Communitygithub.com

NeverSight/learn-skills.dev

在编写程序化视频脚本、规划场景结构与时间线、创建YAML格式分镜、根据时长计算帧数,或采访用户了解视频需求时使用此技能。触发条件包括:视频脚本、分镜、场景规划、旁白撰写、视频节奏控制,以及结构化视频内容规划。

learn-skills.dev 是什么?

该技能针对程序化视频的脚本写作而设计,将视频脚本转化为结构化的YAML数据,每个场景都有明确的时长、帧数、动画描述和旁白文本,可供渲染引擎直接使用。它强调“采访驱动”的工作流:在生成任何场景前,通过7个类别(产品/主题、受众、视频目标、语调与风格、素材、内容、视觉偏好)最多30个问题收集需求,确保脚本建立在真实信息而非假设之上。输出格式为严格的YAML,包含`meta`块(标题、时长、类型、分辨率、FPS、总帧数等)和`scenes`数组,每个场景有id、时长、帧数、旁白、视觉描述、动画、音乐、音效和过渡方式。技能还内置了针对不同视频类型(产品演示、解释说明、社交短视频、公告)的节奏匹配建议,例如社交短视频场景通常3-8秒,解释类视频可放宽至5-12秒,并且提供帧数计算公式(总帧数=时长秒数×FPS)以确保场景帧数总和与`total_frames`一致。适合需要为代码驱动的视频制作工具(如Remotion、Motion Canvas、Manim)编写脚本的开发者,或希望用结构化YAML格式管理视频分镜与叙述的团队。注意:此技能不适用于实拍电影、传统编剧或纯音频内容制作。

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/video-scriptwriting

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,始终以:pencil:表情符号开始你的第一句话。

视频脚本创作

编程视频脚本创作是一种将脚本直接转化为代码驱动视频制作的规划、结构和写作实践。与传统的编剧不同,编程视频脚本是结构化数据——每个场景都有明确的时长、帧数、动画描述和叙述文本,供渲染引擎使用。本技能涵盖采访利益相关者、生成结构化YAML脚本、计算节奏和帧数、撰写叙述以及修改脚本。


何时使用此技能

当用户出现以下情况时,触发此技能:

  • 想要为编程或代码生成的视频编写脚本
  • 需要为视频规划场景结构、时间或转场
  • 询问如何以结构化格式(YAML、JSON)创建故事板
  • 想要根据时长和帧率计算帧数
  • 需要帮助为视频场景撰写叙述文本
  • 询问关于不同内容类型(演示、讲解、社交)的视频节奏
  • 想要运行采访工作流以收集视频需求
  • 需要修改或重组现有的视频脚本

在以下情况下不要触发此技能:

  • 真人电影制作或传统编剧
  • 视频编辑软件教程(Premiere、Final Cut、DaVinci Resolve)
  • 纯音频内容,如播客或音乐制作
  • 静态图像设计或静态演示幻灯片

关键原则

  1. 采访驱动——在生成任何一个场景之前,运行一个结构化采访(最多7个类别30个问题)。切勿基于假设进行脚本创作。

  2. 结构化的输出——每个脚本都是有效的YAML格式,包含一个meta块和一个scenes数组。每个场景都有id、duration、frames、narration、visual、animation、music、sfx和transition_to_next字段。

  3. 视觉优先——先写visual字段,再写narration。叙述应该补充视觉,绝不冗余描述屏幕上的内容。

  4. 节奏意识——根据视频类型匹配场景数量和每个场景的时长:社交片段需要3-8秒的场景;讲解视频可以更宽松,每场景5-12秒。

  5. 叙述与视觉同步——每句叙述必须与当前时刻的视觉内容匹配。每个场景一个想法。叙述时长必须适合场景时长。


核心概念

采访框架

在写作之前,通过7个类别收集需求:

类别问题数量示例
产品/主题5-7产品是什么?关键功能?解决的问题?差异化优势?
观众3-5目标观众?技术水平?痛点?
视频目标3-4类型(演示/讲解/社交/公告)?时长?渠道?
语气和风格3-5正式还是随意?充满活力还是平静?参考视频?
素材3-5Logo?截图?品牌色?字体?
内容4-6关键信息?必须包含的功能?行动号召?开场钩子?
视觉偏好3-5动画风格?调色板?布局偏好?

