agentleFS
gawadehimansh-ctrlgawadehimansh-ctrl/claude-skills/SKILL.md

youtube-thumbnail

Skill0 starsChanged 7 months agoMITView on GitHub

Generate a branded YouTube thumbnail from a video title. Uses a reference photo of the creator, high-CTR thumbnail principles, and brand colours to produce a ready-to-generate image prompt for Gemini. Use this skill whenever the user says "thumbnail", "youtube thumbnail", "build me a thumbnail", or wants a video cover image before writing the script. The thumbnail-first workflow mirrors the graphic-first approach for LinkedIn: sells the video before anyone hears a word of the script.

16 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use long-form and youtube-description.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • timscheueraiSkill

    long-form

    Draft written long-form content (newsletter issue, blog post, Substack issue) in your voice. 800-2000 words, structured intro + body + CTA, paragraph-by-paragraph not list-by-list. Pulls voice from /linkedin-copywriter's corpus (same author, same register · longer arc). Runs the brand-doc skill checklist before output. Logs the row in the Notion Content DB and (for newsletters) drafts a separate punchy subject line. Use when asked to "write a newsletter", "draft a blog post", "long-form X", "Substack issue about Y", "weekly newsletter", or "/long-form". For spoken video scripts (YouTube longs / shorts) use /youtube-script instead · the cadence is fundamentally different.

    Also in 3 projects that use this

  • pamelafoxSkill

    youtube-description

    Generate a YouTube description with a brief intro, relevant links, and clickable timestamps for each question.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill triggers, go straight to Step 1.

    line 11
  2. Distinctive:

    Check the project for a reference photo config.

    line 15
  3. Distinctive:

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

    line 21
  4. Distinctive:

    Every thumbnail must follow these rules:

    line 54
  5. Distinctive:

    Never include the reference photo path in the prompt itself — the user attaches the photo separately.

    line 126
  6. Distinctive:

    Never allow more than 6 words of text, 5 is ideal, 3 is best.

    line 127
  7. Distinctive:

    Never use em dashes.

    line 129
  8. Distinctive:

    If brand-kit.md is in the project, read it and use exact brand colours.

    line 131

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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": "Title",
    "multiSelect": false,
    "options": [
      {"label": "I will type the title", "description": "Type the full working title"},
      {"label": "Suggest one", "description": "Given the topic, propose 3 click-worthy titles first"}
    ]
  },
  {
    "question": "Emotional tone?",
    "header": "Tone",
    "multiSelect": false,
    "options": [
      {"label": "Shock / surprise", "description": "Wide eyes, open mouth, bold reaction"},
      {"label": "Curious / thinking", "description": "Slight smirk, raised eyebrow, gaze off-frame"},
      {"label": "Confident / direct", "description": "Eye contact, calm, assertive"},
      {"label": "Frustrated / strong take", "description": "Intense gaze, hand gesture, tension"}
    ]
  }
]

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:

THUMBNAIL BRIEF: [video title]

Composition: [face position, % of frame, direction of gaze]
Text: "[hook phrase, 3-5 words]"
Text placement: [left, right, top, wraps around face]
Colour palette: [primary hex], [accent hex], [background hex]
Supporting element: [logo / prop / arrow / number]
Emotional tone: [tone from Step 1]

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:

Using the attached reference photo of me, generate a YouTube thumbnail at 1280 x 720 pixels (16:9).

Composition:
- Place me [left / right / centre] filling [30-50]% of the frame
- My expression: [tone details — e.g., shocked with wide eyes and open mouth]
- My gaze: [direction — e.g., looking directly at camera / looking off-frame toward the text]

Text:
- Display "[hook phrase]" in large bold sans-serif typography
- Text colour: [hex]
- Text outline: [colour, thickness for readability]
- Text placement: [specific area]

Colour palette:
- Primary: [hex]
- Accent: [hex]
- Background: [hex] — [describe treatment: flat, gradient, blurred scene, etc.]

Supporting element: [specific description of the supporting visual]

Constraints:
- Face must be clear and sharp
- Text must be readable at 320px wide (YouTube mobile size)
- No watermarks, no YouTube UI elements, no bottom-right corner text
- High contrast between face, text, and background

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.