Video & Animation

Kısa Video Kural Kitabı — Reels / Shorts / TikTok kurgusu için ölçülmüş kurallar (önce konuşan kafa videoları). Hangi çekimin seçileceği, kelimeye oturan kesim, akan altyazı, vurgu, zoom, konuşanın arkasına yazı, ses efektleri, müzik seviyesi, ilk 3 saniye ve bitişler; 52 viral kısa video ve 12 kurgu eğitimi videosundan çıkan sayılarla. Kısa video kurgusu planlarken, kurarken ya da incelerken yükle. Tetikleyiciler - "reels kurgula", "short yap", "altyazı ekle", "kurguma bak", "edit this reel", "short-form edit", "caption style".

Premium, liquid, cut-free motion graphics in the style of top product films (Apple, OpenAI, Anthropic, Bentomotion-style morphs, neon rim-light, glass, metaballs), built with HyperFrames and set to music the user supplies. Use when the user asks for motion graphics, a promo/launch/explainer/reel with "smooth", "liquid", "fluid", "no cuts", "premium", "professional", "like big companies", or mentions MotionKit, a MotionKit style (Ember Flow, Morph Continuum, Neon Rim, Breathing-Gradient SaaS, Glass Orb, Single-Line, Liquid Gradient Pop, Bold Brand…) or wants to reuse the kit/samples.

Hadi Got Motion: a director-grade motion graphics studio for Claude. It makes motion graphics, animated explainers, story reels, cut-out character animation with talking puppets, kinetic type, text movements, real-geography map animations (routes, walks, flights, globes, terrain) and title moments that never look AI-made. On start it checks and installs its own tools, then shows a visual brief picker: title, duration, concept, 12 motion styles that each move their own way, a hands-off 'Let Claude decide' option, 12 map looks, and a script you can upload or type. It gives a time estimate, connects ElevenLabs voices and, optionally, ChatGPT images, then builds and renders the finished MP4. Use it whenever someone asks for a motion graphic, animation, explainer, reel, animated story, kinetic or moving text, or a lyric, title or map animation.

Turn a folder of course materials (lecture slides/PDFs, practice problems with solutions, revision videos, notes) into a six-PDF study pack — a mock test, its answer key, a unit-by-unit problem workbook with show-your-work solutions, a complete master reference (also usable as context for another AI), concepts notes, and a question→answer drill ordered by how likely each question type is. Use when the user says /study-pack, "make me a study pack", "study pack for <course>", "the multiple PDF method", "help me study for <test> from these files", or points at a folder of course materials and asks for practice tests or study notes.

Create fast, emotional AI mini-series episodes for video.

Builds original 2D sprite cartoons from character reference sheets and a reference video. Use when someone asks for a 2D cartoon, sprite film, character animation, OpenVoice preschool voices, or to set up Sprite Stage.

Applies one of 36 video effects (neon text behind the head, magazine cover, reels orbiting around the person, glass widgets, render checklist, tier list, glitch…) to a vertical face-camera clip and renders it in 4K with Remotion. Use when the user types /effects, attaches a selfie/facecam video and asks for an effect, an edit, a "reel effect", or wants to see the list of effects.

Rehearse any important meeting before it happens. Predicts how the conversation will go, then builds a rehearsal kit from the prediction - the script, a two-voice audio talk track, a video with burned-in subtitles, a subtitle file and a flip-through presentation with one slide per talking section. Use whenever someone is preparing for a job interview, sales or discovery call, negotiation, pitch, investor or board update, performance review or any high-stakes conversation, or asks for a mock interview, role-play, practice run, talk track, call prep, or "how will this meeting go", even if they never mention audio, video or slides.

Record a short, polished product demo video of a web app (a real browser, an eased zoom toward each click, a spring-smoothed cursor) and export MP4, a poster and optionally a GIF. Use when a moving demo explains a feature better than a screenshot, for release notes, docs, decks, PRs or Slack. Triggers on "record a demo", "demo video", "screen recording of", "make a GIF of", "show this feature in a video".

