Video & Animation

Instagram Reel script generator: turns one idea into a script someone finishes - 3 hooks from 26 tested formulas scored by a hook scorer, the spoken script, the on-screen text, and a timed beat sheet checked for a slow hook and dead beats. Use when the user wants a Reel script, a short-form video script, hooks, a voiceover, "write a reel about X", "what do I say in this video", "give me hooks", or is about to record without a first line. Pulls the user's best past hooks and outlier transcripts from the IShort MCP (search_my_scripts, list_my_scripts) when connected.

Turn an idea into a polished 2D explainer animation (1920x1080) - pick a ready-made visual theme or design a custom one, then build the animation with Motion Canvas (TypeScript). Use when the user asks for an animated explainer, diagram/flow/process/architecture animation, "make a video about X", or wants to add scenes to an existing TellMotion project.

Use this skill to design on-screen graphics for short-form vertical video (Reels, TikTok, Shorts) in the Kadr style (working name) — hooks, captions, lower thirds, callouts, stickers, stats, lists, quotes, transitions, end cards. Contains guidelines, colors, type, fonts, assets and timeline-driven React graphics components.

把 HTML/Canvas 动画逐帧渲染成 MP4（可配乐、可出 GIF、可出透明层）。当用户说「用代码做视频」「HTML 转视频」「导出 MP4/GIF」「做个动态图解/宣传片/数据动画」「逐帧渲染」时使用。自带渲染器与 11 个开箱即用模板（含多镜头讲解片、竖屏 9:16、前后对比、流程图、字幕卡）、图标/人物/运镜素材库，支持透明输出、外部字幕时间轴与 JSON 镜头表，装好依赖后一条命令出片。

Creates an Instagram carousel exactly like the instagram-carousel skill, but delivers an After Effects-style MP4 animation (letter-by-letter text, wipes, camera moves between slides, Ken Burns, varied sound effects and credit-free music from Openverse) instead of the PNGs. Use when the user types /carousel-mp4 or asks for the carousel 'as a video', 'animated', 'as an mp4', 'for reels' or 'like After Effects'.

Turn the user's script (.txt with [n] slide marks, [file] media and [description] tokens) and voice recording into a video of animated slides synced word-by-word to the narration, styled after the named game with its real icons/art.

Publish a WeChat Channels video draft with Ego Lite via ego-browser — login-check first (sessions expire fast), upload video, fill description/short title/topics/location/cover, save draft only. Soft-fails if Channels is logged out and tells the human to scan QR inside Ego. Personal use. Use when the user asks to post to 视频号 / Channels assistant.

Use when adding a startup cinematic to Hermes Desktop.

Make a narrated walkthrough or demo video of a web app. Playwright drives the real app, a local voice (Kokoro) reads the script, and FFmpeg adds captions, opening slides and a 1080p MP4 plus an .srt. Use this whenever the user wants a product demo video, a narrated screen recording, an explainer or onboarding video, a feature tour, or a case-study video of an app or CRM, even if they never mention Playwright, voice-over or captions. Also use it to re-record or edit a walkthrough made with this toolkit.

K-pop / 偶像风格音乐视频（MV）的专用制作 skill（参考库来自女团 MV，男团、solo 偶像的 MV 同样适用），一条龙覆盖：①整体策划（先定人物、把歌听透，再定概念、世界观、色彩服装、母题、歌曲段落映射、能量曲线、转场系统、AI 制作路线，并出节奏预览片先看方向）；②按拍分镜（剪辑镜头表、每刀制作级别 L1 代码剪辑 / L2 静图+代码 / L3 AI 视频 / L4 视频编辑、首帧图和跑法、生成单元提示词、静图清单、说唱和舞蹈按人列的清单）；③用自带脚本 mvfx.py 直接做闪切、AB 交替、频闪、白闪、甩镜、滚转、歌词字卡、节奏预览片、带镜头号的卡拍粗剪；④生成以后的小测、挑片、找入点、按镜头号逐刀返修；⑤MV 字幕（普通歌词字幕 + 3D 重点字）和成片交付（水印、超分、码率）。只在用户明确在做 MV 时使用：用户提到 MV、音乐视频、打歌 / 回归 / 出道 MV、MV 预告片、舞蹈版 MV、歌词卡点视频，或给出歌曲、歌词、BPM 要为这首歌做 MV 的策划、分镜、卡点剪辑、逐刀优化、字幕。MV 里的 AI 视频提示词先由本 skill 定拍什么、用哪种跑法。没有提到 MV 时不要使用：剧情短剧 / 影视分镜、Seedance 提示词写作与返修、人物或场景设定图、Midjourney 出图、MiniMax H3 提示词、已有视频的局部修改或换机位、灰模预演、玄上画布操作、展示页上线部署，以及没提 MV 的普通视频卡点剪辑，都交给各自的专用 skill 或插件。默认 16:9；不改用户的歌词、歌曲结构和人设；用户明说才提交生成；不操控用户的屏幕。

