Video & Animation

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.

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.

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.

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。

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。

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。

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.

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.

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.

Packages YouTube videos and Shorts: a pack of 3-4 thumbnail variants of one idea for choice and A/B testing, title and thumbnail as one unit, one idea per image, face and emotion, a large object, text up to 3-4 words or none, readable on a small phone screen. Works from own frames and screenshots plus references, generates or refines the frame with models (Nano Banana, Seedream, GPT-Image, Higgsfield and others) with the film-look style and logos in one pass, keeps a consistent channel series, checks the file with a script (size, weight, name), reviews the small view by eye on a contact sheet and shows options to the owner before upload. Triggers: 'YouTube thumbnail', 'video packaging', 'thumbnail A/B test', 'Shorts cover', 'title and thumbnail'. Triggers (RU): «сделай превью», «обложку для ролика», «обложку для YouTube», «упакуй ролик», «варианты для A/B-теста», «заголовок и превью», «обложку для Shorts», «серия превью для канала».

Writes the motion design brief and builds HyperFrames motion segments in the brand's motion language, renders them to transparent WebM and inserts them into the Remotion edit. Use for the motion stage in production or when the user asks for animated cards, transitions or motion graphics. No segment is built without an approved MOTION_BRIEF section.

Builds on-screen captions for a video package with the caption engine (meaning-based word groups, safe areas, UI avoidance), transcribes real recorded speech into a corrected transcript, and produces the SRT. Use for the captions stage, after recording speech, or when captions are out of sync, split badly or duplicated. Platform post text is content-repurposer's job.

Runs a client AI video for a concept studio from brief to delivery. Takes the brief and real product photos, writes a synopsis, builds character and location sheets with 3 options each, a 16:9 approval deck, stills in waves, one prompt for the whole video, client revisions as a list, assembly and a delivery checklist. Core rule: the client approves the preproduction package before the first video frame, and the approved character and location sheets go as references into every generation. Use when a brief arrives for an advertising or product AI video. Triggers: 'client AI video', 'preproduction package', 'character sheet', 'location sheet'. Not for articles or covers (use blog-article and article-cover). Triggers (RU): «вот бриф», «новый клиент», «концепт студия», «препродакшн-пакет», «лист персонажа», «лист локации», «презентация клиенту», «правки от клиента», «готовим сдачу».

Makes motion graphics on the HyperFrames engine (HTML scenes rendered to video) with an AIVFX studio layer: name lower thirds, chapters, numbers, Shorts and Reels hooks, end cards, titles. The brand (colors, fonts, motion, durations) lives in one file, the video is a brief of scene roles, motion is set in words, and the agent renders a draft over footage and a final ProRes 4444 with alpha. Gives timing rules, 9:16 and 16:9 safe zones, lint and black-frame checks, a delivery checklist and a brand file checker. Triggers: 'lower third', 'motion graphics', 'chapter card', 'shorts hook', 'end card', 'transparent overlay', 'brand kit for motion', 'HyperFrames'. Triggers (RU): «сделай плашку», «нижняя треть», «плашка с именем», «заставка», «глава», «титры», «хук для шортс», «финальная карточка», «моушен для ролика», «графика с альфой для монтажа», «заведи бренд для графики», «сделай на хайперфреймс».

This concise reference is authored for the harness. Full product guidance lives in the installed desktop app and official HyperFrames documentation.

Render a 5-6 second motion graphic in which an oversized condensed headline (2-4 words) punches in behind a presenter, using a background-removed cutout of the presenter layered on top of the lettering. A hard cut then removes the presenter while the same headline holds the exact same size and position, and a short supporting line appears for a reading hold. Use it for talking-head intros, chapter openers, launch announcements and social hooks when you have one presenter clip, a headline, a supporting line and a palette. Built on HyperFrames; delivers a 1920x1080 H.264 MP4 plus the editable project.

Builds a 6-8 second logo sting in which the brand mark rides inside a refracting liquid bead (distorted past legibility), the bead swells, holds still for a beat, then ruptures into droplets and leaves the logo lockup (mark plus wordmark) crisp and upright on screen. Delivered as a 1920x1080 H.264 MP4 plus the editable HyperFrames project, with no 3D model, stock footage or generation model. Use it for brand intros and outros, product-launch openers, channel stings and any "reveal our logo" moment, from an SVG or PNG logo (including raster-only logos), a wordmark string and a palette.

Make a roughly 30-second film that explains a code change (a pull request, release or uncommitted diff) to people who will never read the diff. It opens by showing the real diff scrolling past too fast to follow, cuts to a plain-language summary, fires four capability beats each pinned to a real code snippet, and closes on how to get it (install command and URL). Delivered as a 1920x1080 H.264 MP4 plus the editable HyperFrames project. Use when asked to turn a PR, changelog or release into a launch or explainer video.

All-in-one studio harness and production pipeline for generating high-end programmatic video, motion graphics, and kinetic design using Claude Sonnet and HyperFrames. Unifies directorial vision, anti-slop rules, GSAP animation physics, WCAG accessibility gates, audio beat-sync, and automated visual QA. Use whenever creating or editing videos, motion graphics, animated explainers, kinetic typography, product promos, or UI showcases.

Video work: watch and break down a video or reel (from a file path or a YouTube/TikTok/Instagram/Vimeo link), transcribe speech, download a clip, and make captions, graphic overlays or short animations with HyperFrames. Use FIRST for any video or audio task: "watch this video", "what's in this reel", "transcribe", "add captions", "add overlays", "edit my reel", "make an intro". Tells which HyperFrames skill to use next and prepares an accurate word-level transcript (on the GPU if there is one).

All-in-one studio harness and production pipeline for generating high-end programmatic video, motion graphics, and kinetic design using Claude Sonnet and HyperFrames. Unifies directorial vision, anti-slop rules, GSAP animation physics, WCAG accessibility gates, audio beat-sync, and automated visual QA. Use whenever creating or editing videos, motion graphics, animated explainers, kinetic typography, product promos, or UI showcases.

Builds a 10-14 second product sting out of a short run of UI moments (an entry screen, a single counting metric, a navigation list, one click that opens a menu, then an endcard) cut together so every cut carries the previous motion forward and the piece reads as one continuous camera move. Delivered as a 1920x1080 H.264 MP4 plus an editable single-file HyperFrames project. Use it for app launches, feature teasers, social bumpers and site intros when you have a product's logo, a couple of screenshots, one headline number and its real nav labels, and want polished UI motion without narration.

Видео на русском: посмотреть и разобрать видео или рилс (по пути к файлу или по ссылке YouTube/VK/Rutube/Instagram), расшифровать речь, скачать ролик, а также сделать субтитры, плашки/инфографику поверх видео или короткую анимацию через HyperFrames. Использовать ПЕРВЫМ при любой задаче с видео или звуком: «посмотри видео», «что в ролике», «расшифруй», «сделай субтитры», «добавь плашки», «смонтируй рилс», «сделай заставку». Говорит, какой скилл HyperFrames брать дальше, и готовит точную русскую расшифровку по словам (на видеокарте, если она есть).