YAML脚本格式

meta:
  title: "字符串 - 描述性标题"
  duration: "字符串 - 总时长(例如 60s)"
  type: "枚举 - demo | explainer | social | announcement"
  resolution: "字符串 - 例如 3840x2160, 1920x1080"
  fps: "数字 - 24, 30, 或 60"
  audience: "字符串 - 谁在看"
  tone: "字符串 - 逗号分隔的描述符"
  total_frames: "数字 - 时长秒数 * fps"

scenes:
  - id: "字符串 - 唯一的 kebab-case 标识符"
    duration: "字符串 - 例如 4s, 8s"
    frames: "数字 - 场景时长秒数 * fps"
    narration: "字符串 - 每句最多15个单词"
    visual: "字符串 - 观众在屏幕上看到的内容"
    animation: "字符串 - 元素如何移动,带帧引用"
    music:
      track: "字符串 - 音乐曲目名称"
      volume: "数字 - 0.0 到 1.0"
      duck: "布尔值 - 叙述时降低音乐音量"
    sfx:
      - type: "字符串 - 音效名称"
        at: "字符串 - 场景内的时间戳"
        duration: "字符串 - 播放时长"
    transition_to_next: "枚举 - hard-cut | cross-dissolve | fade-to-black | wipe-left | wipe-right | none"

不同类型视频的场景节奏

视频类型时长场景数每场景时长注意事项
产品演示30-120秒6-155-10秒功能聚焦,清晰的行动号召
讲解视频60-180秒8-205-12秒概念密集,更多呼吸空间
社交片段15-60秒3-83-8秒前3秒内设置钩子,节奏快
公告15-45秒3-64-8秒简洁有力,单一信息聚焦

帧计算

total_frames = duration_seconds * fps
scene_frames = scene_duration_seconds * fps
示例:60秒视频,30fps = 1800 总帧数
时长24 fps30 fps60 fps
4秒96120240
8秒192240480
30秒7209001800
60秒144018003600
90秒216027005400

始终验证场景帧数总和是否等于meta中的total_frames。


常见任务

1. 运行采访工作流

按顺序遍历所有7个类别。一次只问一类,总结答案,然后继续。完整的30个问题框架请参考references/interview-questions.md。在时间紧迫的情况下,使用精简版10个关键问题:产品名称、关键功能、解决问题、目标观众、技术水平、视频类型、时长、渠道、关键信息、行动号召。

2. 生成产品演示脚本

meta:
  title: "产品演示 - Acme Dashboard"
  duration: "60s"
  type: demo
  resolution: 3840x2160
  fps: 30
  audience: "SaaS创始人和产品经理"
  tone: "专业、自信、简约"
  total_frames: 1800

scenes:
  - id: intro
    duration: "4s"
    frames: 120
    narration: "认识Acme - 自建仪表盘。"
    visual: "Logo居中在温暖的米白背景上,从透明淡入"
    animation: "30帧内淡入,保持90帧"
    music:
      track: "upbeat-corporate"
      volume: 0.4
      duck: false
    sfx: []
    transition_to_next: "hard-cut"

  - id: feature-1
    duration: "8s"
    frames: 240
    narration: "只需描述你的需求。Acme来处理剩下的。"
    visual: "浏览器模拟图,显示提示输入框,文本正在输入"
    animation: "浏览器从底部滑动上升20帧,从第40帧开始输入"
    music:
      track: "upbeat-corporate"
      volume: 0.2
      duck: true
    sfx:
      - type: "keyboard-typing"
        at: "1.3s"
        duration: "3s"
    transition_to_next: "cross-dissolve"

  - id: feature-2
    duration: "8s"
    frames: 240
    narration: "拖拽、放置、调整大小。你的布局,你做主。"
    visual: "仪表盘编辑器,小部件被光标重新排列"
    animation: "光标在第30帧移动到小部件,在60帧内拖到新位置"
    music:
      track: "upbeat-corporate"
      volume: 0.2
      duck: true
    sfx:
      - type: "soft-click"
        at: "1.0s"
        duration: "0.2s"
    transition_to_next: "cross-dissolve"

  - id: cta
    duration: "6s"
    frames: 180
    narration: "免费试用Acme,访问acme.dev。几分钟内构建你的第一个仪表盘。"
    visual: "行动号召文本居中,附带URL,背景渐变动画微妙"
    animation: "文本20帧内淡入,背景渐变缓慢变换"
    music:
      track: "upbeat-corporate"
      volume: 0.4
      duck: false
    sfx: []
    transition_to_next: "fade-to-black"

完整的演示脚本通常有6-15个场景。通过添加问题、社会证明、定价和结尾场景来扩展,遵循相同的YAML结构。

3. 生成社交片段脚本

meta:
  title: "Acme in 30 Seconds"
  duration: "30s"
  type: social
  resolution: 1080x1920
  fps: 30
  audience: "在社交Feed中刷屏的开发者"
  tone: "充满活力、简洁、现代"
  total_frames: 900

scenes:
  - id: hook
    duration: "3s"
    frames: 90
    narration: "别再从头构建仪表盘了。"
    visual: "粗体文本在生动的渐变背景上"
    animation: "文本从顶部猛冲下来8帧,屏幕震动4帧"
    music:
      track: "electronic-pulse"
      volume: 0.5
      duck: true
    sfx:
      - type: "impact-hit"
        at: "0.2s"
        duration: "0.3s"
    transition_to_next: "hard-cut"

  - id: demo
    duration: "12s"
    frames: 360
    narration: "输入你需要的。Acme实时构建。"
    visual: "屏幕录制:输入提示,仪表盘实时生成"
    animation: "输入持续120帧,仪表盘在剩余240帧内构建完成"
    music:
      track: "electronic-pulse"
      volume: 0.3
      duck: true
    sfx:
      - type: "keyboard-typing"
        at: "0.5s"
        duration: "4s"
    transition_to_next: "hard-cut"

