Communitygithub.com

通用视频编排工作流(后备方案)

适用于创建任意时长或格式的自定义 HyperFrames 视频作品的后备工作流,包括长片、多场景作品、品牌/精选短片、蒙太奇、标题卡、静态循环以及自由格式作品。对输入内容和时长无限制。若存在专门的流程更适合输入内容(如营销产品、网站、主题解说、GitHub PR、现有素材、短动画或 Remotion 移植),请优先使用对应流程;此流程仅作为通用后备方案。

通用视频编排工作流(后备方案) 是什么?

这是一个面向 Claude Code 等 AI 代理的通用视频编排工作流技能。它作为创建自定义 HyperFrames 视频作品的后备方案,适用于任何没有专门对应流程的场景。该技能提供了从创意构思到最终构建的端到端指引,包括设计系统建立(颜色、字体、视觉概念)、多场景提示扩展、布局与动画分离的设计原则,以及音频集成。它通过严格的“硬门”检查确保输出质量,要求必须完成视觉身份定义、概念角度、字体选择和前景密度规划才能开始构建。该工作流支持多个专业化子技能(如媒体处理、动画特效、核心架构),并强调“先建布局、再添动画”的黄金法则,以避免布局冲突。最终输出通过 hyperframes-cli 进行渲染,并遵循明确的输出清单。

兼容平台~Claude Code~Codex CLI✓Cursor
npx skills add https://github.com/1345AbhishekKumar/starter-supabase/tree/HEAD/.agents/skills/general-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

media-use:在获取音频/图片之前,请先调用 /media-use 从 HeyGen 目录中解决 BGM/SFX/图片问题。首先运行 --adopt 以注册现有资源。详情请参阅 /media-use 技能。

general-video — 通用视频工作流

构建前请确认路线。 这是自定义作品编排的后备方案。如果输入内容明显符合某个专门工作流,请优先使用:营销产品 → /product-launch-video;通用网站 → /website-to-video;主题解说 → /faceless-explainer;GitHub PR → /pr-to-video;现有素材 → /embedded-captions · /talking-head-recut;短篇无旁白动画 → /motion-graphics;Remotion 移植 → /remotion-to-hyperframes。超出范围:实时/渲染时数据、对已完成视频进行非线性编辑,或制作 HyperFrames 无法捕获的素材。不确定?请先阅读 /hyperframes。

精确构建所要求的内容。 标题卡就是标题卡——不是标题卡加三个辅助场景加环境音乐加字幕。如果额外场景或元素确实能提升作品质量,请_提出_建议,但不要不经提议就擅自添加。对于小修改(修复颜色、调整一个时长、添加一个元素),跳过规划步骤直接构建。

方法

发现阶段 — 仅限开放式请求

对于模糊、探索性的请求(“为我们的品牌做点什么”、“来个酷炫的开场”)——在挑选颜色之前先理解意图:

  • 受众 — 谁观看?开发者/高管/普通消费者?
  • 平台 — 在哪里播放?社交媒体(15秒)/网站主视觉/产品演示/内部使用?
  • 优先级 — 什么最重要?动效质量/内容准确性/品牌一致性/速度?
  • 变体 — 仅需一个最佳版本,还是 2-3 个有意义的差异化选择(不同节奏、能量或结构——而不仅仅是颜色替换)?

对于具体请求(“添加一个标题卡”、“修正场景 3 的时序”),跳过发现阶段。

步骤 1 — 设计系统 → hyperframes-creative

首先建立视觉身份。如果项目有设计规范,请阅读它(优先级 frame.md → design.md → DESIGN.md;将其视为品牌真理——精确的颜色、字体、约束)。

如果没有规范,在选择任何颜色或字体之前,你必须同时阅读 hyperframes-creative/references/house-style.md 和 hyperframes-creative/references/video-composition.md。 house-style.md 提供了“解读提示 / 生成真实内容”的开场、惰性默认列表和图层配方;video-composition.md 提供了视频媒介的密度/比例/前景细节(数据条、注册标记、等宽字体元数据、“8-10 个元素,其中两个用户并未要求”),正是这些将“制作精良”的输出与“生成式”输出区分开来。只读一个是常见的错误——video-composition.md 正是代理跳过的那一个,也是避免产生扁平、居中、网页风格输出的关键。不要自行发明调色板并跳过这些;跨入 hyperframes-creative 是强制性的,而非可选分支。之后,根据需要从 references/visual-styles.md 中提取命名的风格/情绪,或使用交互式选择器 references/design-picker.md。规范/风格定义的是品牌,而非作品规则。