Planifier, rédiger et auditer du contenu pour Instagram. Utilise ce bundle quand l'utilisatrice dit « écris la légende de mon reel » (hook dans les 125 premiers caractères), « planifie mon carrousel » slide par slide, « décortique le hook de ce reel viral », « trouve-moi des hashtags » calibrés façon 2026, « enlève les tics d'IA de ma légende », « planifie ma semaine de contenu », ou « qu'est-ce qui marche dans ma niche ». Instagram exige un média sur chaque post : les skills écrivent le texte, l'utilisatrice ajoute l'image ou la vidéo et publie elle-même dans l'app Instagram.

Crea Reels/TikToks verticales 9:16 animados con Remotion (texto cinético, mascota pixel "Bit", HUD de progreso, voz en off de ElevenLabs y efectos de sonido) a partir de un tema o guion. Úsala cuando el usuario pida un reel, short, TikTok o video animado vertical para redes sociales, o quiera adaptar el reel "Cartuchos" a otro tema.

Transcribe a falling-bars piano video (Synthesia-style YouTube tutorial, or a local video file) into MIDI, sheet music (PDF, MusicXML, MuseScore) and audio, optionally folded onto a smaller keyboard. Use when the user shares a piano tutorial link or video with falling (or rising) notes and wants its notes, sheet music, a score, a MIDI or an audio version, or wants it to fit a 61, 49 or other smaller keyboard. Trigger phrases include "transcribe this piano video", "sheet music from this YouTube link", "make a MIDI from this tutorial", "Synthesia to MIDI", "Synthesia to sheet music", "piano tutorial to sheet music", "falling notes to MIDI", "get the notes from this piano video", "turn this video into a PDF score", "I want to play this on my 61-key keyboard". Do not use for plain audio or for a filmed piano without falling bars, since the tool reads the bars, not the sound.

用 AI 给实体产品做视频的完整方法和工具：3D 预演定位（可选）→ 图像模型画写实关键帧 → 视频模型生成镜头 → 代码剪辑、字幕、引线标注、配乐、音效、混音 → 多画幅、多语言交付。适用于产品功能演示片、品牌广告（15/30/60 秒）、抖音小红书等竖版短视频、电商主图视频、发布会和路演短片。只要用户想给一个实体产品（硬件、家电、消费电子、家居、穿戴、日用品等）做 AI 视频、宣传片、广告片、种草视频、功能演示或产品展示，或者在这类任务里提到分镜脚本、关键帧、首尾帧、白模或灰模预演、Seedance、可灵 Kling、Runway、Veo、即梦、ChatGPT 或 GPT Image、Nano Banana、Midjourney 出图、视频转场、字幕排版、配乐混音、竖版改版、多语言版本，就使用这个 skill，即使用户没有提到 skill。纯剧情短剧、MV、动画等没有实体产品的视频不适用。English requests such as "make an AI ad / explainer / launch video for my product" also qualify.

Cria Reels/Shorts/TikTok verticais (1080x1920) de alta retenção para vender um app, SaaS ou produto — do roteiro persuasivo ao MP4 renderizado. Primeiro entrega o ROTEIRO (hook visual + sonoro + falado, dor, virada, solução com telas reais, CTA) para aprovação; só depois gera narração (ElevenLabs, opcional), trilha, efeitos e anima tudo em HTML + GSAP com HyperFrames, com efeitos dopaminérgicos fluidos (barra de progresso, zoom punch, confete, contadores, transições contínuas). Use SEMPRE que a pessoa pedir "faz um reel", "vídeo pro Instagram/TikTok", "vídeo explicativo do app", "anúncio em vídeo", "vídeo tocando na dor do cliente", "hook que prenda nos 3 primeiros segundos", "vídeo estilo app explainer", ou quiser transformar uma dor/funcionalidade do produto em vídeo curto vertical — mesmo sem citar a skill. Não use para editar vídeo gravado com pessoas (talking head), thumbnails ou carrosséis estáticos.

Use FIRST for any non-trivial request: before working, search the user's installed skills, MCP servers, plugins and CLIs with qm search, then load and use the ones that fit. The host truncates tool descriptions, so many installed tools are invisible to you; this skill finds them. Any domain: code, documents (PDF, Excel, slides), data, SEO, ads, video, sales, CRM, cloud, security, design, e-commerce, support. Skip only greetings, chit-chat and short knowledge questions.

