geolocation-skill

Original：🇺🇸 English
Translated
1 scriptsChecked / no sensitive code detected

Systematic visual geolocation reasoning from images. [VAD] Analyzes photos, street views, or satellite imagery to determine location. Uses visual clue extraction, hypothesis formation, and web verification. [NÄR] Use when: geolocate, identify location, where is this, find this place, geographic analysis, location from image, OSINT geolocation [EXPERTISE] Visual analysis, geographic indicators, verification strategies

4installs
Sourcecarlheath/ogmios
Added on

NPX Install

npx skill4agent add carlheath/ogmios geolocation-skill

Tags

Translated version includes tags in frontmatter
geolocation-reasoningvisual-image-analysisosint-geolocationhypothesis-verificationiterative-reasoning

SKILL.md Content

View Translation Comparison →

Geolocation Reasoning

Method: Iterative reasoning loop (max 5 iterations) Inspiration: GeoVista research framework

Core Workflow

1. Visual Clue Extraction

CategoryLook for
Text/SignageLanguages, scripts, street signs, license plates, phone formats
InfrastructureRoad markings, traffic lights, poles, utilities, bollards
ArchitectureMaterials, styles, roof types, density patterns
NatureVegetation, terrain, geology, sun position, weather
CultureVehicles, driving side, clothing, shops, brands

2. Hypothesis Formation

Form hypotheses at multiple scales:
ScaleExample
Continent/RegionEurope, Southeast Asia
CountrySpecific nation
Region/StateSub-national
City/TownLocality
PreciseStreet-level
For each: Note supporting evidence, confidence (H/M/L), conflicts.

3. Image Examination

When details unclear:
  • Crop regions of interest
  • Enhance text/signage
  • Isolate architectural details

4. Web Search Verification

StrategyQuery pattern
Sign text
"[exact text]" location
Features
[feature] [suspected region]
Business
"[name]" address
Landmark
[description] landmark [region]
Road
[designation] [country]
Cross-reference multiple clues, look for consistent attribution.

5. Iterative Refinement

After each cycle:
  1. Update hypothesis confidence
  2. Identify remaining uncertainties
  3. Determine if more examination helps
  4. Continue until confident or limit reached

Output Format

**Location Analysis**

Observed Clues:
- [Key observations with confidence]

Reasoning Process:
- [Hypothesis formation and verification]

**Conclusion**
- Most likely location: [As specific as evidence allows]
- Confidence: High/Medium/Low
- Key evidence: [Primary determinants]
- Uncertainties: [What remains unclear]

Important Considerations

AspectGuideline
ConfidenceHigh requires multiple independent confirmations
Single cluesCan mislead (similar signage in multiple countries)
PrivacyDon't identify individuals or residential addresses
IterationMax 5 cycles, stop when marginal value low

References

  • references/visual-clues.md
    — Clue categories
  • references/regional-signatures.md
    — Region-specific indicators
  • references/verification-strategies.md
    — Search patterns
🎯 COMPLETED: [SKILL:geolocation-skill] [location identified from image] 🗣️ CUSTOM COMPLETED: [SKILL:geolocation-skill] [Location found]