Video & Animation

Edit a raw talking-head clip into a finished Instagram reel in Kallaway's editing style (black dotted stage with one live diagram per idea, rounded face card with the head popping out over its edge, one-word white captions, red as the only accent, hard cuts on word onsets, a real sound effect on every animation, optional quiet ducked background music). Free local tools only (ffmpeg, Whisper, HyperFrames). Use when someone says "/kallaway-edit", "edit this like Kallaway", "make this reel in the Kallaway style", or drops raw clips and asks for a Kallaway-style edit.

Edit raw talking-head clips into a finished vertical Instagram reel in the creator's OWN style, read from a style folder made by build-my-style (STYLE.md, locked shine/zoom/shadow, picked sound effects). Picks the last clean take of every line, shows a storyboard page first (a still per beat, A/B/C options on the key beats, Approve/Change and notes), optionally renders short variations of key moments to pick from, then builds the full edit in HyperFrames, reviews its own render, and turns every note the user gives into a dated rule in their STYLE.md so the next edit is better. Free local tools only. Use whenever someone says "/edit-my-video", "edit my video", "edit these clips", "make this into a reel in my style", "storyboard this edit", drops a folder of raw clips and wants an edit, or gives notes on an edit this skill made ("I don't like the zoom", "make the logos bigger").

Turn a plain-language description into a studio-grade motion video made in code with Remotion, React and three.js (3D camera moves, kinetic typography, glass UI, light), with music and sound effects from audio files the user owns, rendered to MP4 in 9:16 and/or 16:9. Use when the user asks for a motion design video, an animated ad, a product launch film, an intro, a promo, an explainer or "a video like this", or wants to change, fix or re-render a video made with this skill.

Style Studio. Walks a creator (usually non-technical) through building their OWN video editing style on an interactive page in their browser - their colours and font, reference reels they love broken down frame by frame, then rounds of real animated options (captions, accent and intro text, zooms, diagrams, logos, split screen, tool talk, sound effects) they mark Keep / Maybe / Drop, plus Shine, Zoom and Shadow labs with Lock buttons. Ends with a STYLE.md guide and locked settings that /edit-my-video uses. Use whenever someone says "/build-my-style", "build my style", "make my editing style", "style studio", "I want my own edit style", "copy the editing style of these reels", "make my brand style for videos", sends reels they want their edits to look like, or comes back to carry on their style (rounds, labs, sounds). Also the STYLE keyword giveaway.

Make motion graphics on real footage with Remotion, driven by measurements from ffmpeg-skill: animated captions timed from an SRT/VTT file, automatic jump cuts that drop the silences ffmpeg-skill measured (with punch-in zooms and captions re-timed), and motion that hits on measured audio peaks and scene cuts. Every composition takes its length, fps and frame size from the probed source; every render is verified (frame count, fps, size, audio) and inspected with a contact sheet, then delivered through ffmpeg-skill templates (YouTube, Reels, TikTok, Shorts, X) and its compliance check. Use this skill when the user wants Remotion, React video, motion graphics, animated captions or titles over a video, jump cuts / silence removal with motion, audio-reactive or beat-synced graphics, or a programmatic video built from a real recording -- even when they do not say "Remotion". Needs Node.js and ffmpeg-skill; local, no API keys.

>- Build and render deterministic 60fps 1080p MP4 animated videos, motion graphics, release recaps, product demos, and data-driven "Wrapped" videos using HTML5 Canvas, SVG, Playwright frame-stepping (window.__setFrame), multimodal contact-sheet visual self-review, procedural Python/NumPy audio synthesis, WAV SFX cue mixing, and FFmpeg. Use whenever the user asks to "make an animated video", "generate an MP4 video from code", "build a release recap / Wrapped video", "render HTML/Canvas/SVG to MP4", "create a programmatic video without Remotion boilerplate", "make a demo or farewell video with sound effects", or "animate metrics/charts into a 60fps video".

Pipeline completo para vídeos 3D com PiP (talking-head) usando Remotion + Three.js + Whisper + Freesound. Cria backgrounds dinâmicos temáticos, kinetic typography, HUDs contextuais, e mixagem profissional (-14 LUFS). Use quando o usuário pedir "vídeo 3D", "vídeo com PiP", "vídeo estilo TikTok cinematográfico", ou "vídeo do meu roteiro".

Regras de UI/UX para telas recriadas dentro de vídeos (app, site, dashboard, chat, notificação) e para páginas simples, para o resultado parecer produto de verdade e não tela feita por IA. Usar ao desenhar, recriar, auditar ou polir qualquer interface que vai aparecer num vídeo ou numa página, inclusive quando for preciso buscar referência visual (Mobbin se disponível; senão Pinterest ou Dribbble).

