JagZ999

explainer-video

Create animated, camera-zooming product explainer videos (SVG/HTML style) with voiceover, background music, and synced sound effects. Use when the user wants to turn product screenshots or a screen-recording/demo into an explainer video, an animated walkthrough, a narrated product demo, or a launch/marketing video. The skill interactively interviews the user about design (colors, fonts, scenes, tone), then about the TTS provider (and API key), builds a self-contained animated HTML explainer, renders it to a sharp MP4, and produces separate music & SFX stems. Triggers: "make an explainer video", "animate my product screenshots", "turn this demo into a video", "create a narrated walkthrough", "product launch video".

AI & Automation Listed

audio-stems

Generate and place a video/animation's audio as SEPARATE stems — voiceover, background music, and a time-synced sound-effects track — and optionally a ducked master mix. Use when adding music and SFX to an animation or explainer, when iterating on audio WITHOUT re-rendering the video, when you need whooshes/clicks/typing/risers placed on exact timeline moments, or when the user wants the music/SFX/VO delivered as separate files. Generates music + SFX via ElevenLabs and mixes with sidechain ducking. Triggers: "add music and sound effects", "give me the stems separately", "place a whoosh on each transition", "typing/generating sounds", "background music track", "ducked mix so the voice leads", "SFX synced to the animation".

glass-cards

Build frosted "liquid glass" UI cards/panels on a dark animated background, where a card ZOOMS FORWARD to demo itself and then falls back as the next one rises, plus a gentle camera zoom-in/settle. Use for glassmorphism UI mockups, a product explainer's feature panels, an animated card grid where each card steps forward in turn, or any "frosted glass panels that zoom out and come back" / "liquid glass" look. Triggers: "liquid glass cards", "glassmorphism panels", "frosted glass UI", "cards that zoom forward then fall back", "glass panel zooming out and back", "animated card grid that highlights one at a time", "camera zoom into the scene".

kinetic-typography

Add animated "kinetic typography" to an HTML page — headlines whose words cascade in one after another, a centered hero headline that gets pushed aside as content/cards slide in, top/bottom supporting lines that slide out of the headline, and a fractured/"cracked" word effect. Use when building motion-graphics-style titles, an animated headline reveal, a product explainer's text, or any "the words move like that launch video" request. Triggers: "animate the headline", "kinetic typography", "make the title words fly/rise in", "cracked text effect", "headline that slides aside when the cards come in", "word-by-word reveal".

smooth-render

Render an HTML/CSS animation to a smooth, sharp MP4 at native resolution (up to 2K/4K) without choppy motion. Use when a CSS/JS animation (especially glassy/blur/backdrop-filter, gradient, or continuous-motion scenes) renders JANKY or stuttery via screenshot/screencast capture, when you need per-frame-accurate logical-time output with no wall-clock drift, or when muxing audio onto a rendered animation. Triggers: "render my animation to video", "the capture is choppy/stuttering", "export this HTML animation as MP4", "2K render of my web animation", "frames are dropping when I record the page".

Data & Documents Listed

vo-sync

Sync an animation, captions, or cues to a voiceover so visuals land on the spoken words, and pace the timeline tightly to the narration (no dead air). Use when you have (or will generate) a voiceover and want cards/elements/captions to appear exactly when they're mentioned, when card raises feel out of sync with the narration, or when there are long voice-less gaps to tighten. Generates VO with word-level timestamps (ElevenLabs) and computes per-scene durations + cue times from them. Triggers: "sync the voiceover with the animation", "make the cards appear when the voice says it", "the VO is out of sync", "tighten the pacing / remove silent gaps", "land captions on the spoken word", "word-timestamp sync".