Video & Animation

Make, fix, redesign or audit TechNext explainer videos starring Nexi, the 3D robot mascot, with the in-house renderer at ~/ClaudeWork/nexi-tutorial. Covers Odoo walkthroughs, topic videos (myth-busting, quick tip, module explainer, before/after), solution videos (one per technext.asia service, built on an analogy or role-play), and any new Nexi video. Output is a 16:9 MP4 with Nexi's robot voice, typed captions, music and sound effects, delivered to the shared drive only after a strict release gate passes. Use whenever the user asks for a Nexi video, a video about an Odoo app or a TechNext service, or a fix or audit of an existing Nexi video.

Write, fix, and extend Adobe After Effects scripts (ExtendScript .jsx) and ScriptUI panels that run first time. Use this whenever the user wants an After Effects script, a .jsx file, a ScriptUI/dockable panel, an automation for AE (build grids of layers, generate shapes, batch-rename, stagger keyframes, create controller/null rigs, replace text, import files, set up render queue), or pastes an AE script error like "Unable to execute script at line…". Also use it when the user writes in Persian or Arabic about "اسکریپت افتر افکت" / "سكربت أفتر إفكتس" / "AE script", or asks for expressions to be applied by a script. Covers ES3 constraints, matchNames, keyframe easing, shape/text layers, RTL Persian and Arabic text, version differences up to AE 26.5, and a linter that must be run before delivering.

Turn a channel, niche, or rough topic into ready-to-make YouTube video ideas - each one packaged with title options, a thumbnail concept, a hook, format, and a reason it will win. Use whenever the user wants YouTube video ideas, content for a YouTube channel, "what should I make a video about," help brainstorming videos, title/thumbnail/hook ideas, a video series or content pillars, repurposing a topic into videos, or asks anything like "give me 10 video ideas for my [niche] channel," "package this idea," "write me some titles," "ideas for shorts," or "I have no idea what to film." Trigger even for casual asks like "video idea?" or when the user pastes a topic and wants it turned into videos. For finding underserved topics/openings first, pair with youtube-gap-finder. Do NOT use for non-YouTube platforms (see instagram-content-creator) or generic keyword research (see content-market-intelligence).

Cria vídeos de motion design 100% em código com o motion-studio (canvas frame a frame + render headless + sons sintetizados + mixagem com música). Use quando o usuário pedir um vídeo em motion, anúncio animado, vinheta, motion graphics, "um vídeo como aquele", para treinar/criar um novo ESTILO de vídeo a partir de uma referência, ou para ajustar/re-renderizar um projeto em motion-studio/projects. Não usa Remotion.

Make a complete faceless stick-figure (người que / stickman / doodle explainer) video from a topic — script, voiceover, consistent character sheet, one AI image per sentence, Ken Burns motion, captions, music — rendered to MP4 (16:9 long-form or 9:16 Shorts/TikTok). Built from 50 YouTube tutorials (Zenn / Ink Explainer / Rico / The Paint Explainer styles). Use when the user says "làm video người que", "video stickman", "video hoạt hình người que", "phim người que", "stick figure video", "doodle explainer", "kênh người que", or asks to turn a topic/script into a stick-figure video. Also for revisions of a stickman project ("đổi ảnh cảnh s05", "đổi giọng", "thêm nhạc").

Combo para fazer um vídeo explicativo ou promo de app (Reels 1080×1920, 30–60 s) com narração, música, legendas sincronizadas e motion premium. Junta as skills remotion-video, voz-pt-br e trilha-e-mixagem, com motion-video e ui-ux-pro-max como opcionais. Use quando o pedido for "vídeo do meu app", "anúncio animado com voz", "explicativo com narração".

Mettre en ligne une vidéo sur la chaîne YouTube de kil (pkkls) puis, sur son ordre, la poser sur la fiche Chrome Web Store et l'envoyer pour examen, le tout sans intervention. À utiliser quand kil demande d'uploader une vidéo sur YouTube ou de la mettre sur le store Chrome.

After Effects animation rendering for web and React applications. Use this skill when implementing Lottie animations, JSON vector animations, interactive animated icons, micro-interactions, or loading animations. Triggers on tasks involving Lottie, lottie-web, lottie-react, dotLottie, After Effects JSON export, bodymovin, animated SVG alternatives, or designer-created animations. Complements GSAP ScrollTrigger and Framer Motion for scroll-driven and interactive animations.

Write CAPTIONS-PLATFORMS.md for one finished short video: a per-platform post caption for Instagram, TikTok, YouTube Shorts (title + description), Facebook, Threads, Bluesky and X, each within that platform's limits, with your comment-keyword CTA on the platforms where it belongs and never on X. Keyword, CTA, platforms, hashtags and limits come from a config file; a checker script fails the file on any miss. Use after an edit is finished, when asked to 'write the captions', 'caption this reel for every platform', or before scheduling.

Modern animation library for React and JavaScript. Create smooth, production-ready animations with motion components, variants, gestures (hover/tap/drag), layout animations, AnimatePresence exit animations, spring physics, and scroll-based effects. Use when building interactive UI components, micro-interactions, page transitions, or complex animation sequences.

Turn videos into a reusable Claude skill or a specialist subagent (e.g. a video editor, social media manager, marketing specialist, or any expert role). Studies one or many YouTube/TikTok videos with the watch and gemini-watch skills, cross-checks what they teach, and writes a SKILL.md and/or agent file with the procedures, settings, principles and pitfalls. Use when the user says "learn this from the video", "teach Claude/my agent to do X", "build a skill/agent from these videos", "turn this tutorial into a skill", or shares a video and says "build this".

