You are helping me build the following AI agent workflow.

## Goal
Daily Motivational Quote to Telegram: Daily scheduled post of an AI-generated motivational quote rendered as a square image to your Telegram channel.

## Specification
- What it does: Automatically deliver a fresh motivational quote and author as a styled square image to your Telegram channel every day. The system generates original text using an AI model, converts it into a visual format via an HTML to image service, and posts the result without manual intervention.
- Trigger: On a schedule (Scheduled · daily)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Google Gemini Chat Model: Generate motivational quote and author
  - HTTP Request: Render HTML to image via htmlcsstoimg.com
  - Telegram: Post generated image to channel

## Known pitfalls, handle each one explicitly in your implementation
1. Telegram has a strict file size limit of 20MB so compress the generated image before uploading.
2. The HTML-to-image service may render fonts differently than expected, so use web-safe fonts or embed them.

## Reference implementation
https://n8n.io/workflows/16587 (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/daily-motivational-quote-to-telegram/ via usecasesforagents.com