Video & Animation

Make 9:16 doodle music reels. A drawing grows stroke by stroke on a grid while a playhead sweeps across it and plays the drawing as music, so the song builds as the picture does. Claude draws it and synthesizes the sound in code, then renders an mp4 on the user's own computer for free. Use when asked for a doodle music reel, a drawing that plays music, a draw-to-music video, "make the drawing sing", or a satisfying reel where a line makes notes. Also for turning a logo, a state or a country outline into a song.

Torn-paper COLLAGE motion film, 5–30 s (YouTube intro or channel trailer, brand or shop promo, 16:9), stop-motion on twos, built in code; AI only for photo cut-outs. Use for collage / scrapbook / cut-out / magazine-cutout / ripped-paper / mixed-media / zine-style videos, or when someone sends a paper-collage reference and says "make it like this ref" (RU: коллаж, рваная бумага, вырезки, аппликация, журнальные вырезки, заставка, интро, «сделай как на рефе», «как San Diego Zoo»). Not for static photo collages, moodboards, split-screen clip grids or a single transition. San Diego Zoo "Africa Rocks" technique: layered torn paper with white fibrous edges, halftone, watercolour sky, photo cut-o...

Pain-first "walkthrough" motion video for a B2B offer — one continuous shot where a single real-looking object (a PO, invoice, lead, form) travels from the prospect's pain (manual retyping, hours, $ per year) into the fix, with a voiceover, iOS UI sounds, real tool logos, a soft reply CTA and the brand logo fading out alone. Use when someone asks for a demo / walkthrough / outreach video, "like the PO Desk video", "go into the pain and show what it costs", "make it a continuum", or a cold-outreach video opening "hey, this is random, but I peeped something in your business". Built from code (pure seek(t) HTML engine), ElevenLabs voice, cue-sheet SFX mix, 60 fps motion blur, 9:16 + 16:9. Sc...

This skill should be used when the user asks to "add music to the animation", "make the music in code", "synthesize a soundtrack", "compose background music that fits the cuts", "sync the music to the video", "check if the audio lines up with the picture", or "the music is too sudden / startling". Covers a code-synthesized score that lives inside the animation page (Web Audio API, rendered offline to WAV), AI-generated or user-supplied music, and an automatic check that cuts land on the beat without a startling jump in loudness.

Turn a ~5-second voiceover line, opinion sentence, or abstract concept into a premium editorial halftone paper-collage B-roll clip — optionally with a fitted voiceover. Load this skill whenever the user says "collage b-roll", "paper collage b-roll", "halftone collage", "collage-style visuals", "collage explainer" (or the Chinese triggers 纸拼贴 b-roll / 半调拼贴 / 拼贴风格配画面), or wants a script line turned into a collage visual metaphor. Enforces a mandatory three-gate approval flow — propose visual metaphors only, generate color collage stills only after the user confirms, and only after the stills are confirmed generate the assemble-from-empty animation. Video model is gemini-omni-flash, locked —...

This skill should be used when the user asks to "draw every frame in JavaScript", "make an animation with no image assets", "animate this in code / on a canvas", "make a hand-drawn style animated video", "turn this into a short animated film", "make an animated explainer drawn in code", "make an animated story / picture book of my photos", or "make a zero-asset animation like the Opus 5.5 ones". Produces a single self-contained HTML file whose frames are computed on an HTML canvas (seekable, deterministic), renders it to MP4, and self-checks the result. Pairs with the soundtrack skill for code-synthesized music. NOT for charts from data (use chart-animation) or 3D/WebGL (use threejs-anima...

Turn a dataset (a link, CSV, Excel, JSON, or PDF table) into a narrated, animated data-visualization lesson with a Video tab (voice narration synced word-by-word to the chart, captions, chapters, music) and an Explore tab (interactive simulation). Checks whether the data fits, picks the best of four animated chart types (dot timeline, line reveal, moving scatter, unit/waffle), writes and fact-checks the script, and self-checks every step. Use when someone wants a data story, narrated data lesson, animated data explainer, or "make a lesson/visualization from this data", including non-technical users.

