Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Geocodes a city name to coordinates, then fetches street-level photos from OpenStreetCam and landmark images from Wikimedia Commons. Uses VLM Run to produce a short travel video and a one-day itinerary in markdown from the collected images.
Combines three public image sources and an AI video model into one automated pipeline, removing the need to manually source photos, write copy, and edit video separately.
When to use it
- Generating a destination brochure before a trip to an unfamiliar city
- Building a one-day itinerary from real street-level and landmark photos
- Creating a short travel video for a specific city without a camera
- Quickly gathering imagery and a travel plan for a client presentation
- Exploring what a city looks like before deciding whether to visit
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a travel brochure and video for Doha, Qatar
- 1Geocodes 'Doha, Qatar' to latitude/longitude using Nominatim
- 2Fetches 3 street-level photos from OpenStreetCam using the coordinates
- 3Fetches 2 landmark images from Wikimedia Commons using the city name
- 4Passes all 5 images to VLM Run to generate a 30-second travel video
- 5Generates a morning/midday/evening one-day travel plan in markdown using the same images
Output directory containing 5 downloaded images, a manifest.json, a travel video file, and a travel_plan.md itinerary
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.