Video & Animation

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, timeline, history, clean, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), automation envelopes drawn on a track's volume or any effect parameter, or one submix bus carrying a chain, a fader and an automation clock for several tracks at once (`<hf-audio-group>`). Don't use for sourcing or generating audio — finding BGM, SFX, or making a voiceover is `/media-use`. Don't use for clip timing or track layout, which is `/hyperframes-core`.

Plan, direct, and produce code-drawn 2D/3D motion graphics and edited videos (reels, hooks, SaaS/product explainers, talking-head edits) on the user's local machine through any coding agent that has terminal + file access (Claude Code, Codex, Cursor, Claude Desktop, VS Code agents, etc.). Workflow: explain the process → user gives references + story → write a paste-ready ElevenLabs voiceover script → user generates and returns the MP3 → build, preview, render. Uses Canvas/SVG/p5.brush/Three.js/GSAP rendered in headless Chrome, Motion Canvas/Revideo, ffmpeg, small local AI models (cutout, transcription), plus LottieFiles, Freesound, Pexels/Pixabay, Firecrawl and ElevenLabs MCPs, and the Playwright MCP to browse any website visually (Pinterest, Behance, Dribbble, brand sites) and grab image/video assets by itself. Use when the user asks to make, edit, animate, caption, voice, or sound-design a video.

يمنتج فيديو كلام للكاميرا إلى ريل/إعلان 9:16: يشيل السكتات، كابشن عربي بتوقيت الكلمة، وموشن قرافيكس بألوانه. وفيه مونتاج مقاطع بلا كلام وبودكاست بكاميرتين. Use when user says "منتج هذا المقطع"، "سو من هذا الفيديو إعلان"، "شيّل السكتات"، "حوّل الفيديو لريل"، "ركّب كابشن عربي"، "اقص الصمت"، "مونتاج من هالمقاطع"، "بودكاست"، "كاميرتين"، or sends a talking video/clip folder. Also a no-person 3D motion-graphics explainer from text: "فيديو موشن"، "شرح بالموشن"، "سو فيديو من هالنص"، "موشن قرافيكس". Not for carousels or video covers.

يصنع فيديو تلاوة قرآن كامل 16:9 بالرسم العثماني (مصحف حفص – مجمع الملك فهد) متزامن مع صوت القارئ، مع «المختصر في التفسير» يُكتب حرفًا حرفًا من Tafsir MCP، وخلفية متحركة، وصورة القارئ واسمه بالخط، وثلاث صور مصغّرة (ثمنيل). Use when the user says "سو فيديو تلاوة"، "ركّب الآيات على التلاوة"، "ترجمة قرآن للتايم لاين"، "الرسم العثماني على الصوت"، "فيديو سورة"، "ثمنيل سورة", or sends a recitation audio / YouTube link of a sura.

Make explainers, feed ads, reels/stories, product demos and data-story videos from a JSON spec with the motionspec engine (script, narration, validate, preview, critique, render, captions, post pack). Use when the user wants any video made, remade for another format, narrated, or checked for brand and claim safety. Works for any product; brand lives in a theme file per project.

Rough-cut raw Vietnamese talking-head (selfie) videos full of false starts, retakes and stutters into one fluent take (keep the last clean take of each sentence, cut in silent gaps, loudnorm, 1080x1920), then hand each cut off to the post-production editor bot with transcript + notes. Use when asked to "cắt thô", "rough cut", "cắt video", "bỏ đoạn nói vấp/nói lại", or to process a batch of raw clips (local folder or public Google Drive folder) for the editor bot.

Direct and render a 30–180 second motion-design film for anything — a product, app, startup, feature launch, service, idea, research result, school project, game or personal story: kinetic typography, animated mock UI, charts, maps, characters and transitions on a music grid, an original procedural score, an AI voiceover (OpenRouter TTS — ElevenLabs v4, Gemini TTS…) verified by speech-to-text, karaoke subtitles and a ducked mix, all rendered to MP4 by code (no video editor, no stock). Optional real footage: frame-perfect capture of a live website, web app or browser game. Use whenever someone asks for a motion design / анимационный / моушн ролик, promo, explainer, launch or pitch video, trailer, teaser, showreel, video presentation of an idea, «видео про продукт/идею», «сделай классный ролик», or wants their idea or app turned into a cinematic video with voice and music — even if they never say \"motion design\".

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

End-to-end edit of a talking-head YouTube video in this workspace, in the channel's OWN brand (marka/MARKA.md + src/theme/theme.ts) — stage layouts that reframe the presenter, word-synced boards, kinetic theses, on-screen graphics, bespoke code-written animation scenes, sound effects + the user's music, master render, QC and delivery docs. Use when the user gives a new video and says "bunu kurgula", "yeni videoyu kurgula", "kurgula", "videoyu düzenle", "yeni video geldi", "edit this video", or asks to continue/resume an edit ("devam"). Also use for revision requests on a delivered edit.

