Video & Animation

把一个故事做成视频来演绎——用 Remotion 流水线把故事拆成镜头，逐镜设计与主题匹配的视觉风格和程序化动画，输出 1080p 成片。**视觉风格不设模板：配色、字体、动效语言按主题自由发挥。**触发词：故事视频、把故事做成视频、视频演绎、用Remotion做视频、口播视频、卡点视频。

Tự động TẠO và CHỈNH SỬA video chuyên nghiệp bằng một lệnh - dựng phim mới từ storyboard (cắt nguồn đúng ranh giới shot, ảnh Ken Burns mượt, chữ trên hình, hoà cảnh, giọng đọc TTS tiếng Việt giọng Bắc, nhạc nền ducking, LUFS chuẩn, phụ đề), thay giọng thuyết minh của video có sẵn (tách nhạc, tự dò mốc câu, đọc lại, giữ nhạc gốc), phụ đề tự động, sửa nhịp khung hình giật (60p/30p→24p), QC tự động (khung lạc, chớp, đứng hình, độ giật, LUFS, độ khớp lời), soi và sửa "AI slop" (câu sáo rỗng, số liệu không nguồn, khẳng định suông, dựng đều như máy, luật riêng của khách) và đẩy bản nháp sang CapCut. Dùng khi người dùng muốn làm video, dựng/cắt/ghép video, lồng tiếng/thuyết minh lại, đổi giọng đọc, thêm phụ đề, sửa video giật/mờ/lệch tiếng, kiểm tra video trước khi giao, kiểm kịch bản/phim nghe như AI viết, làm phim doanh nghiệp/giới thiệu dự án, hoặc dựng phim ngắn/micro-drama bằng AI.

为产品、品牌或服务制作宣传视频：分析用户素材，判断行业与受众，推荐风格与时长，提炼脚本分镜并经用户确认后，用 Remotion 渲染 MP4：模板片（storyboard 驱动的动态排版、SVG、图片）或电影级短片（3D 金属 Logo、还原真实产品界面的打字与点击演示、3D 画廊与景深、运动模糊、真实键盘音效），并从内置开源曲库自动选曲对拍（或用用户音乐、合成兜底）；每支片都叠一层动效设计（匹配剪辑、动态字、形状变形、遮罩转场、粒子高潮）；也能做作品合集、纯动态图形作品集（动态字、形状变形、3D、粒子、遮罩节奏）和单形状 UI 动效循环片（一个形状连续变形、弹簧、光标直接操控、无缝循环）。Use when the user asks for 宣传视频、宣传片、产品发布视频、产品介绍动画、动态设计作品集、片头、promo video, product launch video, explainer video, brand video or motion graphics showreel, or a looping one-shape UI morph animation.

Router for all Remotion skills

>- Creates professional 50-60s vertical explainer videos (9:16 format, 1080x1920 @ 30fps) for any given topic using Remotion, styled with modern aesthetics and narrated by natural voiceover using edge-tts-universal or CIT Voice Studio (selected via TTS_PROVIDER in .env). Follows remotion-dev/skills best practices for smooth springs, typography, sequence timing, and visual engagement.

用自然語言做「原理解說動畫影片」的端到端流程（HyperFrames + 中文旁白 + 字幕 + 三色主題 + 自我審查），產出可直接上課投影或上傳 YouTube 的 MP4。只要使用者要做解說動畫、科普動畫、原理動畫、教學動畫、explainer video、motion graphics 解說片，或說「上網查資料做一支解說 X 的動畫」，就一定要使用此技能。觸發情境包含：「做一個解說動畫」、「做科普影片」、「把這個原理做成動畫」、「做一支 90 秒的教學動畫」、「explain X as an animated video」。

End-to-end know-how for producing short-form and long-form social videos (Instagram Reels, YouTube, Shorts, explainers, talking-head and two-person collabs) with AI tools — ElevenLabs TTS/music/SFX, fal.ai image-to-video, Hedra Character-3 lip-sync, code-built Remotion motion design, ffmpeg mastering and QC — plus hook/CTA writing, Instagram growth rules and post-performance analysis. Use whenever a project involves scripting, storyboarding, generating, editing, rendering, mastering, publishing or analysing a video or reel, choosing AI video/image/voice models, budgeting AI generation spend, cleaning recorded voices, colour-matching speakers, or judging why a post did well or badly. Distilled from the Iran 2.0 Series 2 production (Sept–Oct 2026).

動態設計品味規則（HyperFrames 版）— 時間軸、緩動、彈性、節奏、字體（含繁體中文）、配色、質感與場景連貫，全部附具體數字。只要是製作、調整、重新計時或打磨動畫影片、片頭、轉場、motion graphics、HyperFrames composition，就一定要使用此技能。觸發情境包含：「做一支動畫」、「做動態影片」、「做片頭」、「motion design」、「讓這段字動起來」、「調整動畫節奏」等。

Make a narrated demo or promo video of the project's live site or app — scripted browser takes, Gemini voice-over, captions, music bed, ffmpeg edit, shareable link. Use when the user asks for a video that shows how their system works.