寻找角度(无规范的模糊概要): 在挑选颜色之前,先写一句话——这个名称/单词/主题唤起了什么,以及什么视觉_世界_(隐喻、设定、道具、动机)可以表达它?例如,网络安全工具 → 保险库门/周界扫描线/锁芯;冥想应用 → 潮汐、呼吸、柔和的光晕。阅读主题的_含义_,而不仅仅是字面;选择一个具体的角度而非字面的重新风格化。这是对单场景作品的提示扩展(第 2 步)的低成本替代方案,此时扩展被正确地跳过——它是设计概念与通用渐变徽标的区别。

<硬门> 在编写任何 HTML 之前,请验证你已具备所有四项:

  1. 视觉身份:基于规范或 house-style.md,而非临时发明。(使用了 #333、#3b82f6 或 Roboto?你跳过了这一步。)
  2. 一句话概念角度(“寻找角度”步骤):适用于任何超越琐碎编辑的工作——而非对提示词的字面重新风格化。
  3. 来自嵌入列表的字体配对(hyperframes-creative/references/typography.md → “可嵌入的字体”)——有目的地选择,而非默认使用 Inter/Helvetica Neue/system-ui,也绝不要使用未嵌入的显示字体并期望它能渲染(未打包的字体名仅当本地自动捕获时才嵌入——云端渲染不会捕获它们)。
  4. 来自 video-composition.md 的前景/密度规划:边缘锚定、8-10 个元素、前景元数据、背景纹理规则。(在一个纯色背景上居中堆叠少于约 6 个元素且无边缘锚定细节?你跳过了这一步——这就是通用风格的标志。) </硬门>

步骤 2 — 提示扩展 → hyperframes-creative

对每个多场景作品运行此步骤(对单场景作品和琐碎编辑跳过)。根据设计规范和 house style 将请求转化为一致的中间表示,确保下游工作以相同方式解读。详见 hyperframes-creative/references/prompt-expansion.md。

步骤 3 — 规划

在编写 HTML 之前,从高层次思考:

  1. 什么 — 观众体验:叙事弧线、关键时刻、情感节拍。
  2. 结构 — 多少个构图,子组件 vs 内联,哪些轨道承载视频/音频/叠加/字幕。关于单体单文件 vs 模块化子组件的选择,参见 hyperframes-core/references/composition-patterns.md § 两种架构(经验法则:≥3 个硬场景切换,或任何复用场景 → 模块化;短单场景作品保持一个文件)。
  3. 节奏 — 在实现之前先命名模式(例如 fast-fast-SLOW-SHADER-hold);参见 hyperframes-creative/references/beat-direction.md。
  4. 时序 — 哪些剪辑驱动时长,过渡落在何处,节奏。
  5. 布局 — 先构建最终状态(见下文)。
  6. 动画 — 然后通过 hyperframes-animation 添加动效。

先布局后动画

将每个元素放置在其最显眼时刻所在的位置——完全进入、正确放置、尚未退出。先将其编写为静态 HTML + CSS。暂时不要使用 GSAP。

原因: 如果你将元素定位在动画起始状态(屏幕外、缩放至 0、透明度 0)并通过补间动画移动到你认为的_最终位置_,你实际上是在猜测最终布局——重叠部分在渲染之前都会不可见。先构建最终状态,你可以在添加动效之前发现并修复布局问题。

  1. 为每个场景确定主帧——元素同时可见最多的时刻。那就是你需要构建的布局。
  2. 编写该帧的静态 CSS。内容容器必须使用内边距填充场景,而不是绝对偏移:
.scene-content {
  display: flex;
  flex-direction: column;
  justify-content: center;
  width: 100%;
  height: 100%;
  padding: 120px 160px; /* 内边距定位内容;可填充任何场景尺寸 */
  gap: 24px;
  box-sizing: border-box;
}

绝不要对内容容器使用 position: absolute; top: Npx——当内容高于空间时会发生溢出。将绝对定位保留给装饰性元素。

⚠ 上述 width/height: 100% 仅在每个祖先元素都具有已解析的高度时才生效。 根 <div data-composition-id> 及其与 .scene-content 之间的任何包装器都必须具有明确的尺寸(根元素上设置 position: relative; width: 1920px; height: 1080px——参见 hyperframes-core → “根必须具有尺寸”)。跳过此步骤会导致伸缩容器塌缩到约 0,内容堆积在左上角,第一个字符在 x=0 处被裁剪——而 lint/inspect 仍然报告 0 个问题。此外,始终在 .scene-content 上保留 padding(≥80px):这是标题安全边距。绝不要用裸 gap 替换它。

