Video & Animation

Build a Prezi-style "one picture, one camera" talk deck in open-slide. Covers storyboarding the stations, generating a 4K scene with Gemini, driving the camera inside the page (van Wijk zoom paths, bezier rides, a beat of hold before each card), checking smoothness with Playwright, recording a walkthrough for phone review, and presenting with a launcher. Use when someone wants a zooming or panning presentation, a Prezi-like deck, a cinematic slide deck, or a camera that flies through an illustra

설치본 플러그인에는 `docs/react/` 가 없다 — 이 파일의 `docs/...` 경로를 열 수 없으면 `https://raw.githubusercontent.com/joo6077/claude-plugins/main/` 뒤에 같은 경로를 붙여 읽고, 그래도 못 읽으면 내용을 지어내지 말고 못 읽었다고 적는다.

Turn a git repo's real history (tags, commits, diffs) into a polished release video — MP4/WebM/GIF, fully offline, free, with a scripted QA loop. Use when the user asks for a release video, changelog video, announcement clip, or "video for this release" from a repository.

Create advanced 3D-animation-style videos (product turntables, logo and title reveals, abstract motion graphics, camera fly-throughs, short cinematic scenes, social clips) by writing a Three.js scene, rendering it frame by frame in headless Chrome and encoding it with ffmpeg; a headless Blender path covers photoreal work. Use this skill whenever the user asks for a 3D video, 3D animation, motion-graphics clip, intro/outro, logo or title reveal, product showcase, camera fly-through, "cinematic" r

Motion film rendered from code, frame-checked.

Input a story or topic and output one complete shoot-ready file for Pixar-style animation or AI-generated photorealistic live-action, with character design sheets, scene and prop references, shot lists with @asset Paste prompts, transition and edit tables, six-panel storyboards, and a QC checklist.

Locked still + blueprint → provider motion prompt: camera, motion, physics, audio sync, for Veo/Kling/Sora. Code film → code-film.

用 Remotion 制作录像标注、技术可视化、介绍片场景与封面，落实系列视觉模板，并按需接入 Lottie、3D 和官方专项指导。适用于视频图形与动效制作；介绍片由总装工作流调度，已有网页动画走 web-capture。

当需要把经过查证的知识口播稿制作成手账风、不露脸的知识短视频，并准备素材、配音、分镜、剪辑、封面和复盘时使用。

艺术与视频动画：拆解复刻动画；36种既有实做风格＋16种可迁移研究配方；9种解说动画语法，8种可按口播参数渲片段；含口播整片参考代码及框景检查；人用AI生帧；可选已有录音、系统声音与语音复刻，按需配置。

Plan and produce a narrative video through causal story beats, continuous-action coverage, a timed rough cut, and separate technical and editorial review.

转写工具，不是成片入口。faster-whisper 把 mp4/wav/flac 转成 cues.json + srt，字段与 video-motion SubtitleCue 对齐。用户说「自动字幕 / 语音转字幕 / 转写 / 出字幕文件 / faster-whisper」时使用。用户说做介绍视频走 workflows/explainer-video.md；说给录像加讲解走 video-motion FootageOverlay，需要转写时再调本 skill。

Turn boring slides into animation-rich HTML. Builds self-contained animated SVG illustrations (CSS keyframes, optional click-driven step mode) that replace text blocks and screenshots in any HTML slide deck, and creates them directly from documentation of processes, dependencies, timelines or architectures. Use when the user wants to animate a PPT/PPTX or HTML deck, "make this slide less boring", draw a process/pipeline/dependency graph/timeline/comparison as an animation, or turn a Mermaid diag

Sound-design a finished video with real sound effects from the EditAtlas library (2,278 described sounds, public, downloadable from GitHub with SHA-256 checks). Finds the moments in the picture, lets you look at them as frame sheets, picks sounds by description and measured numbers, places each on its exact frame at a level set by its role, keeps or replaces the film's own music and voice, renders a new MP4 plus a separate SFX WAV, and checks the result in numbers (sync, pace, holes, loudness, m

A hardened, gated pipeline for producing short-form AI-generated "UGC-style" marketing video with a consented identity-locked presenter, real product footage, and word-pop captions — with hard-won fixes for the media-validation, audio-sync, and judge-hallucination traps that make these pipelines silently ship broken output.