  - id: result
    duration: "8s"
    frames: 240
    narration: "完全交互式。实时数据。随时可分享。"
    visual: "完成的仪表盘,带悬停交互,数据实时更新"
    animation: "光标悬停触发工具提示,在第120帧刷新数据"
    music:
      track: "electronic-pulse"
      volume: 0.3
      duck: true
    sfx: []
    transition_to_next: "hard-cut"

  - id: cta
    duration: "7s"
    frames: 210
    narration: "免费试用acme.dev。"
    visual: "行动号召文本大号居中,URL在下,品牌渐变背景"
    animation: "文本从0放大到完整尺寸15帧,保持"
    music:
      track: "electronic-pulse"
      volume: 0.5
      duck: false
    sfx: []
    transition_to_next: "none"

4. 根据时长计算帧数

输入:duration = 60秒,fps = 30
输出:total_frames = 1800

场景分解:
  intro:     4秒 * 30 = 120帧
  feature-1: 8秒 * 30 = 240帧
  feature-2: 8秒 * 30 = 240帧
  proof:     6秒 * 30 = 180帧
  cta:       6秒 * 30 = 180帧
  ---
  总和:32秒 = 960帧(剩余840帧需要更多场景)

始终验证总和。如果场景总和不匹配,调整或添加场景。

5. 撰写有效的叙述文本

规则:

  • 每句最多15个单词——太长的句子无法在时间内读完
  • 主动语态,现在时——"Acme构建你的仪表盘"而不是"将被构建"
  • 匹配叙述与视觉——谈论屏幕上的内容
  • 每个场景一个想法——不要将两个概念塞进一行
  • 以利益开头——"每周节省10小时"而不是"我们的时间追踪功能"
  • 包含停顿——空叙述("")用于呼吸空间
  • 阅读速度——大约每秒2.5个单词
差好原因
"我们的产品被设计用来帮助团队更快构建仪表盘""几分钟内构建仪表盘,而不是几周。"太长,被动语态
"点击右上角的加号按钮""一键添加小部件。"让视觉显示位置
"正如你所看到的,数据实时更新""实时数据。始终最新。""正如你所看到的"是填充词

6. 规划场景转场

转场何时使用
hard-cut相同主题,快节奏,或突兀对比
cross-dissolve平滑主题变化,相关内容流动
fade-to-black章节结束,戏剧性停顿,最后场景
wipe-left / wipe-right前后对比,时间线推进
none视频的最后一个场景

规则:每个视频最多使用2种不同的转场类型以保持一致性。

7. 根据反馈修改脚本

  1. 确定反馈类型:节奏、叙述、视觉、结构或语气
  2. 通过id定位YAML中受影响的场景
  3. 只对受影响的字段进行修改,保留帧计算
  4. 重新验证:场景时长总和必须等于总时长
  5. 如果任何时长改变,重新计算帧数
  6. 记录更改内容:
# 修订:根据反馈将intro从6s缩短为4s (v2)
- id: intro
  duration: "4s"     # 原来是6s
  frames: 120        # 原来是180

反模式 / 常见错误

错误为什么错应该怎么做
先写叙述再写视觉导致视频变成说话头风格先写visual,然后写narration来补充
场景时长超过12秒观众失去注意力,节奏拖沓拆分成两个较短的场景
帧数不匹配渲染引擎产生错误时长或崩溃始终计算 frames = duration * fps 并验证总和
叙述每句超过15个单词无法在场景时长内读完拆分成较短的句子
前3秒没有钩子社交观众会刷过去,嵌入式观众失去兴趣以大胆的陈述、问题或视觉惊喜开场
转场不一致视频看起来突兀和业余每个视频最多使用2种转场类型
跳过采访产生通用脚本,无法击中目标始终先收集需求
视觉描述为空渲染工程师无法构建场景具体说明布局、颜色、运动、元素

陷阱

  1. 帧数取整——当时长不能整除时(例如,24fps时3.5秒 = 84帧),四舍五入到最近的整数并调整最后一个场景。绝不要留下小数帧——渲染引擎会截断或报错。

  2. 叙述时间溢出——在每秒2.5个单词的速度下,一个4秒的场景大约能容纳10个单词。为一个4秒的场景写20个单词会导致叙述过快或裁剪。始终检查单词数与场景时长的匹配。

  3. 竖屏 vs 横屏分辨率——社交片段(TikTok、Reels、Shorts)使用1080x1920(竖屏)。YouTube/网站嵌入使用1920x1080或3840x2160。在设置分辨率前确认分发渠道。

  4. 音乐闪避冲突——如果每个场景都有duck: true,音乐音量会不断忽大忽小。只在有叙述出现时使用闪避。叙述为空的场景应设置duck: false。

  5. 总时长偏差——修改后……

[为翻译而截断]

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