This is YUV.AI's production pipeline for turning raw selfie or screenshare footage into polished short-form videos with liquid-glass cards, MrBeast-paced cuts, and karaoke captions. It chains two skills: video-use handles transcription and word-snapped cuts via ElevenLabs Scribe, hyperframes builds the visual composition layer with real CSS backdrop-filter and GSAP motion graphics. The style is opinionated and specific: Anton uppercase for English display text, Rubik Black for Hebrew, always renders both 9:16 and 16:9, always saves with versioned backups. If you need Apple-keynote polish on talking-head content without manually syncing captions or faking glass effects in After Effects, this is the automated route. Bilingual by design, Hebrew gets full RTL treatment.
npx -y skills add hoodini/ai-agents-skills --skill yuv-viral-video --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
mindrally/skills
giuseppe-trisciuoglio/developer-kit
syncfusion/react-ui-components-skills
supercent-io/skills-template
binjuhor/shadcn-lar