Video & Animation

Design and animate 2D scenes in Quar Animator through its MCP server (the quar-animator tools — list_projects, get_scene_context, apply_edit_batch, render_frame, render_preview, export…). Use when the user wants something designed, drawn, animated, rigged or exported in Quar Animator — a logo animation, a title card, a looping banner, kinetic typography, a character walk cycle, a UI micro-interaction for Lottie, slides — or wants an existing Quar project improved.

Turn a talking-head clip, a voice recording or plain text into a vertical (9:16) or wide (16:9) video with motion design timed to what is said - word-timed captions (Hebrew/RTL and English), keyword cards, A/B reveals, icons, end card, brand theme, optional copyright-free music. Runs fully locally (Whisper/ivrit.ai + Remotion + ffmpeg) with two human approval gates. Use when asked to edit, caption, add motion graphics or "After Effects" to a short social video, voice note or text.

Learning objective in, accessible explainer video out. Turns a measurable learning objective into a short, code-drawn explainer video with narration, word-aligned subtitles, transcript, audio-description notes, sourced-claim traceability, and QC against written Mayer multimedia-principle criteria. Four human approval gates. No generative video models, no stock footage. Use when an e-learning developer, instructional designer, or educator wants a teaching video that starts from an objective rather than a topic.

RAW KINETIQ. Turns a song file into a finished kinetic-typography lyric video (MP4) where every word hits on time and the whole look (colours, fonts, motion, backgrounds) is designed from what that song is about and how it feels - lyrics timed with Whisper plus a Demucs vocal stem, visuals synced to the beat, the user's own images and cutouts placed in it, a self-check before rendering, rendered with Remotion. Use this whenever the user wants a lyric video, kinetic lyrics, a "music video" or visualizer for their own song, animated lyrics for YouTube, or a vertical TikTok/Reels/Shorts lyric clip, even when they say it casually ("make a vid for my track", "do the kinetic thing for this song", "raw kinetiq this"). Works from just an audio file; lyrics can be pasted, read from the file's tags (Suno embeds them) or transcribed. Not for AI-generated footage music videos unless they want lyrics on top.

Make high-quality motion-graphics videos (launch films, explainers, social reels, game trailers, loops, stings) with Remotion. Use it when asked to create, animate, storyboard, or render a motion video, kinetic type, a product promo, or an animated social post, or to pick a visual style for one. It includes 15 house styles (NxrStyle 01–15), 70 ID'd techniques with exact timings, universal motion laws, and a QA process (ffprobe, −14 LUFS, contact sheets, determinism). By NxrLabs.

Make a finished promo, launch, recap or behind-the-scenes video in one go: ask every question once up front (scenes, references, formats and aspect ratios, length and platform caps, source repos and sites, languages, music, voice and captions, brand), then storyboard, build, score, render every format and QA each file with no further questions. Original synthesised score with stems and sound effects keyed to the animation, facts pulled from git, one source re-laid out per aspect ratio, and a QA pass on loudness, black/frozen/silent frames, end-card hold, text size on a phone and platform safe zones. Use when someone wants a complete multi-format video delivered end to end rather than a co-creation session. Built on HyperFrames.

Make a polished product demo video (LinkedIn, X, a launch page, a store listing) by recording the real product in a browser, then framing, captioning and rendering it — end to end, with no video editor. Use when someone wants a demo, promo, launch or feature video, a screen recording made presentable, or "a video showing what my extension / web app does". macOS for recording.

Directs and produces high-end motion graphics videos for products and startups (launch promos, explainers, landing-page and app-store videos, reels, 6–15 s ad cuts) with storytelling built on the shape of the music, measured kinetic typography, physical transitions, procedural 3D characters that act out the user's process, the real product UI animated in DOM, 9:16 and 4:5 verticals, language versions and voice-over, in Remotion + three.js. Use it WHENEVER someone asks for an animated video, motion graphics, a promo, an explainer, a product or launch video, an animation with characters, animated titles, a reel or ad cuts, even if they don't say "motion graphics", and also to review, improve or make variants of an existing one. Also triggers on Spanish requests ("video animado", "promo", "video de lanzamiento", "explainer", "títulos animados", "reel", "cortes para anuncios"). Every project gets its own visual line; the skill gives the method and the parameters, not a fixed look.

Create studio-grade, deterministic motion graphics and programmatic videos in Remotion, HTML/CSS/GSAP, or HTML5 Canvas without AI slop. Features multi-engine routing, 10-stage production pipeline, anti-slop visual rules, and category playbooks for Reels, Launches, Brand Manifestos, Kinetic Typography, and Explainers.

