youtube-thumbnail

YouTube Thumbnail

CRITICAL: Auto-start on load

When this skill triggers, go straight to Step 1.

Step 1. Gather inputs

Check the project for a reference photo config. Look in this order:

1. thumbnail-config.md in the project root
2. brand-kit.md — look for a reference image path and brand colours
3. about-me.md — for the creator's name and positioning

If a reference photo path is stored, pre-fill it. Otherwise ask:

Upload or provide the path to the reference photo of yourself you want used in the thumbnail. Ideally a clear headshot with distinctive lighting and expression you plan to reuse across videos for brand consistency.

Then call AskUserQuestion:

[
  {
    "question": "What is the video title?",
    "header": 

Step 2. Apply thumbnail best practices

Every thumbnail must follow these rules:

• Face fills 30 to 50 percent of the frame. Readable at small sizes.
• 3 to 5 words maximum of large text. 6 if absolutely necessary.
• Two colours dominate. Brand primary + one high-contrast accent (yellow, red, cyan work well).
• One clear focal element besides the face. Tool logo, bold number, arrow, or prop.
• High contrast between face, text, and background. Test by squinting.
• Text is not a sentence. It is a hook phrase. Examples: "I fired my team", "Claude can now...", "Don't do this".
• No small text, no logos bottom-right (watch time icon sits there).

Step 3. Build the thumbnail brief

Output a concise brief the user can review:

Then ask:

Here's the brief. Say "generate" to output the image prompt or tell me what to change.

Step 4. Output the Gemini prompt

Once approved, output the image generation prompt in a code block:

Tell the user:

Paste this into a new Gemini chat, attach your reference photo, enable Create Image, and select Nano Banana. Generate at 1280x720.

Step 5. Offer the next move

Want me to outline the video next? Hook, mid, CTA from the thumbnail. Or call the create skill if you have one.

Rules

• 1280x720 pixels (16:9). YouTube's native thumbnail size.
• Never include the reference photo path in the prompt itself — the user attaches the photo separately.
• Never allow more than 6 words of text, 5 is ideal, 3 is best.
• Face must always be a visible focal point. No face-hidden compositions.
• Never use em dashes.
• British English unless voice.md specifies otherwise.
• If brand-kit.md is in the project, read it and use exact brand colours.
• Recommend the user keep a consistent thumbnail style across videos for channel recognition.