Make kinetic-typography motion reels (MP4) in code: showreels, portfolio or work reels, product promos, intro films, "motion design"-style videos with bold condensed type, HUD micro-type, black/cream/lime palette, three.js generative layers (particle terrain, liquid marble, chrome knot, particle clouds), shape-continuity transitions and a synthesized, beat-locked score. Canvas 2D + WebGL rendered frame by frame in headless Chrome, encoded with ffmpeg. Use when the user asks for a reel, showreel, motion-graphics / kinetic-type video, a "Work Reel" in this style, or to extend/re-cut the Work Reel ’26.

Record a polished product-demo video (mp4 + subtitles + chapters) of a web app from a JSON scenario, using a scripted headless Chrome with captions, title cards and a visible cursor. Use when the user asks for a demo video, product walkthrough, screen recording, or "record the UI changes" for a web app they can run locally or on staging.

Record polished, scripted demo videos of a web app (product walkthroughs, before → after architecture animations, feature segments) as 1440×900 MP4s in a consistent house format — white title cards, pill captions, click ripples, fast-forwarded waits — by driving headless Chrome with Playwright and encoding with ffmpeg. Use this whenever the user wants a demo video, screencast, walkthrough recording, product video, "record the app", "make a video of this feature", "extend/add to the demo video", an animated architecture diagram, or wants to show a feature to stakeholders as a video, even if they don't say "skill" or name a format.

Record clean, fast-paced demo clips of a mobile app running on an Android emulator or iOS simulator, for ads, store previews, social posts, or AI video tools that take a screen recording as input. Use when the user asks to record, film, or capture the app ("앱 녹화", "앱 영상 찍어줘", "demo video of the app"). Handles the build choice, device performance, a clean status bar, host-side recording, cutting dead time between taps, and checking each clip. Not for automated test runs or for editing finished videos.

把一个知识点（数学为主，其他学科也行）做成"口诀 + 图形演示"的讲解短视频，风格类似抖音「Rap&科学」：暗色电影感背景、顶部常驻口诀、中间蓝色图形逐步演示、白字公式加黄色结果、底部逐句字幕，画面跟着唱词或配音卡点。音频由用户或客户自带（任何 AI 音乐平台生成的歌、真人说唱、普通配音都行），背景从自带素材库里按用途自动挑，画面由脚本逐帧绘制后用 ffmpeg 合成，可另出竖屏版。用户说"做一个数学说唱视频""把这个知识点做成口诀视频""复刻 Rap&科学 那种视频""教学说唱 MV""给这段配音/这首歌做讲解画面""口诀讲解视频"，或想把某个公式、定理、解题方法做成好记的歌加动画时，都应使用本 skill，即使没有明确说"说唱"。只想了解做法、选音乐工具、或教别人做时，也用本 skill 里的说明回答。

Turn a CSV, or a short description plus real data, into an accurate data-animation short video — bar chart race, line race, big-number counter, or share/waffle shift — exported as MP4 + GIF + cover PNG in 9:16, 16:9, 1:1, 4:5 or 3:4 for Douyin/TikTok, Xiaohongshu, YouTube Shorts, Reels, Bilibili or X. Use when the user asks for an animated chart, a bar chart race, a "data video", 动态排行榜, 数据可视化视频, or wants numbers turned into a short clip. Every on-screen number comes from the source data.

Make an animated cartoon in which every frame is drawn by code (SVG, Canvas 2D, DOM/CSS, WebGL shaders, three.js) and rendered to MP4 in headless Chrome, with character voices, sound effects and ambience from ElevenLabs. Covers one story told in many visual styles (picture book, comic, pixel art, liquid chrome, low-poly, flow field, ASCII, Bauhaus, rubber hose, path-traced photo, raymarched landscape, anime cel, child's crayon drawing), the scene contract that lets several agents build scenes in parallel, voice and sound practice, and how to check a film you cannot watch. Use when the user asks for a cartoon, animated short, animated story, multi-style animation, "animation made only with...

Turn a talking-head recording into a finished vertical 9:16 Instagram Reel / TikTok / YouTube Short in a bold editorial style - tightened pauses, kinetic Anton + Didot typography, a red / white / black-and-white palette, B-roll inserts that illustrate exactly what is being said, split screens with the speaker, camera-move transitions, film grain, voice mastered to -14 LUFS. Everything is rendered by code (Python + ffmpeg/libass) - no After Effects or other editing app needed; footage is sourced free of charge (own material, free-licensed stock and archives via the Pixabay / thesvg MCP connectors and Wikimedia Commons - paid AI generation only on explicit request). Use this skill whenever...

