PluginBench
Skill
Pass
Audit score 90

muapi-youtube-thumbnail

samuraigpt/generative-media-skills

Design high-CTR YouTube thumbnails with striking imagery, bold text, and emotional impact.

What is muapi-youtube-thumbnail?

This skill generates eye-catching YouTube thumbnails optimized for click-through rate. It guides composition planning, image generation via MUAPI, and text overlay placement to ensure thumbnails stand out in YouTube's grid and drive viewer engagement.

  • Plans thumbnail composition using emotion-first design and high-contrast principles
  • Generates 16:9 aspect ratio images tailored to channel style and topic
  • Provides suggested overlay text (3–5 words) with placement and font recommendations
  • Incorporates optional subject descriptions (faces, people, objects) for maximum impact
  • Leverages MUAPI image generation with vibrant, high-contrast styling

How to install muapi-youtube-thumbnail

npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-youtube-thumbnail
Prerequisites
  • MUAPI API key configured (via `muapi auth configure`)
  • MUAPI CLI installed and accessible
  • Access to post-production tools (Canva, Photoshop) for text overlay application
Claude Code
Cursor
Windsurf
Cline

How to use muapi-youtube-thumbnail

  1. 1.Provide the video title or topic and optional channel style description
  2. 2.Optionally describe the subject or person to feature in the thumbnail
  3. 3.The skill will plan the composition using emotion-first design principles
  4. 4.The skill generates a 16:9 image via MUAPI image generation
  5. 5.Review the generated image and suggested overlay text, placement, and font style
  6. 6.Apply the text overlay in your post-production tool (Canva, Photoshop, etc.)

Use cases

Good for
  • Creating thumbnails for a new YouTube video before upload
  • Designing A/B test variants to compare CTR performance
  • Generating thumbnails for educational, gaming, or tech channel content
  • Quickly iterating on thumbnail concepts during video production workflow
  • Ensuring visual consistency with existing channel branding and style
Who it's for
  • YouTube content creators and video producers
  • Digital marketers optimizing video performance
  • Social media managers handling multiple channels
  • Video editors integrating thumbnail design into production pipelines

muapi-youtube-thumbnail FAQ

Can the skill add text directly to the thumbnail image?

No. Image models render text unreliably, so the skill provides text suggestions, placement guidance, and font recommendations for you to apply in post-production tools like Canva or Photoshop.

What if I don't have a subject description?

The skill will design an object or scene that dramatizes the topic based on your video title and channel style.

Can I use my own channel image or face photo?

Yes. If you have a channel image or face photo in your session, the skill can incorporate it using `muapi image edit`.

How many words should the overlay text be?

3–5 words maximum. Shorter text with high contrast performs better for CTR in YouTube's grid layout.

What aspect ratio does this generate?

16:9, which is the standard YouTube thumbnail format.

Full instructions (SKILL.md)

Source of truth, from samuraigpt/generative-media-skills.


slug: muapi-youtube-thumbnail name: muapi-youtube-thumbnail version: "1.0.0" description: Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed. acceptLicenseTerms: true

YouTube Thumbnail

Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed.

Inputs

NameTypeRequiredDefaultDescription
titletextyes—The video title or topic (e.g. "I tried 7 AI tools in 24 hours — here's what happened").
channel_styletextnobold, high contrast, bright colors, clean design, YouTube tech aestheticChannel brand style (e.g. "dark moody gaming", "bright educational", "minimal corporate").
subject_descriptiontextno—Optional description of the person or subject to feature (e.g. "a surprised young man in a hoodie").

Steps

Thumbnails are the #1 factor in YouTube CTR. Generate a single, maximum-impact 16:9 image.

Phase A — Plan the composition

Before generating, briefly reason about the best thumbnail formula for this topic:

  • Emotion-first: shocked/curious face if relevant + bold text = high CTR
  • Text overlay: 3–5 words max, high-contrast (white/yellow on dark, or vice-versa)
  • Contrast & saturation: thumbnails compete in a grid — they must pop

Phase B — Generate the thumbnail

  1. Build the image generation prompt:
    • Subject: {{subject_description}} if provided, otherwise design an object/scene that dramatizes the topic.
    • Mood: derives from {{channel_style}}.
    • Composition: rule-of-thirds, subject on left or right with empty space for text.
    • Style tags: {{channel_style}}, youtube thumbnail composition, ultra detailed, vibrant, high contrast, 16:9.
  2. Call muapi image generate (model=gpt-image-2-text-to-image, aspect_ratio=16:9).

Phase C — Text overlay guidance

After generation, return:

  • Suggested overlay text: 3–5 bold words that complement the title {{title}}.
  • Text placement: where on the canvas to position text (e.g. "bold yellow text, top-right third").
  • Font recommendation: style suggestion (e.g. "Impact-style all-caps with black outline").

Notes

  • Never put too much text in the prompt — text rendering in image models is unreliable. Guide the user on adding text in post-production (Canva, Photoshop).
  • If the user already has a channel image or face photo in the session, use muapi image edit to incorporate it.
  • Suggest A/B variants only if the user asks.

Trigger Keywords

youtube thumbnail, yt thumbnail, thumbnail, video thumbnail, youtube cover


Notes for the Executing Agent

  • This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call muapi CLI commands. Use muapi auth configure first if MUAPI_API_KEY is unset.
  • For model IDs without a CLI alias yet, fall back to the raw endpoint via curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}' and poll with muapi predict wait <request_id>.
  • Substitute {{input_name}} placeholders with the user's actual inputs before issuing each call.