Turn the current project into a narrated instructional video (how to do one task) or a feature update video (what's new in a release) using Hyperframes, or a general video for any process, third-party app, physical task or topic without a codebase (`--mode general`, researching official docs, screenshots and topic images). Steps outside the code (a vendor portal before a connector) work in any mode. 11 styles (teaching and energy), frame-preset themes, Kokoro voices, and a business share post; `/showhow options` lists them. Use when someone says "/showhow", "make a how-to video", "make a tutorial for X", "make a what's new video", "feature update video", "release video for 2.4", "make a video about X", "explain how X works in a video", or wants to show users how something works. Reads the project code, docs and git history directly - no live URL or screen recording needed.

Create short vertical videos (TikTok / Reels / Shorts / 抖音 / 快手 / 小红书) from a topic, a product link/image, or a script you already wrote. ClipForge runs the full pipeline — script → footage → voiceover → subtitles → BGM → compose — with a free, no-API-key path (free stock + Edge TTS + local FFmpeg). Use when the user wants to turn an idea, product, or written narration into a finished short video. Pipeline-correctness rules are hard; everything creative is your call.

为老板、专家、讲师与创始人完成获客型短视频IP定位、100个故事选题、可直接拍摄的口播脚本和访谈式日更内容。用户要做人设定位、内容栏目、爆款选题、脚本、主页包装或私域承接时使用；不处理剪辑软件教学、投流执行或账号代运营。

Direct the look of AI video like a cinematographer: camera language, movement, lighting, color, and style lenses. Use when a prompt needs a real shot in it, not just a subject, or when results look flat and amateur.

Direct and produce AI short videos led by a recurring cute pet, from visible story beats through shots, generation prompts, footage review, editing, and learning. Use for pet IP series featuring dogs, cats, or other companion animals. Do not use for unrelated human-led or generic film projects.

Use this skill whenever the user wants to create a finished video from a topic, title, idea, prompt, or script with MoneyPrinterTurbo. This includes short-form, voice-over, educational, marketing, social-media, and stock-footage videos. Also use it when the user mentions MoneyPrinterTurbo, provides this Skill URL, asks an AI agent to install or configure MoneyPrinterTurbo, needs missing API keys identified, wants a failed generation repaired, or wants a generated MP4 located and delivered. Use this skill when the expected outcome is a final video file, not setup instructions.

Produces Douyin / WeChat Channels (视频号) / TikTok-style vertical ad videos (≤30s, 9:16) end to end — hook-first script, cost quotes confirmed by the user before any paid generation, product-zero storyboard (AI footage shows only people; every product shot is real pixels via motion_clip / product-reveal overlays, so labels never garble), Seedance 2.5 via 即梦画布 CLI (credits) or reAPI (USD), per-video visual styling (fonts, stickers, calc board, end card), aligned captions, Suno BGM, cover image, publish copy and automated QA. Use when the user asks for 抖音/视频号/短视频/带货视频/广告片/口播视频/系列视频, mentions Seedance, 即梦, 画布, reAPI, 字幕, 花字, 封面, 价格卡, 算账板, 产品揭幕, 超分, or wants to turn a product + script into a finished video. Not for long-form editing, live streaming, or pure image tasks.

制作「Vibe 知识大赏」风格的无旁白 HTML 科普短视频（120–150s / 16:9 / 图形动画 + 事件拟声 + 氛围垫音）。当用户要做认知科普短视频、复刻 Vibe 知识大赏、把一篇科普文案做成动画短片、给知识视频配事件音效与封面、或需要这套流程图/分镜/验收时使用。不适用于需要人声解说、实拍、剧情或访谈的片子。

为产品、网站、App、SaaS、开源项目、课程、AI 模型或活动制作有商业质感的宣传片（4K MP4 + 网页版），流程包括调研、需求问询、风格样帧、真实页面 4K 截图、配乐卡点、AI 旁白、混音和自动校验。用户说「做宣传片」「做产品介绍视频」「做推广视频 / 预告片」「给这个项目做个视频」，或者要求 promo video、product trailer、launch video 时使用。

Make a promo, trailer, devlog or "how I made it" video about a web game, in the game's own look, opening on the Playgama AI logo sting. It shows real gameplay filmed frame by frame, the real prompts and agent steps as on-screen cards, a voice-over, music and an end card, all in the game's own colours, fonts and UI. Use this whenever a game developer wants any video about their game for YouTube, Shorts, TikTok, Reels, a landing page or a Playgama listing, especially a game made with an AI agent or published through Playgama MCP or the Playgama Bridge SDK. Use it even when they only say "make a trailer", "record gameplay for a video", "a short about my game" or "a video of how I built this", and whenever they need the Playgama AI logo or its intro animation.

Checks a rendered video before the final render — automatic QA (resolution, fps, duration, clipping, loudness, silence, black/frozen frames, missing assets, fonts, text overflow, safe areas, on-screen facts) plus a visual review of the contact sheet and stills by the video-qa subagent. Use after a draft render, before asking for the finalRender gate, or when the user asks to check a video.

用脚本化工具链从零驱动一条可交付的音视频成片, 不需要任何视频生成模型. 覆盖结构化提示词脚手架, 内容核查与文案编排, 分镜设计, 逐拍卡点, 程序化画面渲染, 程序化配乐合成, FFmpeg 编码封装, 以及在无视觉能力下用字符图与客观指标完成验收. 适用于科普讲解片, 产品宣传片, 数据动画, 片头片尾等需要自主生成视频的任务.