文稿/SRT 驱动、代码生成视觉的讲解汇报视频流水线。Use when 用户要把口播稿/汇报内容做成带字幕条的视频（汇报视频、讲解视频、口播视频、发布会风格视频、文稿驱动视频、SRT 驱动动画），覆盖五阶段：大纲 → 文稿+SRT → 分镜 storyboard → HTML/JS 逐镜确定性渲染（Playwright+FFmpeg）→ 拼接交付 final.mp4。内含可选音效模块（Freesound CC0 下载、adelay+amix 混音或剪映对点清单，默认关闭）与跨会话 WORKLOG 接力机制。

Turns ANY voiceover (and an optional script) into a finished 16:9 documentary-style reel in After Effects in one request: cuts pauses and breaths, writes the visual story, sources every picture for free (Wikimedia Commons archival photos, Pixabay MCP clips and portraits, logo SVGs via the thesvg MCP, ffmpeg Ken-Burns moves - no credits, no paid generation), builds the edit natively in After Effects, renders a 1080p H.264 MP4. Look: dark archival documentary, clips in floating rounded glass frames with a glowing border, a moving perspective grid with keywords flipping colour, big captions, typewriter / giant-word / photo-card pages, flashes, synthesised SFX. Use whenever someone gives a vo...

Google Flow (Veo) 商业广告与宣传片导演工作台 Skill。专注于「城市文旅宣传片」、「品牌情绪 TVC」与「产品高光展示」三大方向。当用户输入视频主题、总时长或上传产品参考图时，自动构建全局视觉与声音圣经（Visual & Audio Bible）、智能切分 15s 多段分镜时间轴、规划无缝转场桥接（Match Cut / 甩镜遮罩 / 光斑呼吸 / 首尾帧接力），生成直接内嵌【纯净电影画面 + 原生中文配音 + 动作音效 + BGM】的一体化 Google Flow 提示词（严禁生成字幕以防字符错乱，字幕留待后期剪辑添加），并自动导出本地 Markdown 执行单、交互式 HTML 故事板且同步至 Google Drive。

Create a full narrated movie recap and a short Instagram Reel from a user-supplied local film or episode, including subtitles, thumbnails, and upload copy. Use when asked to run movie-recap or produce these recap packages from local footage.

Turn a silent screen recording (product demo, tutorial, walkthrough, bug repro) into a narrated video in one command. Finds the steps in the recording, helps write one line per step, voices each line with a saved or cloned voice, starts every line exactly at its step, speeds up or freezes frames automatically when a line runs long ("freeze-sync"), mixes optional ducked music, normalizes loudness and writes SRT/VTT captions (optionally burned in). Use when the user wants to add AI voiceover or na

Make a finished vertical short video (YouTube Shorts, TikTok, Instagram Reels; 1080x1920 MP4) from a plain-text script in one command, with AI voiceover in a saved or cloned voice, word-timed pop captions taken from the real speech, Ken Burns motion on images, cropped and looped B-roll clips or animated gradient backgrounds, auto-ducked background music and -14 LUFS loudness. Use when the user asks to turn a script, tips list, story or blog post into a Short/Reel/TikTok, make a faceless short wi

Animation and motion in web interfaces — when to animate and when not to, durations, curves, springs, micro-interactions (hover, press, toggles), elements entering and leaving, page transitions, scroll animation, number changes, and choosing a tool (CSS, View Transitions, Motion, GSAP). Use whenever something in the task should move, change smoothly or "come alive" — "add an animation", "make it smooth", "make this block feel alive", "hover effect", "reveal on scroll", "transition", "motion", "t

制作黑底科学档案风的生物生长动画，包含原创阶段素材、连续形变、解剖标注与 MP4 导出。适用于“换一种生物做类似海马生长动画”、标本演化动效或生长序列；明显变态发育须按形态连续的阶段分段设计。

Make an ElevenLabs voiceover sound like a person instead of a robot - rewrite the script for the ear, direct it with audio tags, set stability and speed, generate seeded takes and pick the one that flows. Use when a TTS or AI voiceover sounds robotic, choppy, flat, "too AI" or has no emotion, pauses in the wrong places, when writing a voiceover script for ElevenLabs, or before paying for a long generation.