ee5ec.md","json":"https://newruntime.com/posts/geo-sleuth-is-an-open-source-agent-skill-2ee5ec.json"}
related_patterns: ["skills-become-portable-capability-layer"]
---

# Geo-sleuth is an open-source agent skill that locates photos with no GPS or landmarks

## Retrieval answer

Geo-sleuth makes photo geolocation a portable agent capability rather than a one-off model prompt.

Geo-sleuth makes photo geolocation a portable agent capability rather than a one-off model prompt. The repository describes a skill that combines OpenStreetMap geometry, elevation skylines, satellite imagery, and street view to locate photographs without GPS or obvious landmarks. A useful agent skill can package a multi-source workflow and expose evidence for inspection, not merely return an answer.

The mechanism is: Reproducible checkpoints let a reader compare divergent runs rather than treating a location guess as self-validating. The repository lists Claude Code, Codex, Cursor, and Gemini CLI as compatible environments, and its README provides three example cases with reproduction conditions and checkpoints. Why now: The project is presented as a cross-agent skill, while its examples make that capability inspectable across runs.

The first implication is: Portable skills may be more useful when they package procedures together with evidence checkpoints. This is a project repository and its own examples; it does not independently establish geolocation accuracy, robustness across photo types, or operational safety. Evidence boundary: The evidence is the project's GitHub repository and its own examples; it does not independently establish accuracy, robustness, or operational safety. What to watch: Whether future versions publish broader, independently assessable evaluations of accuracy and failure modes. The repository is the source for these claims: https://github.com/Oldcircle/geo-sleuth

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Skills](https://newruntime.com/topics/skills.md): Explore the skills topic hub.
- topic hub: [Agents](https://newruntime.com/topics/agents.md): Explore the agents topic hub.
- topic hub: [Open Source](https://newruntime.com/topics/open-source.md): Explore the open-source topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)