You are helping me build the following AI agent workflow.

## Goal
Auto-Publish YouTube Shorts to TikTok: Every hour, it checks your YouTube Shorts playlist for new videos, downloads them, and automatically posts or drafts them on TikTok.

## Specification
- What it does: You get your latest YouTube Shorts on TikTok automatically every hour without lifting a finger. This process checks your playlist, downloads the new videos, and posts or drafts them directly to your account while keeping everything up to date.
- Trigger: On a schedule (Scheduled · every hour)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - n8n: Workflow orchestration and data table deduplication
  - YouTube RSS Feed: Polling for new Shorts in a playlist
  - RapidAPI YouTube Media Downloader: Downloading video files as MP4
  - TikTok Content Posting API: Uploading and publishing videos

## Known pitfalls, handle each one explicitly in your implementation
1. TikTok requires specific aspect ratios so you must add a video processing node to crop or pad vertical videos to 9:16 resolution.
2. YouTube RSS feeds often delay updates by several hours so implement a retry mechanism with exponential backoff for missing new items.

## Reference implementation
https://n8n.io/workflows/16171 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/auto-publish-youtube-shorts-to-tiktok/ via usecasesforagents.com