Communitygithub.com

yuv-video-director

YUV.AI 视频管道指挥家。将脚本转换为品牌化 MP4,协调 HyperFrames、Lottie、ManimCE 引擎,并自动验证渲染。

yuv-video-director 是什么?

yuv-video-director 是 YUV.AI 视频制作管道的核心编排器,旨在将任何创意或脚本转化为具有品牌标识的 MP4 视频。它作为一个智能路由器,分析叙事需求并为每个“节拍”分配最佳渲染引擎:利用 HyperFrames 进行确定性 HTML→视频渲染(通过无头 Chrome 逐帧 seek + FFmpeg),Lottie 用于品牌动图,ManimCE 用于数学/神经网络/概念动画,以及 GSAP 用于文本和过渡。该技能强制执行“YUV.AI Neon Phoenix”品牌准则(粉色 #FF1464、青色 #00E5FF、Anton+Inter 字体),并通过 frame.md 规范进行视觉统一。它支持横向 (16:9) 和纵向 (9:16) 格式,适用于短片、预告片、讲解视频和教程。关键工作流程包括:规划节拍、预渲染 Manim 和字幕资产、在 HyperFrames 中编写多引擎 index.html、通过 linting 和帧抽查进行自我验证,最后渲染 MP4。该技能捆绑了参考实现,包括可 seek 的神经网络背景生成器、品牌 Lottie 文件、Manim 场景模板和内容 Lottie 生成器,使其成为构建复杂动画视频的完整解决方案。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/hoodini/ai-agents-skills/tree/HEAD/skills/yuv-video-director

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

yuv-video-director 是做什么的?

YUV.AI 视频的指挥家。你(智能体)决定每个节拍需要什么,将其路由到正确的引擎,将一切组合成一个 HyperFrames 合成,包裹上 YUV.AI Neon Phoenix 品牌,自我验证,然后渲染成 MP4。本技能是路由器 + 工作参考实现;仅当引擎参与时才加载其参考文件。

设计源头: yuv-design-system 技能(Neon 模式 — 粉色 #FF1464,青色 #00E5FF,深黑/白,Anton+Inter+JetBrains Mono,神经网络凤凰主题)。视频形式是 frame.md — 参见 references/frame-md.md。捆绑模板:assets/FRAME.md。将其放入项目根目录;HyperFrames 会读取它。

唯一法则(决定一切)

HyperFrames 的渲染方式是在每个帧中通过无头 Chrome → FFmpeg 进行 seek(frameIndex = floor(t·fps),相同输入 → 相同输出)。因此每个视觉效果属于以下两种之一:

模式运行方式…引擎规则
实时可 seek 适配器在渲染内部运行,每帧驱动到时间 tGSAP、Lottie (window.__hfLottie)、Three.js、由 GSAP 代理 onUpdate 驱动的 canvas必须是时钟驱动 — 不使用 Date.now()、Math.random()(种子化 mulberry32)、setTimeout 或 .play()
预渲染资产离线运行,输出文件,作为片段导入ManimCE (Python→MP4/alpha)、TTS 音频、背景移除先渲染,然后作为 <video>/资产片段放入

如果可以 seek,则是适配器。如果不能,则预渲染。 Manim 始终是预渲染片段 — 它有自己的渲染器并在 Python 中运行;永远不能成为实时适配器。

将每个节拍路由到引擎

"将 X 解释为预告片/宣传片(FOMO,悬念,快节奏)" → references/teaser-explainer.md(公式)
"解释概念 / 数学 / 神经网络 / 算法 / 训练" → ManimCE(预渲染片段 — 为预告片切成 BURSTS)
"品牌动图:logo 片头 · 数据揭示 · 图标弹出 · 脉冲" → Lottie(实时,lottie-web)
"动态字幕 · 标题 · 揭示 · 过渡 · 数据标注" → GSAP(实时)← 默认
"3D / 空间" → Three.js(实时)(不使用 Babylon)
语音 → 字幕 → transcribe + approve 网页应用(参见 video-edit 技能)
未提供配音 → TTS(Kokoro:npx hyperframes tts)
品牌颜色 / 字体 / 主题 → frame.md(前端获取)

