Video & Animation

Provider-independent production workflow for AI agents creating brand launch films, product reveal videos, manifesto films, campaign hero films, website hero videos, investor/customer launch assets, and social cutdowns. Use when planning, scripting, generating, editing, reviewing, or delivering launch films that must align strategy, claims, brand voice, visual direction, product proof, accessibility, compliance, and multi-platform delivery.

Procedural sound design with the sfx engine — writing a cue sheet against a video's timeline, which sound goes with which visual event, gain hierarchy, panning, musical key, automatic mastering to -14 LUFS, adding new generators, and verifying sync. Use when adding, changing or checking audio, SFX, music beds or loudness for any video in this repo.

Makes premium, fact-checked videos that follow a brand's guidelines, in code with Remotion — brand films, product showcases, event or conference openers, teasers and promos — with motion design, 3D, real photos, AI narration in any language, generated images, music, sound effects, captions and 1080p60 exports. Uses whichever AI services the person has (OpenRouter, Gemini, ElevenLabs, GPT Image; all optional). Includes a quality checklist, a fact-checking workflow, review tools and a starter project. Use when someone asks to create, script, voice, score, render, revise or fix a video, film, promo, motion-graphics piece, intro/outro, opening film or product showcase, or gives feedback on one ("the transition feels weird", "the voice sounds different", "make it more premium", "add captions", "another version with a different voice"), even if they never mention Remotion.

Act as the director of a short AI-generated film, from a rough idea to a finished cut, with as few paid re-generations as possible. Claude writes the story, shot list, palette and every prompt; an image model (Codex preferred, Higgsfield as fallback) draws character sheets and first/last frames for each shot; a video model (Seedance via Volcano Ark or Higgsfield) animates between those frames; ffmpeg/Python handle the edit. Independent reviewer agents check every stage before money is spent. Use when someone wants to make an AI short film, AI animation, AI music video, story video, "make a film from this idea", "turn this story into a video", storyboard + generate shots, or asks for a Seedance / Kling / Veo multi-shot workflow. NOT for launch/promo videos of an app (use launch-film) and NOT for editing a talking-head clip into a reel.

Expert skill for designing, implementing, reviewing, and optimizing premium web animations and motion systems. Use whenever a website, landing page, web app, React/Next.js interface, UI component, scroll experience, page transition, micro-interaction, hover effect, text reveal, parallax effect, SVG animation, loading state, or interactive motion needs to be designed or improved. Prioritizes purposeful motion, visual hierarchy, natural easing, accessibility, responsive behavior, performance, and cohesive motion systems over decorative animation. Selects the simplest appropriate technology between CSS, Web Animations API, View Transitions API, native scroll-driven animations, GSAP, Motion/Framer Motion, Lottie, Rive, SVG, Canvas, or WebGL.

Build an animated, video-driven landing page or hero section - full-bleed looping video background with a gradient overlay, glass cards, animated headline and call-to-action buttons, scroll reveals - that stays fast and accessible (poster image, lazy video, reduced-motion and mobile fallbacks). Includes a site template, ffmpeg asset script and a motion audit script. Use proactively when asked for an animated website, motion site, cinematic landing page, video hero, or to make a page feel alive.

Use when the user wants to create AI-generated videos from an idea or script — 短视频/AI视频/做视频/视频制作/分镜/镜头脚本/故事板/图生视频/视频提示词/人物设定图/场景参考图/道具参考图/情景图/首帧/尾帧/口型/视频配音/多集短剧/系列视频/漫剧/微表情/情绪戏/2D转真人/自拍风/UGC/vlog/韩系街拍/导演风格（王家卫/诺兰/韦斯安德森等）/转场设计. NOT for executing video editing itself, NOT for real-actor filming guidance, NOT for pure text writing without video generation intent.

Records the best scenes of a website or web app (WebGL hero, 3D, scroll) as 1080p MP4 for decks, uploads them to Figma Slides, and builds brand or product showreels in Remotion. Use on "record the site scenes", "site video for the deck", "showreel", "launch video", "gerar vídeo do site", "vídeo pro deck", "reel do produto", /site-reels.

Add live, interactive effects that keep a web page moving after it loads. They are a WebGL aurora / liquid-light shader behind the hero that bends around the pointer, holographic 3D tilt cards with glare and an iridescent edge, a grid spotlight that follows the cursor, RGB-split glitch headings, and hover text scramble on links and buttons. Ships drop-in React/Next.js code (one shared rAF loop, zero layout shift, accessible) plus the rules that keep it smooth. Use this whenever someone wants a page to feel more alive, trippy, premium or "wow". Also use it for a shader or animated gradient background, 3D/tilt/hologram cards, cursor-follow or spotlight effects, glitch or decoding/scramble text, or interactive hover effects, even if they don't name a technique.

Use when adding or fixing motion on a web page - scroll reveals, hero intros and crossfades, ambient loops, looping background video, image rotators, sticky elements - or when an animation stutters, fires at the wrong time, plays off-screen, or does not run at all.

