Youtube

Automate audio/video transcription, meeting notes, subtitle generation, and content processing

Autonomous task execution from GTD.md items. Use when processing GTD tasks, call prep, outreach, or podcast preparation.

Build a premium cinematic landing page with mouse-scrub video hero and brand-driven narrative-arc sections. Use whenever the user provides a hero video plus a product / subject / brand and wants a landing page, promo site, product showcase, marketing page, or storytelling site. Works for any language (RTL or LTR — Hebrew, English, Arabic, Spanish, French, Japanese, etc.) and any subject (food, tech, animals, fashion, services, SaaS, wildlife campaigns, music releases, books, real estate). The signature effect is mouse-driven video scrubbing — the hero video lives across the entire page as a fixed backdrop, and moving the mouse left-right scrubs the video timeline so the subject responds to the cursor. Below the hero, 4-5 fully-opaque sections each carry their own brand identity (color, typography emphasis, layout pattern) and walk the viewer through a narrative arc (e.g. longing → joy → nostalgia → contemplation → action). Triggers on phrases like "build a landing page from this video", "cinematic landing page", "mouse scrub hero", "video that follows the cursor", "Apple-style premium product page", "the baby video scrub thing", "narrative landing page", "scrubable hero", "golden landing template", "make a promo site for this brand", "build me a showcase page with this clip". Do NOT use for parallax frame-scrub landings where the page itself doesn't scroll (use `parallax-landing-page` instead) or for video editing / captioning workflows (use `video-edit`).

Turn any video into a cinematic scroll-driven landing page — Apple-style hero where scrolling progresses the visible frame through the video. Use when the user provides a video file and asks for "a landing page from this video", "scroll-frame website", "Apple-style scroll site", "hero that scrubs the video", "like the GitHub Copilot landing", or any equivalent. Extracts N evenly-spaced frames via ffmpeg, builds a self-contained HTML page with a sticky hero + JS scroll listener that swaps the visible frame as you scroll, plus headline, sections and CTA below. For YUV.AI projects, applies the yuv-design-system skill in Neon mode (pink/cyan/white, default for YUV.AI web) — Decks (purple/yellow) is reserved for slides only. For generic / non-YUV.AI projects, picks an appropriate palette per the source video. Output is one folder with `index.html` and a `frames/` directory — drop on any static host.

Top-of-pyramid orchestrator for Yuval Avidani's YUV.AI brand work. Apply when (a) the user wants YUV.AI output and the medium is ambiguous or multi-medium, (b) the user is planning a launch or cross-channel campaign for YUV.AI, or (c) explicitly invokes /yuv-pilot or asks "what should I build for YUV.AI / my brand". Triggers: "for YUV.AI", "for my brand", "YUV.AI launch", "ship something for me", "orchestrate", "cross-channel", "multi-platform for me", "yuv-pilot", Hebrew השקה, מולטי-פלטפורמה ל-יובל. Does NOT do the work — it identifies the right downstream YUV.AI skills (yuv-design-system across 3 modes, yuv-decks for slides, yuv-viral-video for short MP4s, hyperframes for HTML→MP4, nano-banana for in-brand imagery, gsap for animation), explains the composition, hands off. Does NOT apply to non-YUV.AI requests. When a request is clearly single-medium (just a deck, just a viral short), the specific skill wins — yuv-pilot is the front door for ambiguous or multi-output requests.

GPU VRAM management patterns for sharing memory across services (Ollama, Whisper, ComfyUI). OOM retry logic, auto-unload on idle, and service signaling protocol.