Video & Animation

Xử lý media — ffprobe thông số, ffmpeg cắt/ghép/transcode/GIF, trích frame, tách audio, phụ đề (shift/convert/burn), timecode SMPTE, phát hiện shot, OCR frame/ảnh, tải từ URL (yt-dlp), nhạc (thể loại/mood/BPM/lyrics). Dùng khi đưa video/audio/ảnh/URL media và muốn tóm tắt nội dung, trích text, cắt ghép, làm phụ đề, lấy khung hình, hoặc tải xuống.

将主题或材料经搜索核实制成苹果 Live Photo 信息动效卡。用 Remotion 编排图片、PNG、emoji、场景、时间线和可选图表，适用于知识解释、产品比较、变化过程及数据故事；制作可预览动效与配对实况资源，说明接收端兼容性。

Find everything worth keeping from this AI session (the main build, side discoveries, techniques, the feedback the user taught you), rate each by rarity on evidence, save them to LOOT.md, and turn the rare one that earns it into finished public work: a GitHub repo with docs and a logo, an agent skill, a blog post, a gist, a demo video. Also reads past Claude Code and Codex sessions. Use when the user says "loot", "/loot", "what's worth shipping from this", or "turn this into a repo / skill / blog post".

Write, structure and fix prompts for Kling 4.0 and Kling 4.0 Flash video generation, following Kling's official 4.0 user guide. Covers text-to-video, Omni Reference (@Image/@Video/@Element roles), first/last frames and up to 10 keyframes, 30-second multi-shot timelines, video editing ("Edit @Video1"), creative recreation of a reference video, dialogue in any supported language or accent, burned-in subtitles and on-screen text, and stylized looks. Use this skill whenever the user mentions Kling, Kling 4, Kling 4.0, Kling Flash or kling.ai and wants a video prompt written, expanded, converted, translated or debugged, even if they just describe a scene ("make a Kling prompt where…", "turn this idea into a 15s ad for Kling", "my Kling video keeps adding music / the face drifts / the camera ignores me"). Also use it to convert prompts written for Kling 3.0, Seedance, Veo, Sora or other video models into Kling 4.0 format.

Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content extracted into atomic, reusable Claude skills that an agent can invoke in real-world situations. NOT for simple summarization, book reviews, or role-playing as the author (that is nuwa-skill's job).

Use whenever words will appear on screen in a video - a title or intro, captions or subtitles, lower-thirds, labels, formulas, key terms, quotes, a lyric video or any kinetic typography - in Remotion or any other video tool, even when the user never says "typography". Puts the full range of text-animation techniques in front of you (slice, scramble, stomp, stroke write-on, marker highlight, odometer and about 75 more) so you choose by what the words mean instead of defaulting to fade, slide or pop. Includes ready-made Remotion components. For a whole kinetic-typography video made from a script, or when the user wants to plan and approve the type line by line, the kinetic-type-director skill runs the full process and builds on this one.

Engineering-grade explainer videos built as moving diagrams, in Remotion and three.js, where every number on screen is read from a source or computed by the build. Use when asked for an explainer, a technical walkthrough, an animated diagram, a LinkedIn or social video about how something works, or "make a video about X", especially when accuracy matters. Covers intake, brief, fact ledger, art direction, layout contract, frame-driven animation, procedural 3D assets, measured verification, encode and delivery. Hands off to the cuelab skill for sound.

Use when the user asks for a kinetic typography video (or a lyric, quote or lesson video where the words are the main visual) made from a script, or asks to direct, plan, review or approve the typography line by line before it is built. Drafts a "type script" (a text-animation technique for every line, chosen for its meaning), shows it as an interactive page in the built-in browser where the user previews and swaps styles, reads their choices back, then builds the approved version in Remotion. Not for simply adding captions or a title to a video; that is the kinetic-type skill on its own.

Generate AI videos and images with the Cheaper Gen. API (cheapergen.com), which runs official ByteDance Seedance and Seedream, Alibaba Wan and MiniMax models below their official prices. Use when the user wants to create a video or image with these models, add text-to-video, image-to-video, reference-to-video, text-to-image or image editing to code, or work with a CHEAPERGEN_API_KEY or cg_live_ key. Covers picking a model, quoting the price, submitting, polling or webhooks, @Image1-style reference mentions, uploads, billing and errors.

为中文历史与知识视频设计分镜、视觉风格和 Remotion 动效，制作文字审阅包、真人录制包与成片；也用于局部回修。

Build an evidence-based brag document or self-review draft from your merged pull requests and commits, leaving visible gaps where results are unknown. Use for review season, promotion cases or resume updates.

Cari judul film/serial dari link TikTok. Download video, bagi jadi 10 frame, diskusi dua AI bergantian (detektif vs skeptik) dengan verifikasi web search, semua file disimpan ke Google Drive via rclone. Gunakan saat user memberi link TikTok/video dan bertanya ini film apa.

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.

Plan and produce a 30–75s motion-design launch video for any product, in code, with Remotion (React), an optional AI voiceover and instrumental music, beat-synced cuts, kinetic typography and UI rebuilt from the product's real screens. Use when someone asks for a launch video, product explainer, feature showreel, What's new video, animated product demo, or social cutdowns (16:9, 1:1, 9:16).

Creative director for SaaS product launch videos made with HyperFrames (HTML to MP4) and Three.js. Pitches 3 distinct creative directions (clean editorial, bold graphic, cinematic 3D, technical/dev looks, each with a narrative shape and signature move) with rendered still frames, then builds the chosen one around the product's real UI. Works from the product's code, its website link (link mode extracts the brand) or screenshots, and can replicate a reference video's style, structure and rhythm (reference mode: shot detection, contact sheets, render-vs-reference comparison); includes a UI-rebuild rig, a Three.js device/panel stage, music prompting and variation mixing, and final delivery. Use when the user wants a launch video, product promo, feature announcement or social media video for a software product, sends a video to replicate, or mentions HyperFrames launch videos.

Turn any website URL into a ~25s 1920x1080 motion-graphics launch/promo video that copies the site's own design (background, colours, fonts, logo, UI style, real copy), with royalty-free procedural background music in a different style every time, plus whooshes on scene changes. Uses the Higgsfield sandbox (Higgsedit motion-graphics engine) - no video/audio generation credits. Use when the user shares a link and asks for a launch video, promo video, product video, motion video, "make a video for my website", or wants music added to such a video.

Run the affiliate lifecycle for a publisher up to, never including, the consent click. Phase 1 builds the join queue — which programs to apply to, in what order, grouped by network, each with a prefilled application packet and the exact human step. Use when deciding which affiliate programs to join next, preparing affiliate applications, or planning network (Impact, PartnerStack, FirstPromoter, direct) setup.

Transcribing, displaying and animating captions

Structure Remotion markup for interactivity

Router for all Remotion skills

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。

Router for all Remotion skills

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.