muapi-youtube-thumbnail
Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed.
Security Assessment
About muapi-youtube-thumbnail
muapi-youtube-thumbnail is a guided recipe for designing a high-click-through YouTube thumbnail. Because thumbnails are a primary driver of YouTube CTR, the skill focuses on producing a single, maximum-impact 16:9 image built around striking imagery, bold text placement, and an emotional face or subject when relevant.
The workflow runs in phases. Phase A plans the composition, reasoning about the best formula for the topic (emotion-first faces, three-to-five-word high-contrast text overlays, and strong contrast and saturation so the image pops in a crowded grid). Phase B builds an image-generation prompt from the user's inputs — title (required), channel_style, and optional subject_description — using rule-of-thirds framing with empty space reserved for text, then calls the muapi CLI (muapi image generate with model gpt-image-2-text-to-image at 16:9). Phase C returns text-overlay guidance: suggested 3–5 word overlay text, placement, and font recommendation, with advice to add final text in post-production tools like Canva or Photoshop since image models render text unreliably. It can also incorporate an existing face or channel image via muapi image edit.
Target users are YouTubers, content creators, and social-media designers who want a fast, formula-driven thumbnail. It is an LLM-orchestrated recipe that drives the official muapi CLI, authenticating via muapi auth configure and the MUAPI_API_KEY environment variable, with a documented raw-endpoint fallback that sends the user's own API key to the official muapi API. Credential use follows standard official tooling with no exfiltration, making it a safe creative-generation utility.
FAQ
What does this skill produce?
A single high-impact 16:9 YouTube thumbnail image plus guidance on overlay text wording, placement, and font, optimized for click-through in a crowded grid.
What inputs does it need?
A required title (the video topic), and optional channel_style (brand look) and subject_description (a person or subject to feature).
What are the prerequisites?
Access to the muapi CLI and a MUAPI_API_KEY; run muapi auth configure if the key is unset. It generates images with the gpt-image-2-text-to-image model at 16:9.
Why does it recommend adding text in post-production?
Image models render text unreliably, so the skill keeps text out of the generation prompt and suggests adding the final overlay in tools like Canva or Photoshop.
How are credentials handled?
Authentication uses the official muapi CLI and the MUAPI_API_KEY environment variable; a documented curl fallback sends your own key to the official muapi API endpoint, with no third-party exfiltration.
Install muapi-youtube-thumbnail
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
samuraigpt/generative-media-skills