GSAP 是文本/动效的可靠默认值。对于设计的品牌图形使用 Lottie,对于解释想法使用 Manim。

工作流程

  1. 规划节拍。 叙事弧线 + 每个节拍所需的引擎。选择 16:9 和/或 9:16。
  2. 设置品牌。 确保 FRAME.md 在项目根目录(复制 assets/FRAME.md)。所有颜色/字体/主题来自它 — 绝不发明。每个视频中的三个品牌必备项(参见 references/brand-kit.md + references/cinematic.md):真正的凤凰标志(assets/logo-phoenix.png)在揭示处和结束卡,一个真正的特色 Lottie(生成一个 — assets/lottie-burst-generator.py),以及链接结束卡(标志 + "LET'S FLY HIGH" + 完整链接集 + CTA)。关于预告片/社交节奏参见 references/editing.md;关于心理/悬念/FOMO 剪辑参见 references/cinematic.md。
  3. 首先预渲染资产节拍(以便它们作为片段存在):
    • Manim → references/manim.md + assets/manim-scene-template.py。运行 py -m manim render -qh --fps 30 scene.py SceneName,将 MP4 复制到 assets/。
    • 字幕/TTS → 重用 video-edit 技能(transcribe → approve 网页应用 → 同步)和 npx hyperframes tts。
  4. 脚手架 + 合成。 npx hyperframes init <slug> --non-interactive。编写 index.html(hyperframes 技能是合约)。使用:
    • 可 seek 的神经网络场背景 → assets/neural-net-field.js
    • 品牌方式的 Lottie → references/lottie.md + assets/neural-pulse.json
    • Manim 渲染作为 <video class="clip" muted playsinline> 主体片段
    • 每个场景的 GSAP 入场,每个边界上的霓虹 闪光 过渡,仅在最终场景淡出
    • 对于预告片 / 社交节奏(快速硬切、动态文字猛击、钩子蒙太奇、故障/色度刺击)→ references/editing.md — 像制作人一样剪辑,而不是幻灯片
  5. 自我验证(关卡)。 references/gates.md:npx hyperframes lint(0 错误) → validate(0 控制台错误,WCAG AA) → 渲染 → 在时间线上抽查 5 帧。修复 → 重新运行。Lottie 必须经过截图验证(Skottie-vs-lottie-web 陷阱)。
  6. 渲染。 npx hyperframes render --fps 30 --output renders/<name>_FINAL.mp4。对于竖屏,使用 1080×1920 布局克隆(参见 video-edit)。

先决条件(首先检查;优雅降级)

参见 references/prereqs.md。需要 Node 22+、FFmpeg、Python 3.11+ with pip(Manim/字幕)。此机器上:真正的 Python 是 py → C:\Python313(裸 python 是 Hermes 的 venv,没有 pip — 不要使用它)。ManimCE 通过 py -m pip install manim 安装(如果您使用 Text()/MarkupText 而不是 Tex/MathTex 创作,则不需要 LaTeX)。如果 Manim 不可用 → 跳过数学节拍或提供安装;永远不要硬失败整个视频。

本技能捆绑的内容(通过 lint + 渲染的参考实现)

文件内容
assets/FRAME.mdYUV.AI Neon Phoenix 视频帧规范(基于 HeyGen 的 Coral 包重新品牌化)
assets/neural-net-field.js确定性、可 seek 的神经网络凤凰 canvas 背景
assets/neural-pulse.json手动编写的 Bodymovin Lottie(在 lottie-web 中渲染,而不仅仅是 Skottie)
assets/gen_content_lotties.py6 个生产级 CONTENT Lottie 的生成器(WhatsApp 折叠、解码光束、眼睛阅读、幽灵线英雄、球体提取、脑火)— 透明、持久+连续、经过 lottie-web 验证
assets/{wa-collapse,decode-beam,eye-read,ghost-line,orb-extract,brain-fire}.json生成的 6 个内容 Lottie,可直接使用
assets/manim-scene-template.pyManimCE 场景模板,霓虹品牌样式,仅文本(无 LaTeX)
assets/what_is_nn.py"什么是神经网络" ManimCE 场景(神经元 → 网络 → 训练,34.5 秒)
assets/Anton-Regular.woff2本地 Anton(渲染器不会自动解析;声明 @font-face)
references/composition-pattern.md完整的多引擎 index.html 模式(场 + Lottie + Manim 片段 + GSAP + 闪光)
references/teaser-explainer.md电影预告片讲解公式:冷开场猛击 → manim BURSTS → 面对面 → FOMO 蒙太奇 → 悬念;内容同步透明 Lottie 节拍;seek-modulo 修复;预告片音乐合成

配套技能

hyperframes(合成合约 — 编写时始终调用)、hyperframes-cli、lottie、video-edit(字幕 + approve 网页应用)、yuv-design-system(品牌)。本技能协调它们。

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

hoodini/ai-agents-skills

Edit any selfie or screen-share footage into a viral short-form video in YUV.AI's signature style — Apple-style liquid-glass cards (real CSS backdrop-filter), dark-mode polish, MrBeast-paced cuts, video-title karaoke captions, premium GSAP motion graphics, no fake content, never covering the speaker's face. Hebrew is rendered in Rubik Black, English in Anton uppercase. Always renders BOTH 9:16 and 16:9 and always saves with _V<N> suffix for backups. Trigger when the user drops a path to an .mp4/.mov/.mkv and says "edit this", "make it viral", "turn this into a short", or any Hebrew equivalent (ערוך סרטון, סרטון ויראלי, להפוך לוויראלי, ריל, שורט). The pipeline is the COMBINATION of two skills: video-use (transcription + word-snapped cuts + base extraction) and hyperframes (HTML/CSS/GSAP visual composition + render). Do NOT use for podcast-only audio edits.