Measures and reconstructs UI motion from recordings, fits easing and springs, diagnoses jank, tunes gestures, and gates sparse interface sound. Use for "match this easing", "reverse engineer this motion", "debug this animation", or "add a click sound". For new web motion use animate; for motion critique use review-animations; for opportunity discovery use find-animation-opportunities.

Transcribe audio or video on your own machine with Whisper (mlx-whisper, faster-whisper or whisper.cpp) and get word-level timestamps as words.json, a plain .txt and an .srt. No API key, nothing uploaded. This is the transcription step the editing skills (edit-style, longform-edit, reel-captions) depend on. Use when asked to transcribe a take, get word timings, make an SRT, re-transcribe a final render for a caption sync check, or 'run whisper locally'.

Have Google Gemini actually watch a video (moving picture and audio together) and report back. Gemini reads public YouTube links natively, so nothing is downloaded. Use when a video's value is visual or in the audio (editing technique, physical demonstrations, software walkthroughs, music, tone), when the watch skill finds no captions, when YouTube downloads are blocked, or when the user asks to use Gemini on a video.

Runs five agents that keep a YouTube channel's titles and descriptions matched to what people search for now: a Channel Reader that pulls the user's own video list and stats with their YouTube Data API key, YouTube Analytics OAuth or a pasted YouTube Studio export, a Niche Watcher that finds what is working right now for similar-size channels from public search results the API returns or the user provides, a Title Writer that drafts titles, descriptions and chapters for new videos, a Back Catalogue agent that picks old videos worth a refresh and drafts new versions, and a Change Tracker that records every change the user makes and compares before and after on matched windows. Use when a creator asks for YouTube SEO, better titles or descriptions, what is working in their niche, a back catalogue refresh, or says \"seo run\". Never invents search volumes or stats and never changes a video; drafts only.

Writes captions for a finished video from its transcript: pulls the line worth repeating, writes first-line options, writes per-platform versions (Instagram, TikTok, YouTube title and description, others on request), keeps the creator's voice using their best past captions, and checks the call to action matches what the video actually says. Use when a creator asks for captions, a caption hook, a YouTube title and description, or a CTA check. Drafts only; never posts or schedules.

Create polished short product demo or store promo videos from product screenshots, screen recordings, a repository, and optional visual references. Use for a new promo or a substantial restyle, not for simple trimming or captions.

“一个关键词出一期像素风口播动画”工作流。用户只给一个主题或关键词（比如“上下文是什么”“MCP”），就依次写口播稿、用复刻音色配音并加速 1.2 倍、转 SRT、在 weilanx-claude-videos 工程里新建一期（竖屏 3:4、首帧带封面）并剪好、写好发布文案（标题和描述），最后打开 Remotion Studio 给用户预览；用户确认后再导出，成片目录里同时带字幕稿和发布文案。用户说“做一期 XX”“用这个关键词出一期视频”“按工作流来”时使用。

「Vox 拼贴风科普短视频」工作流：给一个科普主题（新闻、诺奖、科学发现、科技事件），先上网查权威资料和可用的真实素材（NASA、Wikimedia Commons、官方新闻稿插图），写一份像聊天一样有语气、有强钩子和深度结尾的口播稿，用带语气提示的豆包复刻音色配音，再在 weilanx-claude-videos 工程里做成横屏 16:9 的 Vox 拼贴片：A-roll 是黑卡大字，B-roll 是钉在旧纸桌面上的真实视频和照片，按字幕硬切，配一条有律动的电子配乐。最后打开 Remotion Studio 给用户预览，确认后再导出。用户说「做一期 Vox 风格的科普」「用 Vox 风格讲讲 XX」「做一期 XX 的科普，要真实素材」「像诺奖那期一样做一期」时使用。

「暗金文献风纯音乐知识短片」工作流：给一个知识点（数学、经济、心理、科学、历史上的某个规律或冷知识），不配音、不找素材，只用代码画面 + 中英双语字幕 + 一首配乐，在 weilanx-claude-videos 工程里做成横屏 16:9 的 30～60 秒短片：近黑底、金色细线、衬线字，先找一个「锚词」，开头用第二人称写观众的处境，第一个高潮踩在配乐的「换气 + 重拍」上让锚词砸出来，结尾重新定义锚词并抛一个问题。最后打开 Remotion Studio 给用户预览，确认后再导出。用户说「做一期暗金风的」「像棋盘麦粒那期一样做一期」「用金色风格讲讲 XX」「做一条纯音乐的知识视频」「Vibe 知识视频」「不要口播，只要字幕和音乐」时都用这个 skill，即使没提「暗金」两个字，只要是无口播、靠画面和字幕讲一个知识点的短片也用它。

Compare multiple frames from videos or photos across cameras, lighting, and output formats, then review a deliberate color adjustment.

Reframe a selected source range for wide YouTube, vertical Reels or Shorts, square, or portrait-feed delivery with fit or intentional crop.

Audit the picture and audio at edit boundaries in a rendered video, catching clipped speech, sudden sound changes, black frames, awkward dissolves, and visible jump cuts.

Measure and finish the mixed audio of a Reel, Short, long video, or audio-only deliverable with local FFmpeg and an encoded-output check.