小Lin说（Xiao Lin Shuo）风格的财经、科普讲解视频包装。包含 Remotion 版式组件库（巨型数字、卡片墙、白卡图表、整页文档荧光笔、实体卡、大公式条、白底计算器、片名和章节卡、画中画、转场）、资料检索规范（每种版式要查的数据和原文、来源分级、事实文件模板、Wikimedia Commons 自由许可照片下载脚本）、按台词关键词计时的分镜 API、分块渲染、人声加音乐加合成音效的混音，以及逐帧质检。适用场景：把出镜口播片段包装成小Lin说式的讲解画面；复刻或改进"一口气了解……"类视频的图形语言；给已有口播视频重做讲解包装。

Burn styled, well-placed subtitles into a screen-recorded product demo or UI walkthrough, and produce the caption copy that goes with it. This skill should be used when someone asks to "add subtitles", "caption this demo", or "make this recording readable for a non-English audience (Chinese, Japanese, Korean, any other)", or when a demo video's on-screen text is too small or English-only for the target audience. Handles the full loop: frame-by-frame video analysis, verbatim extraction of on-screen UI text, caption copy drafting with a reading-speed budget, a white-on-purple outlined caption look (white fill, thick coloured outline, soft halo), focus-following placement that never covers the live demo panel, ffmpeg/libass burn-in, and frame-level verification. Also covers the traps that silently break this workflow: -ss placed before -i kills the ass filter, downscaled preview frames give wrong crop coordinates, single-layer ASS cannot render a glow, and captions that straddle scene transitions.

Make a short procedural animation in any style — an explainer, a history, a little story — as a single-file canvas video with a synthesized score, rendered to MP4. Ships with styles (cut paper, crosshatch ink, riso print, sketchbook, manim-style math, pixel art, isometric line art) and makes new ones from the user's references. Walks the user through intake, then three check-ins (story, look, storyboard) before animating, and proves the result with measured review checks. Use when the user asks for an animated video, short, explainer or reel made in code, or wants a look matched from references.

用代码做视频的唯一入口：一句需求 → 成片 MP4 + 可编辑源码。内置五个引擎（onetake / video-shotcraft / claude-motion / mg-motion / wise-motion）与 880 条可检索素材（124 张 Remotion 镜头配方卡、462 条通用动效条目、47 套动画源码案例、20 个源码组件、30 个物件模型、14 个场景起点、15 种 MG 风格签名技法、35 个纯时间动效函数、6 套起始 look），共用一套节奏语法、声音规范与三道质检闸。Use when 用户要做动效 / MG / motion design / 产品宣传片 / 发布片 / teaser / 功能演示 / 网页或截图变视频 / 转场与文字动效 / 复刻某个动效 / 用 Remotion 或逐帧渲染做片，或抱怨成片「像 PPT、没节奏、一个一个展示」。NOT for 实拍剪辑与长视频、只想要内容摘要、只出图不出片、品牌 logo 设计。

Cria vídeos explicativos de quadro branco desenhado à mão (traço de Excalidraw) que se desenham junto com a narração, com uma câmera passeando por um quadro único e um afastamento final que mostra o mapa inteiro. Roteiro, voz por OpenRouter ou ElevenLabs, sincronia palavra por palavra e render em MP4 16:9 com Remotion. Use sempre que pedirem um vídeo explicativo, whiteboard, quadro desenhado, explainer ou um vídeo que explique um sistema, produto, processo, livro ou ideia, mesmo sem citar a skill.

Generate production-ready 2D TSX video files for VidTSX (Remotion-based) from a shot, scene, or video description. Use whenever the user wants to create or generate a VidTSX video, a 2D TSX shot or scene, an animated clip, title card, or rendered motion graphic — including when they describe a visual animation they want built, or say "make a shot", "build this scene", "generate the TSX", or "turn this into a video". Covers the mandatory file structure and composition config, dimension presets (horizontal/vertical/square), six style presets (minimalist, memphis, neo-brutalism, glassmorphism, neon, corporate), and the hard rules that keep renders from crashing, covering frame-based animation only (no useState/useEffect/setTimeout), strictly monotonic interpolate ranges, Easing.bezier not wrapper syntax, and the chroma-js and @remotion/paths import gotchas. Not for 3D/three.js compositions, general React work, or editing video files.