hoodini/ai-agents-skills

Turn any video into a cinematic scroll-driven landing page — Apple-style hero where scrolling progresses the visible frame through the video. Use when the user provides a video file and asks for "a landing page from this video", "scroll-frame website", "Apple-style scroll site", "hero that scrubs the video", "like the GitHub Copilot landing", or any equivalent. Extracts N evenly-spaced frames via ffmpeg, builds a self-contained HTML page with a sticky hero + JS scroll listener that swaps the visible frame as you scroll, plus headline, sections and CTA below. For YUV.AI projects, applies the yuv-design-system skill in Neon mode (pink/cyan/white, default for YUV.AI web) — Decks (purple/yellow) is reserved for slides only. For generic / non-YUV.AI projects, picks an appropriate palette per the source video. Output is one folder with `index.html` and a `frames/` directory — drop on any static host.

hoodini/ai-agents-skills

Yuval Avidani's YUV.AI brand and design system. Apply ONLY when YUV.AI-branded output is requested — presentations, decks, keynotes, portfolio, brand site, profile, speaker bio, brand assets, or any prompt mentioning YUV.AI / "my brand" / "my deck" / "my site" / "for me". Do NOT auto-trigger on generic "build a game / web app / dashboard / landing page" without YUV.AI context — those use whatever palette fits. Three modes; NEON (hot pink #FF1464 + neon cyan #00E5FF + white, DEFAULT for YUV.AI web, apps, games, dashboards, social, general visual work); DECKS (Fly High purple/yellow/grey, presentations and slides ONLY); Warm Editorial (pink/yellow/bone for Hope, Marcus, bigcats.ai, practical.yuv.ai). Universal Fly High throughline across all modes; flight/progress motifs (HUD strips, dials, "Let's Fly High" tagline, phoenix mark). Anton + Inter (EN), Rubik + Assistant (HE), letter-spacing 0 default. Bundled brand assets, canonical socials, credentials. Project brand wins if specified.

hoodini/ai-agents-skills

Build a premium cinematic landing page with mouse-scrub video hero and brand-driven narrative-arc sections. Use whenever the user provides a hero video plus a product / subject / brand and wants a landing page, promo site, product showcase, marketing page, or storytelling site. Works for any language (RTL or LTR — Hebrew, English, Arabic, Spanish, French, Japanese, etc.) and any subject (food, tech, animals, fashion, services, SaaS, wildlife campaigns, music releases, books, real estate). The signature effect is mouse-driven video scrubbing — the hero video lives across the entire page as a fixed backdrop, and moving the mouse left-right scrubs the video timeline so the subject responds to the cursor. Below the hero, 4-5 fully-opaque sections each carry their own brand identity (color, typography emphasis, layout pattern) and walk the viewer through a narrative arc (e.g. longing → joy → nostalgia → contemplation → action). Triggers on phrases like "build a landing page from this video", "cinematic landing ...

hoodini/ai-agents-skills

Build a scroll-driven cinematic landing page from a short video. The user provides a 5–15 second video (often AI-generated); this skill extracts every frame at HD JPEG quality, then produces a single-hero HTML page where the user's scroll gesture scrubs the frames in place (the page itself never scrolls) and 5 dramatic text overlays crossfade in/out — Google Anton headlines, Caveat handwritten accents, locked body, virtual scroll. Use this skill whenever the user wants to "turn this video into a landing page", "make a scroll-scrub landing page", "build a parallax hero from this clip", "add a new landing page to the parasites showcase", "do the same as github/lion/hope for this new video", or any variant that pairs a short clip with dramatic scroll-triggered storytelling. Trigger even if the user only says "use my video for a landing page" — that is this skill.

hoodini/ai-agents-skills

Edit any video into a captioned showcase — transcribe (any language, defaults to large-v3), present a transcript_review.txt for the user to fix mishears BEFORE rendering, then build a HyperFrames composition with liquid-glass caption pills, liquid blob background, liquid morph wipes, optional behind-subject text via background removal, and render the final video. Use whenever the user provides a video file and asks to edit it, caption it, add subtitles, fix existing captions, make a reel/promo/captioned tutorial, or "do the same" pattern as a prior captioned video. Supports English, Hebrew, and any Whisper-supported language. **Renders both 16:9 (YouTube / horizontal) and 9:16 (TikTok / Instagram Reels / YouTube Shorts) from the SAME 16:9 source** — vertical mode uses a centered footage strip with a blurred backdrop + liquid blobs and a vertical-tuned caption pill, no need to re-shoot. THE PIPELINE PAUSES FOR USER APPROVAL on the transcript before final render — this is the support mechanism for getting ca...

hoodini/github-trending

Fetch and display GitHub trending repositories and developers. Use when building dashboards showing trending repos, discovering popular projects, or tracking GitHub trends. Triggers on GitHub trending, trending repos, popular repositories, GitHub discover.

hoodini/mongodb

Work with MongoDB databases using best practices. Use when designing schemas, writing queries, building aggregation pipelines, or optimizing performance. Triggers on MongoDB, Mongoose, NoSQL, aggregation pipeline, document database, MongoDB Atlas.

hoodini/owasp-security

Implement secure coding practices following OWASP Top 10. Use when preventing security vulnerabilities, implementing authentication, securing APIs, or conducting security reviews. Triggers on OWASP, security, XSS, SQL injection, CSRF, authentication security, secure coding, vulnerability.

相关技能