Build scroll-driven animations with GSAP, ScrollTrigger, SplitText and Lenis smooth scroll — reveals, pinned sections, horizontal scroll, parallax, scrubbed timelines, text effects — in vanilla JS, React, Next.js, Vue/Nuxt, or Astro, with correct setup, cleanup and responsive fallbacks. Use whenever the user mentions GSAP, ScrollTrigger, Lenis, smooth scroll, parallax, pin, scrub, "animasi saat scroll", horizontal scroll, or scroll storytelling.

Make or edit animated, narrated, interactive web books from reference PDFs, animated picture books (paper-puppet films) from a story, a joke or a fairy tale, narrated documentaries about a book or an idea, built from public-domain pictures, upright shorts for a phone feed that make one point in under three minutes, scroll stories whose picture changes as the reader scrolls, and maps you explore, where a stretch of history plays year by year and the reader clicks the people and places on it. Use

Edit talking-head videos (lessons, courses, interviews) end to end in DaVinci Resolve Studio: word-level transcripts, a dossier of every take, the last complete take of each paragraph, a frame-accurate cut list, timeline assembly by script, render with presets, QC (loudness, frames, repeated words) and delivery. Load before any Resolve scripting, assembly, render, QC or video delivery work.

Recreate the visual style of any video in code (three.js / canvas → mp4) with your own story — from checking whether the style can be drawn in code, through a frame-accurate style spec, story and scenes, rendering and sound, to a finished video. Use when the user gives a video or channel link and asks to recreate its style, make "a video like this", break down a format, or make a new episode in a style that was already recreated.

Keep web animations inside the frame budget — animate composite-only properties, keep motion off the main thread when the page is busy, and find the cause when an animation drops frames. Covers the layout/paint/composite pipeline, cheaper property swaps, CSS vs WAAPI vs requestAnimationFrame, Motion's hardware-accelerated path, React re-rendering per frame, inherited CSS variable recalculation, blur cost, and when `will-change` actually helps. Use when an animation is janky, choppy, stutters, or

视频自动剪辑助手。基于 FFmpeg 自动提取精彩片段、生成字幕、裁剪时长、制作短视视频，支持多平台导出。当用户需要：自动剪辑视频、提取关键词片段、生成字幕并烧录、导出短视频、提取视频精华、生成视频摘要时使用此技能。

Use when making a narrated or voiced animated video with recurring characters - an anime, cartoon or comic episode, a short for a group chat, a story video about friends, family, a class or a team - from photos, a chat export, a story idea or a script, in any visual style, Hebrew/RTL or English. Also use when such a video has subtitles or cards too fast to read, music stopping early, the ending cut off, lines buried under music, mouths out of sync, a gesture before its line, or one face...

Use when turning a slide deck plus per-slide narration audio into an mp4 video — a self-playing/self-presenting deck video, "slides to video", "presentation to mp4", a shareable WhatsApp/Slack/Drive video of a narrated deck, or when a slide video needs a per-slide progress bar / countdown / slide counter. Also use when a slide video should highlight, glow or spotlight the element being talked about in time with the voice, or when narration and on-screen animation need syncing. Also use when...

Use when turning a still image, illustration, comic panel or character art into a short animated clip (image-to-video), choosing a video model or provider (Gemini Omni, Veo, Seedance, Kling, ElevenLabs Flows) or hitting their API gates, lip-syncing a character's mouth to existing dialogue audio (Sync, fal.ai, active speaker), or fixing a generated clip with artifacts - duplicated props, a door or a second figure appearing, hands through bodies, glowing eyes, a gesture repeated at the start,...