Regras para montar motion graphics sobre uma narração (Reels explicativos, tutoriais e anúncios narrados com telas de interface) — a cena se constrói conforme a fala, sem spoiler; legenda com tempo de leitura e sem marca-texto; um elemento real ou metáfora visual para cada ideia dita; destaques variados; troca de cena só depois da fala e na batida da trilha. Usar em todo vídeo narrado com motion, em After Effects, EffectCraft, HyperFrames ou Remotion, antes de escrever as cenas e de novo antes de renderizar.

Sound design e mixagem de vídeo no estúdio. Usar sempre que for dar som a um vídeo ou animação (efeito para cada elemento que entra ou sai, música, narração, mix final, som colado na prévia), montar ou ampliar a biblioteca de efeitos (sintetizar ou nivelar um pack), medir as batidas e o drop de uma música para cortar no tempo, separar a voz da música em stems ou conferir se o som de cena está alto demais antes de entregar. Vale para vídeo feito no After Effects, HyperFrames, Remotion ou editado à mão.

Ponto de entrada de qualquer pedido de vídeo neste estúdio (Reel, anúncio, tutorial narrado, vídeo de produto, motion, edição de bruto, legenda). Usar no começo de todo vídeo para abrir o método, escolher o motor (After Effects, EffectCraft, HyperFrames ou Remotion) e a skill de receita certa, sempre com referências antes de animar.

Turn topics, requirements, articles or scripts into stickman videos. Director mode creates approved storyboards and standalone video prompts; Autopilot mode produces narrated, captioned illustration-and-micro-animation videos through configured generation tools and a local renderer. Also guide installation handoff, first use and setup of this specific Skill.

Edit real footage by conversation, fully local. Transcribe with whisper.cpp, pick takes from the transcript, write a JSON edit list, validate it, render with ffmpeg, add animated Hyperframes captions and overlays, reframe to 9:16 / 1:1 / 16:9, then self-check the render. Use for talking heads, UGC and testimonial ads, founder videos, call recordings, interviews, tutorials — whenever someone wants footage cut, trimmed, captioned, reframed or turned into ad variants ("cut this into a 30s ad", "remove the ums", "make a vertical version", "edit these takes").

Make release-notes or weekly-update music videos using Suno, Gemini audio review, Dreamina/Seedance animation, Blender and a timed video composition. Use to plan an episode, write lyrics, compare takes, sync captions, build product demos, edit the video or prepare silent clips and a posting kit.

把拉片数据和原片合成一条**能直接看的视频**：一边是画面，一边是这一镜的分镜信息 （镜号、起止、时长、景别、类别、运镜、画面描述、台词），**镜头切了信息跟着切**， 镜头表自动滚动并高亮当前这一镜。 版式只看原片的宽高比：**横版 / 方版 → 画面在上、信息在下；竖版 → 画面在左、信息在右**， 画面永远原样缩放，不裁不拉。 镜头表**随播放滚动**：切点处滚一小段把当前镜头带到锚点、随后停住，高亮条同步滑过去。 实现上只截三张图（底板 + 铺开的长图 ×2），滚动与高亮由 ffmpeg 按时间裁窗， **布局全在 scripts/panel.css 里，改它就能改版式**，不用碰脚本。 吃 video-shots 产出的 shots.json（有 frames/ 就把关键帧当缩略图用）。 零 npm 依赖，用 ffmpeg 合成、无头浏览器渲面板。 Use when asked to 导出视频、合成视频、分镜视频、带分镜信息的视频、解说版视频、 video with shot info、annotated shot video。

拉片：把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面。 分工刻在骨子里：**能量的都由代码量**（切点来自 ffmpeg 场景检测，时长是切点相减， 运动量是逐帧差分的中位数），模型只判断它真正该判断的那几件事（景别 / 类别 / 运镜 / 画面 / 节奏）， 然后每一条判断都被代码当场对账——**声称推拉摇移却实测几乎不动，门直接拦**。 看片走联系表（每镜起手帧 + 收尾帧各拼一张大图，一屏二十几个镜头，a/b 对照就是运镜）， 不是一张张翻。检测漏刀多刀用 recut 补刀并刀，自动重编号重算时长，手改边界过不了门。 产出 shots.json + Markdown 镜头表 + **单页交互式拉片报告**：内嵌播放器（播放时同步高亮镜头、 点镜头跳转）、镜头节奏带、可搜索可筛选可排序的镜头表（列表 / 卡片两种视图、首尾关键帧并排、 点图开大图）、景别类别运镜分布、出场人物、质量门、导出 JSON。单文件零依赖，离线双击能开。 15 道质量门全部由脚本确定性检查。 零依赖、零 API key，只要 node 和 ffmpeg。 Use when asked to 拉片、拆镜头、分析视频镜头、镜头时长、景别、运镜、镜头表、 video shot breakdown、shot list from video。

