muapi-youtube-thumbnail

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

Paste into Claude, ChatGPT or Cursor.

Read the source66 lines
muapi-youtube-thumbnail/SKILL.md66 lines3.2 KBpushed 100d agoRawView on GitHub
1---
2slug: muapi-youtube-thumbnail
3name: muapi-youtube-thumbnail
4version: "1.0.0"
5description: Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed.
6acceptLicenseTerms: true
7---
8 
9 
10# YouTube Thumbnail
11 
12**Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed.**
13 
14## Inputs
15 
16| Name | Type | Required | Default | Description |
17|:---|:---|:---|:---|:---|
18| `title` | text | yes | — | The video title or topic (e.g. "I tried 7 AI tools in 24 hours — here's what happened"). |
19| `channel_style` | text | no | bold, high contrast, bright colors, clean design, YouTube tech aesthetic | Channel brand style (e.g. "dark moody gaming", "bright educational", "minimal corporate"). |
20| `subject_description` | text | no | — | Optional description of the person or subject to feature (e.g. "a surprised young man in a hoodie"). |
21 
22 
23## Steps
24 
25Thumbnails are the #1 factor in YouTube CTR. Generate a single, maximum-impact 16:9 image.
26 
27### Phase A — Plan the composition
28 
29Before generating, briefly reason about the best thumbnail formula for this topic:
30- **Emotion-first**: shocked/curious face if relevant + bold text = high CTR
31- **Text overlay**: 3–5 words max, high-contrast (white/yellow on dark, or vice-versa)
32- **Contrast & saturation**: thumbnails compete in a grid — they must pop
33 
34### Phase B — Generate the thumbnail
35 
361. Build the image generation prompt:
37 - Subject: `{{subject_description}}` if provided, otherwise design an object/scene that dramatizes the topic.
38 - Mood: derives from `{{channel_style}}`.
39 - Composition: rule-of-thirds, subject on left or right with empty space for text.
40 - Style tags: `{{channel_style}}, youtube thumbnail composition, ultra detailed, vibrant, high contrast, 16:9`.
412. Call `muapi image generate` (model=gpt-image-2-text-to-image, aspect_ratio=16:9).
42 
43### Phase C — Text overlay guidance
44 
45After generation, return:
46- **Suggested overlay text**: 3–5 bold words that complement the title `{{title}}`.
47- **Text placement**: where on the canvas to position text (e.g. "bold yellow text, top-right third").
48- **Font recommendation**: style suggestion (e.g. "Impact-style all-caps with black outline").
49 
50## Notes
51- 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).
52- If the user already has a channel image or face photo in the session, use `muapi image edit` to incorporate it.
53- Suggest A/B variants only if the user asks.
54 
55## Trigger Keywords
56 
57`youtube thumbnail`, `yt thumbnail`, `thumbnail`, `video thumbnail`, `youtube cover`
58 
59 
60---
61 
62## Notes for the Executing Agent
63 
64- 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.
65- 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>`.
66- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.

Discussion

Alternatives

Also in Media