Communitygithub.com

NeverSight/learn-skills.dev

在程序化视频创建、基于React的视频合成、动画实现(文本、元素、场景过渡)、视频渲染为MP4/WebM以及搭建独立Remotion项目时启用此技能。触发条件包括视频创建、Remotion合成、useCurrentFrame、interpolate、spring动画和视频渲染。

learn-skills.dev 是什么?

该技能专注于使用Remotion框架进行程序化视频创建。Remotion是一个基于React的框架,它允许开发者通过编写React组件来定义视频的每一帧,从而充分利用TypeScript、npm包和组件化架构来构建各种视频,从动画解说和社交媒体剪辑到数据驱动可视化和大规模个性化视频。该技能涵盖了项目设置、合成结构、基于帧的动画(interpolate和spring)、场景排序、资产管理、音频集成、通过Zod模式参数化视频以及通过CLI或程序化API渲染为MP4/WebM。它适用于Claude Code、Cursor、Codex等AI助手平台,帮助用户高效地创建和渲染程序化视频。该技能的核心原则包括:每一帧都是纯函数、合成是视频单元、使用interpolate进行动画、使用Sequence和Series进行时间偏移、资产静态化但数据动态化。它还提供了常见任务的代码示例,如项目初始化、基本合成创建、逐字动画、spring动画、场景过渡、资产处理、音频集成和视频渲染。

兼容平台✓Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/absolutelyskilled/absolutelyskilled/remotion-video

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

当此技能被激活时,务必以 :clapper: 表情符号开始你的第一个回复。

Remotion 视频

Remotion 是一个使用 React 进行程序化视频创建的框架。与基于时间线的编辑器不同,你可以将视频合成编写为 React 组件,其中的每一帧都是当前帧编号的函数。这为你提供了 TypeScript、npm 包和基于组件的架构的全部能力来构建视频——从动画解说和社交媒体剪辑,到数据驱动可视化和大规模个性化视频。

本技能涵盖项目设置、合成结构、基于帧的动画(使用 interpolate 和 spring)、场景排序、资产管理、音频集成、使用 Zod 模式参数化视频,以及通过 CLI 或程序化 API 渲染为 MP4/WebM。


何时使用本技能

当用户出现以下情况时触发此技能:

  • 想要使用 React/TypeScript 程序化创建视频
  • 询问关于 Remotion 合成、useCurrentFrame 或 useVideoConfig
  • 需要对文本、元素或场景之间的过渡进行动画处理
  • 想要将视频从代码渲染为 MP4、WebM 或 GIF
  • 询问关于 spring 动画、interpolate 或基于帧的时序
  • 需要从头开始搭建一个新的 Remotion 项目
  • 想要为 Remotion 视频添加音频、图像或字体
  • 询问关于参数化/数据驱动视频生成
  • 需要配置 Remotion Studio 用于预览合成

在以下情况下不要触发此技能:

  • 与视频创建无关的通用 React 问题——请使用 React 技能
  • 使用传统时间线工具(Premiere、DaVinci、FFmpeg CLI)进行视频编辑
  • 网页的 CSS 动画——请使用动画/动效设计技能
  • Web 应用中的视频播放或流媒体——请使用媒体播放器技能

核心原则

  1. 每一帧都是纯函数 - Remotion 组件通过 useCurrentFrame() 接收当前帧,并且必须为该帧进行确定性渲染。无副作用,无无种子的随机性,不依赖墙钟时间。相同的帧编号必须始终产生相同的视觉输出。

  2. 合成是视频的单元 - 每个 <Composition> 定义了一个具有明确尺寸(宽度、高度)、帧率(fps)和时长(durationInFrames)的视频。将合成视为项目中的“页面”——每个独立可渲染的视频变体或场景对应一个合成。

  3. 使用 interpolate 处理一切 - interpolate() 函数将帧编号映射到任何数值(不透明度、位置、缩放、颜色通道)。结合 extrapolateRight: 'clamp',它是所有动画的主力。当你需要基于物理的缓动效果时,请使用 spring()。