動畫影片的視覺自我審查循環（HyperFrames 版）— 輸出草稿、在每個時間軸節拍截圖拼成 contact sheet、逐張對照檢查表、修正、重來。只要動畫的畫面或時間有任何修改，以及在宣告影片完成之前，都一定要使用此技能。

Structure Remotion markup for interactivity

Router for all Remotion skills

WHEN the user wants MCP/agent-driven video editing entrypoints backed by OpenMontage rather than a greenfield MCP.

Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation. Use when: "create my Soul", "train my face", "make my digital twin", "build me an avatar", "learn my appearance", "create a character of me", "set up identity for video", "I want my face in generated images". Chain: train Soul (one-time, returns reference_id) → use in higgsfield-generate via `--soul-id <id>` with models like `text2image_soul_v2` or `soul_cinema_studio`. NOT for: one-shot face swaps (use higgsfield-generate with --image), named-character / non-photo avatars (use higgsfield-generate with prompt).

Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gpt_image_2. Entry point for professional brand/product visuals. Use when: "product photo", "studio shot", "lifestyle image", "Pinterest pin", "hero/banner", "carousel", "ad creative", "Meta ads", "virtual try-on", "model wearing", "person holding product", "closeup with hands", "levitating/floating/splash product", "CGI/surreal product", "restyle", "seasonal/aesthetic variation", or any product, brand, or paid-social creative. Modes: product_shot, lifestyle_scene, closeup_product_with_person, moodboard_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, restyle. Backend assembles the final prompt; never freehand it. NOT for: no-product text-to-image (use higgsfield-generate), branded avatar video (use higgsfield-generate Marketing Studio), marketplace listing cards (use higgsfield-marketplace-cards), Soul Character training (use higgsfield-soul-id).

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated motion-first unit, including an animated title. Route fresh creation through hyperframes before using this skill.

Generate marketplace product image cards through Higgsfield: compliant main image, secondary product images, and A+ style content modules. Use when the user asks for marketplace listing images, product detail cards, secondary product images, product infographics, lifestyle listing shots, A+ style content, marketplace image sets, or sales-ready product visuals. Backend owns marketplace compliance references and prompt templates; this skill only routes user intent to the CLI. NOT for generic brand product photography without marketplace/listing context (use higgsfield-product-photoshoot), video generation or UGC ads (use higgsfield-generate), or Soul Character training (use higgsfield-soul-id).

Generate images/videos via Higgsfield AI. Default: GPT Image 2 for images/design/text, Seedance 2.0 for video, Nano Banana 2/Pro for character/reference image work, Marketing Studio for ads with avatars/products/hooks, settings, plus Soul V2/Cinema/Cast/Location and Kling 3.0. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "produce a clip", "create an ad", "make a UGC video", "product demo", "unboxing", "brand video", "presenter video", "import product from URL", "create avatar for ad", or "analyze video virality". Supports image-to-image, image-to-video, references, job/upload IDs, and Marketing Studio. Chain with higgsfield-soul-id for face/identity consistency. Virality Predictor (`brain_activity`) analyzes video virality: hook strength, attention, retention, distraction risk, and creative score. NOT for: Soul Character training (use higgsfield-soul-id), product photoshoots, marketplace listing cards, text/chat/TTS tasks.

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.

Produce a video artifact with code — a pure time→frame renderer plus a validated render/encode/mux pipeline (motion graphics, data animations, explainers, showreels, generative loops, audio-reactive pieces). Use when the deliverable is a video file, a looping animation, a frame sequence to mux with audio, or when you must verify duration/fps/container specs, loop seams, a "nothing is ever frozen" floor, contact-sheet reviews, loudness/true-peak targets, or render throughput. Load before writing the first line of drawing code.

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

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.

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

영상(mp4)을 분석해 코드로 연출을 입힌 해설·하이라이트 영상을 만든다. 화면녹화(줌인·클릭 리플·풍선 도움말·HUD), 게임 플레이(돋보기 확대·피격 타격감·슬로모션·정지 화면·팝업 텍스트·HP 게이지 분석), 브이로그·애니메이션(대상 추적 말풍선·스티커·색보정·배속), 광고·홍보·여행 필름(원본 글씨 지우기·다국어 광고 타이포·낙관·먹물 전환·빛 번짐·레터박스)을 영상 유형별 프로필로 처리하고, 신스로 합성한 배경음(pop/epic/chill/cute/zen 국악풍)·효과음·원본 소리·선택적 성우 내레이션(TTS)을 믹스한다. "화면녹화에 설명 효과 넣어줘", "게임 영상 재밌게 편집", "보스전 하이라이트", "브이로그 자막·효과", "클릭할 때 줌인·풍선도움말", "자막·배경음·성우 입혀줘", "광고 영상으로 만들어줘", "홍보 영상 영어판", "원본 글씨 지우고 영어로", "screen recording explainer", "gameplay highlight edit", "promo film" 등에 사용한다.