Talking Explainer - turn a topic into a narrated 16:9 (1920x1080, 60fps) motion-design explainer where a TALKING cartoon presenter (real lip sync - six mouth shapes driven by the voice, poses on cue words, blinks) explains it in the user's own voice, with short basic-English kinetic text on screen, in a sleek APPLE product-page look (white light, Geist type, glass cards, critically damped springs, Solar icons, a lens spine), a camera push-in and an emphasis beat on every scene, and the user's own brand (logo open, corner logo, end card with their call to action). Hook-first script in the user's speaking style -> they record the take -> storyboard -> parallel scene workers -> render with word-sync and zone proof. MUST USE when the user says "talking explainer", "talking mascot", "make the mascot talk", "lip sync explainer", "explainer with a talking character", or asks for an explainer video where the presenter speaks. Also covers: making the user's OWN talking character from 3 image prompts, swapping a…

Write HTML/CSS and render deterministic MP4 with HeyGen's HyperFrames; ~450 ready blocks (transitions, kinetic type, captions, charts, maps, 3D), a /figma sub-skill that pulls brand tokens and frames into video, reverse-any-video, slideshow/present mode, and Remotion-to-HyperFrames porting. Use for launch films, explainers, social clips, title cards, or when the user wants video from HTML rather than React.

Use when the user wants to edit, cut, assemble, fix or elevate ANY video — reels, TikToks, ads, commercials, talking heads, interviews, documentaries, product videos, YouTube, podcasts — or asks about pacing, hooks, retention, transitions, kinetic text, captions, subtitles, motion graphics, color correction, color grading, LUTs, audio cleanup, noise removal, voice enhancement, music, ducking, sound design, b-roll, storyboarding a video edit, ffmpeg commands, CapCut projects, AI video/image/music generation for content, or export settings for social platforms. Also use when the user drops raw footage in a folder and wants it turned into something publishable, when they say a video "feels slow / boring / amateur / doesn't flow", or when they need to find the good take among many bad ones. Triggers include "edita este video", "monta esto", "haz un reel", "que se vea profesional", "comercial de TV", "subtítulos", "corregir color", "quitar ruido de la voz", "transiciones", "b-roll", "ffmpeg", "CapCut", "no me…

Thêm phủ hình, b-roll đồ hoạ theo lời cho video người nói, thu nhỏ khung mặt, số đếm, danh sách, so sánh, các bước, biểu đồ cột và phụ đề karaoke Remotion.

Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage. Measure and watch it, rebuild every layer, then check the render against the original frame by frame. Use to reverse, recreate, replicate or copy a video.

Make a YouTube video end to end with the videokit toolkit (Remotion, code-drawn animation, Gemini voice). Asks the brief first (long 16:9 or Short 9:16, narration voice, look, how the characters and every other asset are made - drawn in code, emoji or Gemini-generated - and music), writes a full draft of the story and every scene's transitions, animation, lighting, sound effects and quality for approval BEFORE building anything, then records the voice, builds the timeline, music and mix, animates with the pro-look effects library, checks it automatically and with a reviewer agent that scores the draft, an animatic and the final cut against a fixed checklist, and renders 1080p (plus a TikTok cut) with the upload sheet. Use this whenever the user wants a new video, explainer, Short, animation, MV or lyric video made, or wants to turn an idea or a script into a video, even if they only say make a video about X, can you animate this, or do a short on Y. Not for advice questions about YouTube or ideas only -…

Make a ~55-70 s vertical cartoon story short in the "2D characters in a colourful 3D world" style (flat bean-head cartoon cards with ink outlines, painted 3D town/world with black ink lines, saturated sky, depth-of-field backgrounds, gliding cameras, voice narration, synthesized SFX + march-style music), rendered with three.js inside Remotion. Proven on "The Bridge That Fell for a Song" (2026-10-31). Use when the user asks for another video "like the bridge video", "like the soldiers/bridge short", "in that cartoon 3D style", a history/science story short with cartoon characters in 3D, or says "use the cartoon short skill".

复刻"科普观察室"式 AI 科普视频全流程：选题→查资料→出处核对→数据模型→写讲稿→多 CLI 盲审→回原文定谳→配音字幕→画面(Remotion)→机器检查→人审片→发布包→评论回流。当用户要做一期科普视频、开新科普选题、提到盲审/定谳/审片/出片/发布包，或在科普系列项目目录里问"这一期到哪了/继续/下一步"时使用。单点任务（只要去AI味、只要配音、只要字幕、只要改 Remotion 动画）不要加载本技能，直接做该单步。