  4. 使用 Sequence 处理时间偏移 - 使用 <Sequence from={frame}> 延迟子元素开始出现的时间,使用 <Series> 逐个播放子元素。切勿使用 setTimeout 或手动帧计算进行排序——声明式原语在预览和渲染中都能正确处理。

  5. 资产是静态的,数据是动态的 - 将图像、字体和音频文件放在 public/ 文件夹中,并使用 staticFile() 引用它们。对于动态数据(API 响应、数据库记录),使用 delayRender() / continueRender() 来暂停渲染,直到数据加载完毕。


核心概念

合成结构

每个 Remotion 项目都有一个注册合成的根文件:

import { Composition } from 'remotion';
import { MyVideo } from './MyVideo';

export const RemotionRoot: React.FC = () => {
  return (
    <Composition
      id="MyVideo"
      component={MyVideo}
      durationInFrames={150}
      fps={30}
      width={1920}
      height={1080}
    />
  );
};

基于帧的时序

Remotion 中的所有时序都以帧表示,而非秒。转换方式如下:

  • 秒到帧:秒 * fps
  • 帧到秒:帧 / fps

在 30fps 时,5 秒的视频对应 150 帧。第 0 帧是起始帧。

动画模型

Remotion 提供了两个核心动画原语:

原语用途示例
interpolate()从帧到值的线性/强制映射淡入、滑动、缩放
spring()基于物理的动画,带阻尼/质量弹跳入场、自然运动

两者都返回一个数值,你可以将其应用于样式(不透明度、变换等)。


常见任务

1. 搭建一个新的 Remotion 项目

npx create-video@latest

这将会创建一个包含 TypeScript、示例合成和配置好的 Remotion Studio 的项目。项目结构如下:

my-video/
  src/
    Root.tsx          # 注册所有合成
    MyComp.tsx        # 你的第一个合成组件
  public/             # 静态资产(图像、字体、音频)
  remotion.config.ts  # Remotion 配置
  package.json

使用以下命令启动预览工作室:

npx remotion studio

2. 使用 useCurrentFrame 创建一个基本合成

import { AbsoluteFill, useCurrentFrame, useVideoConfig, interpolate } from 'remotion';

export const FadeInText: React.FC = () => {
  const frame = useCurrentFrame();
  const { fps } = useVideoConfig();

  const opacity = interpolate(frame, [0, 30], [0, 1], {
    extrapolateRight: 'clamp',
  });

  const translateY = interpolate(frame, [0, 30], [20, 0], {
    extrapolateRight: 'clamp',
  });

  return (
    <AbsoluteFill
      style={{
        justifyContent: 'center',
        alignItems: 'center',
        backgroundColor: '#0f0f0f',
      }}
    >
      <h1
        style={{
          fontSize: 80,
          color: 'white',
          opacity,
          transform: `translateY(${translateY}px)`,
        }}
      >
        Hello Remotion
      </h1>
    </AbsoluteFill>
  );
};

3. 逐字动画文本

将文本拆分为单词,并使用 <Sequence> 交错显示每个单词:

import { AbsoluteFill, Sequence, useCurrentFrame, interpolate } from 'remotion';

const AnimatedWord: React.FC<{ children: string }> = ({ children }) => {
  const frame = useCurrentFrame();
  const opacity = interpolate(frame, [0, 15], [0, 1], {
    extrapolateRight: 'clamp',
  });
  const translateY = interpolate(frame, [0, 15], [10, 0], {
    extrapolateRight: 'clamp',
  });

  return (
    <span
      style={{
        display: 'inline-block',
        opacity,
        transform: `translateY(${translateY}px)`,
        marginRight: 12,
      }}
    >
      {children}
    </span>
  );
};

export const WordByWord: React.FC<{ text: string }> = ({ text }) => {
  const words = text.split(' ');

  return (
    <AbsoluteFill
      style={{
        justifyContent: 'center',
        alignItems: 'center',
        backgroundColor: '#1a1a2e',
        flexWrap: 'wrap',
        padding: 100,
      }}
    >
      {words.map((word, i) => (
        <Sequence key={i} from={i * 8}>
          <AnimatedWord>{word}</AnimatedWord>
        </Sequence>
      ))}
    </AbsoluteFill>
  );
};