把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。 走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条流）， 隐私保证来自结构，不来自枚举。 难点不在容器 tag，在**看不见的那几层**：x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进 DSE、avc1 的 compressorname 里还有一份——`ffprobe` 一个都看不见。 五个藏身处逐一堵死，每一处都有实测。 默认 `--mode copy`：**画面逐字节照搬**（cmp 验证过），只重编音频，53 秒的片子 1.3 秒跑完； `--mode encode` 完整重编码，多杀掉码流域的东西。 验收不靠声称：把源片所有元数据字符串当「针」，在输出文件里做**字节级扫描**， 扎到一根就红。12 道门全部由脚本确定性检查。 零依赖、零 API key，只要 node 和 ffmpeg。 Use when asked to 清元数据、去元数据、抹掉视频信息、视频隐私、去水印信息、 strip video metadata、remove exif from video、scrub video。

想做视频却不知道用什么工具？想让 AI 帮你「找技能 → 装技能 → 做视频 → 一条龙」？视频创作技能路由器（Video Creation Skill Router）是一个 AI video skill / animation skill 元技能——视频创作能力的发现与编排层，自身不生产视频，只做匹配、下载、编排执行、善后询问。你只管说需求（"把勾股定理做成讲解动画""给我的 APP 做个宣传片""剪掉这段口播的口误"），它自动完成：① 判定视频类别（商业宣传/知识科普/其他）并优先匹配本地已装技能；② 本地无命中则按类别走对应渠道（内置精选目录→GitHub 实时搜索→网络搜索）发现并下载安装；③ 编排执行所装技能，输出剪辑后的视频文件；④ 生成后说明所装技能的作用，问你要保留还是卸载。安装/卸载全程走安全协议（快照+校验+可回滚，禁 rm -rf）。覆盖 explainer video 知识讲解、product demo 商业宣传、talking-head 口播剪辑、motion graphics 动效、Manim 数学动画、Remotion 程序化视频。Use when 用户说「做视频」「找动画技能」「下载视频技能」「帮我剪辑口播」「video skill」「animation skill」「ai video skill」「how do I make a video with AI」「is there a skill for video editing」时触发。解决"想创作视频却不知道选什么工具、装了技能不敢卸"的问题。

עורך סרטונים — making YouTube Shorts edits from Avatar series (currently Avatar: Seven Havens). Use for ANY request to make, plan, edit or improve a video/short/edit for the user's YouTube channel. Holds the user's taste rules, what they liked and disliked, and the working technical pipeline.

Creative-director and motion-design layer for Remotion video work. Use for motion graphics, product promo videos, SaaS launch videos, product demos, UI animation, kinetic typography, cinematic product videos, animated explainers, marketing videos, and any Remotion project where story, look, motion or polish matters. Decides story, art direction, motion language, camera choreography, UI choreography and visual QA (premium light mode by default), then delegates all Remotion implementation to the official remotion-* skills. Also adds named effects to new or existing videos, including presenter (talking-head) footage, such as /logo-orbit, /number-roll, /words-kinetic and /portal, applying, offering or pushing back on each under a decision policy. Invoke as /motion-director:motion-design with a brief such as "15-second promo for my AI calendar".

Dub audio and video into other languages using the ElevenLabs Dubbing API (dubbing_v2), preserving the original speakers' voices. Use when translating videos, podcasts, or recordings into other languages, localizing media content, reviewing or correcting dubbing transcripts and translations, or regenerating a dub after edits.

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

Plan and build product launch films, explainers, demo walkthroughs, and teasers from references and real product screens. Use HTML and GSAP with the bundled frame renderer and music composed to the picture's cues.

>- Create, animate, review and render videos in code with fframes (Rust, SVG scenes, ffmpeg encoding, Skia GPU rendering). Use whenever the user wants a video, animation, motion graphic, explainer, promo, social clip, title card, podcast visual, lyric/caption video or any rendered .mp4/.webm made programmatically, or asks to change, fix, speed up or check an fframes video. Covers installing fframes, creating a project, designing good-looking motion, 3D shots (`fframes::three_d`, three.js style scenes), sound (music, voice, SFX, loudness), watching it in a real-time preview window, and checking the result without watching it: frames and contact sheets as PNG, automatic problem detection, loudness numbers, fast draft and range renders.