You are helping me build the following AI agent workflow.

## Goal
Website Screenshot To Telegram: Takes a visual snapshot of any URL via uProc and posts the image directly to your Telegram channel.

## Specification
- What it does: Capture any website instantly as a clear image and send it directly to your Telegram channel with just one click. You get immediate visual proof of site content without needing to manually download or share screenshots yourself.
- Trigger: Run manually (Manual · on demand)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - uProc: Capture website screenshot
  - Telegram: Send image to channel

## Known pitfalls, handle each one explicitly in your implementation
1. Telegram has strict file size limits so compress the image before uploading to avoid rejection.
2. Bot permissions must include sending media in the target chat or the post will silently fail.
3. uProc may block requests from data center IPs so use a residential proxy if the site blocks bots.

## Reference implementation
https://n8n.io/workflows/858 (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/website-screenshot-to-telegram/ via usecasesforagents.com