Use when someone wants to make a motion graphics video, launch film, product explainer, app promo, animated reel or short in code (HTML, Canvas and CSS rendered frame by frame by Chrome), with real sound design, a screen-on-laptop mockup, and a measured quality gate. Free, no After Effects, no Remotion, no paid tools. Triggers - motion graphics, motion design video, animated reel, launch video, promo film, explainer, kinetic typography, make a video like this, sound effects for my video, put my video on a laptop screen, green screen laptop, instagram reel, tiktok, short.

Build an interactive website hero where the brand's poster is printed on a cotton cloth pinned to a washing line with wooden pegs, under an open sky with drifting clouds - visitors press a soft dent into the cloth with the pointer, grab it anywhere and pull it, and when they let go it swings back and settles (a real cloth simulation, not a video), in the brand's colours, fonts, logo, headline and buttons. One self-contained HTML page plus a paste-in embed, checked for contrast and layout at four widths, with a still picture when WebGL or the network fails and for reduced motion, and a frame-perfect MP4 and poster recorded in headless Chrome in which a drawn pointer pulls the cloth. Use when someone wants a playful, touchable hero, a draggable flag or banner, a poster on a clothesline, a launch header people play with, or a hero for a textile, laundry, outdoor or "light and simple" product.

Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or generate photoreal assets through kie.ai, write semantic HTML, and verify desktop, mobile, and reduced-motion scroll states visually. Use for "scrollcraft", "scroll craft", "layered hero", "premium hero", "cinematic hero", "scrollytelling", "scroll animation site", "a site where scrolling plays a video", "Apple-style landing page", "3D scroll world", "interactive landing page", "make my brand a scroll experience", "this looks like a template", or requests for a distinctive website that feels like an experience rather than a document.

Create Algerian Darija narration and integrate Natiq audio into Remotion, motion graphics, or ffmpeg video projects. Use when a video needs Algerian voiceover or existing narration needs revision.

使用哪都通 / Nxtpath 的 Seedance 2.5 API，从参考图或文本生成视频，续查已有任务并下载成片。适用于图生视频、动画小样和视频返工；支持本地图片的私有 R2 托管。不用于静态图片生成或原生 SVG / rig 动画制作。

通过哪都通 / Nxtpath 的 MiniMax H3 生成视频并恢复旧任务，支持首尾帧和参考图。用于明确指定哪都通、调用本 skill 或续查其历史任务；一般 MiniMax 新任务及官方 API 使用 minimax-video，Seedance 使用 nxtpath-video。

使用 MiniMax 官方 API 生成、续查和下载 H3 视频，支持文生视频、首尾帧及图片/视频/音频参考。用于 MiniMax 或海螺视频制作、官方 API 配置和已有官方任务恢复；明确指定哪都通或恢复其旧任务时使用 nxtpath-minimax-video。

Clean up voice audio in a video: rumble, electrical hum, background noise and hiss, muddy or harsh tone, sharp S sounds, uneven volume, and loudness for YouTube/Instagram/TikTok. Measures the audio first, picks the strongest cleanup that doesn't make the words less clear, and keeps lip sync exact. Use when the user says "clean up the audio", "fix the sound", "remove background noise", "remove hum", "my audio is too quiet/loud", "make it sound better", or after a rough cut.

Make a looping illustrated 3D video that plays with perception, the way Japanese illusion artists do (e.g. @garments__): a scene squashed flat by a telephoto lens morphs into deep perspective, things that looked side by side turn out to be at different depths, and objects quietly swap position while the view is flat. Also for recreating a reference illusion video, or a new scene (street, supermarket, station, room) in that style. Use when asked for a perspective/optical-illusion video, a "dolly zoom" or "flat to 3D" effect, or to recreate one of these clips.

将法律故事文案制作为“透明抽象卡通人物＋独立写实电影背景”的生图视频。用于角色资产制作、背景生图、图生视频、配音、字幕与剪辑；作为完整独立的视频制作项目运行。

Convierte historias en cómic animado: viñetas, tramas de semitono, globos/rótulos, paneos sobre ilustraciones y animación limitada. Úsala para 'motion comic', 'cómic animado', 'historieta animada', 'manga animado'.

SRTC (Screen Recording To Claude), a hotkey screen+voice recorder whose takes land in the open Claude chat as the prompt (narration = request, screenshots + pointer zooms = context). Use when the user mentions SRTC, Screen Recording To Claude, Video to Claude, vtc, the ⌃⌘S recorder, wants an existing screen recording (.mov/.mp4) digested into sheets + transcript, wants to change the hotkey/mic/cap/retention, clean recordings, or when the hotkey or audio stops working.

Use when a finished video or post needs a title, caption, description, tags, hashtags, cover text or pinned comment for YouTube, TikTok, Instagram, Facebook, X, Threads or LinkedIn, and the text must read like a person wrote it, not a brochure or an AI

Use when someone shares a reference video, ad, Reel, Short or TikTok (link or file) and wants their own video to follow its structure, pacing or visual style