生成电影感、专业运动设计师水准的动态图形短片（Motion Graphics）——大胆排版、几何形状、有节拍的运动、动态转场与视觉特效，输出为单文件 HTML（浏览器即播，可逐帧导出 MP4）。当用户想要电影感或大片感的动画、动态图形、动效短片、片头片尾、开场动画、title sequence、kinetic typography（动态文字、文字动画）、品牌或产品宣传动画、logo 演绎、发布会或活动开场、倒计时、预告片式文字动画、竖版动态海报（抖音、视频号、Reels），或说“让这段文案动起来”“做得像专业动效设计师做的”“motion graphics / promo animation / cinematic intro / logo reveal”时，务必使用本 skill，即使用户没有明确说“动态图形”。不适用于：网页 UI 交互动效（hover、滚动动画）、静态海报、数据图表、剪辑真实视频素材、3D 建模。

Make a motion-design video with the user from brief to finished MP4: a brand film, product or company video, talk teaser, launch, explainer, lesson or idea turned into motion graphics. Runs in one live review page: a setup form (brief, website, content and files, length, landscape/portrait, how many directions, styles, music, sound effects, voiceover and voice, captions, and the language/script of the words, e.g. English, Urdu script, Roman Urdu or mixed), low-detail draft videos to compare side by side, an editable transcript beside each player, a polished final to iterate on, composed music and effects, a voiceover with word-by-word captions (designed or from a 150+ style gallery), and a Render MP4 button. Use this whenever someone wants a motion graphics, animated, explainer, promo or brand video, storyboards to pick from, or "a video about" a website, company, product, talk or idea, even if they never say "motion design".

Production Python and Node.js scripts to download 1080p watermark-free TikTok videos (hdplay), search videos by keyword/region, paginate 200 followers per request, and query the TikTok Creative Center Commercial Ads Library via TikTokAPI.io.

Real-time TikTok Data, 1080p No-Watermark Video, Creator Profiles, Comments & Creative Center Ads via TikTokAPI.io REST API and MCP Server.

Upload local PR screenshots and recordings to GitHub with GitHub CLI `--attach`. Use whenever visual-proof produces review evidence or a local image/video must appear in a pull request body or comment.

Teach the user something with a short interactive HTML lesson (driveable figures, auto-playing code traces, request-flow diagrams, predict-first questions, flashcards) plus notes. Use when the user says teach me, help me learn or understand, explain visually or step by step, make a lesson, quiz me, or hands over a tweet thread, URL, article, PDF, book chapter, code snippet, video or course lesson to learn from. Not for ordinary questions that just need a direct answer.

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

Direct and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解), and new films cut from real archive footage and documents (剪辑与纪实, e.g. 用档案影像剪一支新闻片); when they want a film about their own topic and haven't chosen a style (help them choose); when they want to change a style into their own, make their own style from a blank page, or use a style they saved (改风格、从空白开始、我的风格); when they start the skill without saying what they want; or when they ask which film styles there are. Not for plain editing, trimming or converting the user's existing video files.

Set up ReelStyles on this computer for the user's AI agent. Checks and installs Node.js 22+, ffmpeg, git and Chrome for HyperFrames, wires the ReelStyles skill into the agents the user has (Claude Code, Codex, Cursor, Roo Code, Cline, Gemini CLI, GitHub Copilot, Windsurf), then renders a 5 s test film. Use when the user says "set up ReelStyles", "install ReelStyles", or before the first ReelStyles video if setup has not passed.

Turn a video URL or video file into context an agent can read, as one bundle folder with the post text, captions or a whisper transcript, and deduplicated frames. Use when the user shares a video link (x.com, YouTube, any site yt-dlp supports) or a video file and asks what it shows, to summarise or explain it, or to learn from it. Filing what was learned as a study note is the learn skill.

Make a 9:16 comedy-sketch reel (30-45 s, English) with two 3D characters - the Nerd (spiky hair, glasses, hoodie) and Claude, the small orange low-poly robot on his desk - rendered in Blender from one storyboard.json. The Nerd has a real dev/AI pain, Claude answers deadpan and slips in one verified tip, then a twist and a loop back to frame 1. Runs research with sources, script, free `say` draft, layout stills, ElevenLabs takes, whisper check, final EEVEE render, cover and QA. Use for "make a Nerd + Claude sketch", "duo reel", "new episode", "sketch reel about X", "video con l'omino arancione".

Start or continue a multi-session learning workspace in the current folder - a mission, vetted resources, learning records, numbered interactive lessons, reference sheets, a glossary, flashcard review, and a queue for working through a course (Udemy, YouTube playlist) or a book chapter by chapter.

Review a finished Pipeline piece (a short vertical video with its caption and cover) before it goes to a human for approval. Reads the /ig skill script results, applies four critic lenses against the campaign's own brief and voice, and returns a SHIP or FIX verdict as JSON. Use whenever a piece built by Pipeline needs a fresh-eyes review, or when asked to "review", "QA" or "check" a Pipeline piece.

Cut AI tells from interface and chart copy: eyebrow labels, 01/02/03 numbering, redundant subtitles, captions that explain what is already visible, leaked design notes, decorative badges, status dots, chart clutter and legends a direct label could replace. Applies /pstack:unslop to every string it keeps.

Makes narrated lesson films for YouTube that teach one technical mechanism in about one to two minutes, with every frame drawn by code and a computed score, for STEM viewers with short attention spans. Builds on the code-film skill for the look, the taste and the defect checks, and adds a spoken voice that sets the clock (Kokoro, word timestamps), a script written as one conversation, a pause to guess, a recap and an ending that fades, a scene system in 16:9 with parallel capture, -14 LUFS mastering, exact captions, and checks that the voice said every word and the picture moves on each word it is tied to. Use when the user wants an explainer or lesson video, a YouTube video that teaches something, a narrated version of a code-film, or a Short cut from one. Not for a film with no voice, such as a music video, an ad or a visual poem, which belongs to code-film, or an animated diagram inside a page or doc.