4. 使用 spring 进行元素动画

使用 spring() 创建自然流畅的基于物理的动画:

import { AbsoluteFill, useCurrentFrame, useVideoConfig, spring } from 'remotion';

export const SpringCard: React.FC = () => {
  const frame = useCurrentFrame();
  const { fps } = useVideoConfig();

  const scale = spring({
    frame,
    fps,
    config: { damping: 200, stiffness: 100, mass: 0.5 },
  });

  const slideUp = spring({
    frame: frame - 10,
    fps,
    config: { damping: 12, stiffness: 100 },
  });

  return (
    <AbsoluteFill style={{ justifyContent: 'center', alignItems: 'center', backgroundColor: '#0d1117' }}>
      <div
        style={{
          width: 400,
          height: 250,
          backgroundColor: '#161b22',
          borderRadius: 16,
          transform: `scale(${scale}) translateY(${(1 - slideUp) * 50}px)`,
        }}
      >
        <p style={{ color: 'white', fontSize: 32 }}>Spring Animation</p>
      </div>
    </AbsoluteFill>
  );
};

5. 使用 Sequence 和 Series 进行场景过渡

使用 <Sequence> 处理重叠场景,使用 <Series> 处理顺序播放:

import { AbsoluteFill, Sequence, Series, useCurrentFrame, interpolate } from 'remotion';

const Scene: React.FC<{ color: string; title: string }> = ({ color, title }) => {
  const frame = useCurrentFrame();
  const opacity = interpolate(frame, [0, 20], [0, 1], {
    extrapolateRight: 'clamp',
  });

  return (
    <AbsoluteFill style={{ backgroundColor: color, justifyContent: 'center', alignItems: 'center' }}>
      <h1 style={{ color: 'white', fontSize: 72, opacity }}>{title}</h1>
    </AbsoluteFill>
  );
};

export const MultiScene: React.FC = () => {
  return (
    <AbsoluteFill>
      <Series>
        <Series.Sequence durationInFrames={60}>
          <Scene color="#e63946" title="Scene One" />
        </Series.Sequence>
        <Series.Sequence durationInFrames={60}>
          <Scene color="#457b9d" title="Scene Two" />
        </Series.Sequence>
        <Series.Sequence durationInFrames={60}>
          <Scene color="#2a9d8f" title="Scene Three" />
        </Series.Sequence>
      </Series>
    </AbsoluteFill>
  );
};

6. 资产处理(图像、字体、staticFile)

使用 staticFile() 引用 public/ 文件夹中的静态资产:

import { AbsoluteFill, Img, staticFile } from 'remotion';

export const AssetDemo: React.FC = () => {
  return (
    <AbsoluteFill style={{ justifyContent: 'center', alignItems: 'center' }}>
      <Img
        src={staticFile('logo.png')}
        style={{ width: 300, height: 300 }}
      />
    </AbsoluteFill>
  );
};

使用 @remotion/google-fonts 或 CSS @font-face 加载自定义字体:

import { loadFont } from '@remotion/google-fonts/Inter';

const { fontFamily } = loadFont();

export const FontDemo: React.FC = () => {
  return (
    <AbsoluteFill style={{ justifyContent: 'center', alignItems: 'center' }}>
      <h1 style={{ fontFamily, fontSize: 64, color: 'white' }}>
        Custom Font
      </h1>
    </AbsoluteFill>
  );
};