Use when the user gives a video file or link and wants Shorts/Reels/TikToks cut from it. Fetches and transcribes locally, you pick the best 10-50 s moments with a rubric, the user approves, then it renders 9:16 clips with face-tracked crop, word-by-word captions, SFX, optional ducked music and -14 LUFS audio, plus titles and hashtags.

Plug-and-play motion design studio for product films in HyperFrames. Give it a company name, a URL or a codebase and it researches the product, builds a brand kit (logo, fonts, colours, real UI), scripts real product moments, and builds the film from 30 archetype scene templates studied from 18 premium reference reels. Includes an ElevenLabs voiceover pipeline with a budget guard, an SFX mix, native format presets (16:9 1080/4K, 9:16, 1:1, 4:5), and QA gates including a WCAG flash check. Use for product launch films, social cuts, explainers, logo stings, reel recreations ("make this kind of motion for X"), or "make a video for <company>".

Audit every animation and transition in a web or React Native app against how often people see it. Census all motion sites with a scanner, tag each with frequency tier, purpose and role, give each a verdict (CUT, SWAP, TRIM, GUARD, CHECK, KEEP) with a suggested duration, and price the waiting it causes in seconds per day on real user flows. Use when an interface feels slow or "floaty", before a motion polish pass, when reviewing a PR that adds animation, or when you need a reduced-motion story.

Turn a talking-head video and its transcript into motion-graphic B-roll timed to the speaker's words, in a continuous one-shape style (one element that morphs and never cuts, driven by a cursor, spring motion). Use when someone gives a video (and ideally a transcript) and asks for motion graphics, B-roll, animated cutaways or overlays.

Create polished Chinese knowledge-explainer videos with Remotion from a topic or source material. Use when the user asks for a Vibe 知识大赏-style science, technology, history, business, psychology, or general knowledge video; wants a Remotion project, animated explainer, coded video, narration script, storyboard, subtitles, preview clip, or final MP4; or wants to turn documents and verified research into visual video scenes.

Read a codebase and unfold it into an interactive, zoomable map of what the system does, so a newcomer reaches a developer's understanding. The overview is an architecture diagram with inputs and outputs marked; clicking a part zooms into what fits its code (process flowchart, sequence, state machine, data model, class diagram, C4, deployment, behaviour tree, timeline) or opens screenshots and videos. Boxes cite their source files, hover traces data flow, guided tours and a presentation mode teach it, and a built-in editor lets anyone refine it. Exports PNG, SVG, PDF, Mermaid, draw.io and Excalidraw. Use whenever someone wants to understand, explain, present, document, review or onboard people onto a codebase, repo, service, pipeline, ROS 2 stack, firmware or app, e.g. "diagram this repo", "how does this code work", "architecture overview", "walk me through this project" or "I'm bad at presenting what I built", even if they never say diagram.

Seedance 2.5 skill for Dola AI 15-second — specialized Seedance 2.5 video generation with hard-locked single-segment 15-second output, bulk TXT/Notepad prompt queueing, resilient skip-and-continue failure handling, end-of-run retry analysis, and an opt-in 15-minute Dola AI 15-Second Mode watchdog. Normal video generation runs on autopilot without confirmation; the cron/watchdog stays OFF until the user manually says “dola ai 15 second mode activate”. Always generates each video as one complete call and preserves the original Seedance 2.5 generation rules.

Use for any CapCut / 剪映 work from Claude through the CapCut MCP — uploading local media, building or editing CapCut cloud drafts (video clips, music, sound effects, text, captions, filters, transitions, text templates), material/template search, automatic captions, AI rough cuts (AI Lab), AI image/video generation, and fixing the CapCut MCP connection or login. Adapts the official CapCut Codex plugin to Claude; read before the first CapCut tool call.

Seedance 2.5 skill for Dola AI 30-second — specialized Seedance 2.5 video generation with hard-locked single-segment 30-second output, bulk TXT/Notepad prompt queueing, resilient skip-and-continue failure handling, end-of-run retry analysis, and an opt-in 15-minute Dola AI 30-Second Mode watchdog. Normal video generation runs on autopilot without confirmation; the cron/watchdog stays OFF until the user manually says “dola ai 30 second mode activate”. Always generates each video as one complete call and preserves the original Seedance 2.5 generation rules.