Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Takes a tabiji.ai itinerary URL, sources and vision-scores Instagram photos for the destination and each attraction, applies text overlays, and publishes a 6-slide carousel via the Instagram Graph API. Uses a 3-agent pipeline: photo finding, overlay rendering, and publishing with cleanup.
Handles the full pipeline from URL to published post in one command, replacing separate photo research, image editing, and manual Instagram upload steps.
When to use it
- Turning a tabiji.ai city itinerary into a ready-to-post Instagram carousel
- Sourcing and scoring destination photos without manual searching
- Adding attraction names and insider tips as text overlays to travel photos
- Publishing multi-slide Instagram posts programmatically from a single URL
- Automating social content creation for each new tabiji.ai itinerary
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create an Instagram carousel for my Kuala Lumpur itinerary at tabiji.ai/i/kl-trip/
- 1Fetches the tabiji.ai itinerary and extracts the destination name and top 5 attraction names
- 2Searches Instagram for photos of each subject, downloads candidates, and vision-scores each to select the best image per subject
- 3Runs the overlay script on each selected photo to produce 6 slides with titles, tips, and watermarks
- 4Pushes slides to the tabiji GitHub repo for public hosting, then creates carousel item containers and a carousel container via the Instagram Graph API
- 5Publishes the carousel, retrieves the post permalink, and deletes the hosted images from GitHub and local temp files
Instagram carousel post URL (e.g. https://www.instagram.com/p/ABC123/)
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.