7. 音频集成

添加带音量控制和时序的音频:

import { AbsoluteFill, Audio, Sequence, staticFile, interpolate } from 'remotion';

export const WithAudio: React.FC = () => {
  return (
    <AbsoluteFill style={{ backgroundColor: '#000' }}>
      <Audio
        src={staticFile('background-music.mp3')}
        volume={(f) =>
          interpolate(f, [0, 30, 120, 150], [0, 0.8, 0.8, 0], {
            extrapolateLeft: 'clamp',
            extrapolateRight: 'clamp',
          })
        }
      />
      <Sequence from={15}>
        <Audio src={staticFile('whoosh.mp3')} volume={0.5} />
      </Sequence>
    </AbsoluteFill>
  );
};

8. 渲染视频

从命令行渲染为 MP4:

# 渲染默认合成
npx remotion render src/index.ts MyVideo out/video.mp4

# 以 4K 分辨率渲染
npx remotion render src/index.ts MyVideo out/video.mp4 --width 3840 --height 2160

# 渲染为 WebM
npx remotion render src/index.ts MyVideo out/video.webm --codec vp8

# 渲染特定帧范围
npx remotion render src/index.ts MyVideo out/video.mp4 --frames 0-90

# 使用自定义属性渲染
npx remotion render src/index.ts MyVideo out/video.mp4 --props '{"title": "Hello"}'

关于程序化渲染,请参阅 references/rendering-guide.md。


反模式 / 常见错误

错误错误原因正确做法
使用 Math.random() 而未带种子在渲染过程中每帧产生不同输出使用确定性种子或 Remotion 的 random()
使用 setTimeout / setInterval破坏基于帧的渲染——定时器不会按帧推进使用 useCurrentFrame() 和帧计算处理所有时序
缺少 extrapolateRight: 'clamp'值在后续帧上超出目标范围始终在 interpolate() 中添加 { extrapolateRight: 'clamp' }
在帧计算中硬编码 fps当合成 fps 更改时失效使用 useVideoConfig().fps 推导时序
使用 <Video> 进行渲染输出由于寻轨开销导致渲染性能降低使用 <OffthreadVideo> 获得更好的渲染性能
忘记为异步数据使用 delayRender()在数据加载前渲染,显示空/损坏的帧立即调用 delayRender(),数据就绪时调用 continueRender()
使用非确定性值的内联样式预览和渲染之间出现闪烁或不一致仅从帧编号推导所有样式值
庞大的单一合成难以维护,且无法独立渲染场景拆分为多个合成或使用 Series 处理场景

注意事项

  1. extrapolateRight 默认值为 'extend' - 如果你编写 interpolate(frame, [0, 30], [0, 1]) 而没有进行强制限制,该值在第 30 帧之后将持续增加(例如,第 60 帧时透明度为 2)。除非你故意需要外推,否则始终传递 { extrapolateRight: 'clamp' }。

  2. spring() 从其上下文的第 0 帧开始 - 当在 <Sequence from={60}> 内部使用 spring() 时,传递给 spring 的帧会在父级的第 60 帧处重置为 0。如果你传递父级的原始帧,动画将已经完成。请在 Sequence 子级内部使用 useCurrentFrame(),而不是使用来自父级的帧。

  3. staticFile() 路径相对于 public/ - 调用 staticFile('images/logo.png') 会查找 public/images/logo.png。使用绝对路径或 public/ 外部的路径将在预览中静默失败,并在渲染期间报错。确保所有资产都在 public/ 目录中。

  4. delayRender 有 30 秒超时 - 如果你的异步操作(API 调用、字体加载)耗时超过 30 秒,渲染将中止。对于慢速操作,请使用 delayRender('Loading data', { timeoutInMilliseconds: 60000 }) 增加超时时间。

  5. 合成尺寸必须为偶数 - 视频编解码器(H.264、VP8)需要偶数宽度和高度。如果你传递奇数值,Remotion 会抛出错误。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

相关技能