  1. 添加入场——使用 gsap.from() 从屏幕外/不可见动画到 CSS 位置(在子组件中优先使用 gsap.fromTo(),以便起始状态明确;参见 hyperframes-core/references/sub-compositions.md)。CSS 位置是事实基准;补间动画只是到达那里的旅程。
  2. 退出由过渡处理——根据 hyperframes-animation/transitions/ 中的场景过渡规则,只有最终场景将元素动画退出;场景之间的过渡本身就构成了退出。

跨时共享空间: 如果元素 A 在元素 B 进入同一区域之前退出,两者仍需要为其各自的主帧设置正确的 CSS 位置——时间线排序防止它们共存,而布局步骤则捕获意外重叠。分层发光/阴影和 z 堆叠深度是_有意的_重叠;此步骤的目的是捕获_无意的_碰撞(两个标题叠在一起、内容溢出帧外)。

构建 — 委派给领域技能

此表映射了技能的全部范围(参见 description)到其参考资料——并非详尽无遗;当意图未列出时,通过 hyperframes-creative(外观/概念)、hyperframes-animation(动效)、hyperframes-core(契约)、hyperframes-media(音频/字幕)进行路由。第一行是叠加的——请同时阅读它和你的意图行,而非只读一个。

构建…首先阅读(按顺序)
始终 — 每个非琐碎作品,除下方意图行外额外阅读hyperframes-creative/references/house-style.md + references/video-composition.md(同样在步骤 1 / 硬门中加以限制;关于“制作精良而非生成式”的前景细节)
动态文字 / 文字为主hyperframes-animation/techniques.md(动态类型)+ adapters/gsap-easing-and-stagger.md + rules/kinetic-beat-slam.md
标题卡 / 下三分之一 / 叠加 / 画中画 / 文字后置主体hyperframes-creative/references/composition-patterns.md +(关于居中/尺寸帧)hyperframes-core → “根必须具有尺寸”
徽标 / 品牌标记揭示hyperframes-animation/rules/svg-path-draw.md(绘制动画)+ rules/3d-text-depth-layers.md + rules/scale-swap-transition.md
数据 / 统计 / 数字hyperframes-animation/rules/counting-dynamic-scale.md + rules/stat-bars-and-fills.md + hyperframes-creative/references/data-in-motion.md
产品 / 应用 / UI 演示hyperframes-animation/rules/3d-page-scroll.md + rules/cursor-click-ripple.md + rules/press-release-spring.md
音频响应 / 音乐驱动hyperframes-creative/references/audio-reactive.md(预先提取频段;映射到动效)
旁白 / 画外音 / 音乐 / 音效 / 字幕hyperframes-media → 共享音频引擎 scripts/audio.mjs(一次调用 = TTS + BGM + SFX → audio_meta.json);通过 hyperframes-core 处理字幕编写和资源放置。详见下方音频。
多场景 / 转场hyperframes-animation/transitions/overview.md 然后是 transitions/catalog.md(阅读概览后并未完成——GSAP 配方在目录中)
模块化 / 子组件hyperframes-core/references/composition-patterns.md + references/sub-compositions.md

音频:单一引擎(TTS · BGM · SFX)

仅当作品需要时(遵循“精确构建所要求的内容”原则——不要在标题卡上添加环境音乐)。不要手工制作 TTS 或购买副本:编写一个中性的 audio_request.json 并调用 hyperframes-media 中的共享引擎。它会根据一个开关自动降级——存在 HeyGen 凭据 → 使用 HeyGen TTS + 音乐/SFX 检索;不存在 → 使用 ElevenLabs/Kokoro TTS,Lyria/MusicGen BGM 生成,以及捆绑的音效库。完整标志列表 + 请求/元数据模式:hyperframes-media/scripts/audio.mjs 的头部注释。

// audio_request.json — 每个旁白段落一行;`id` 是你的标识(用于回连 audio_meta)
{
  "lines": [
    { "id": "s1", "text": "你的开场白。", "sfx": ["whoosh"] },
    { "id": "s2", "text": "下一个节拍。" },
  ],
  "bgm": { "query": "calm cinematic underscore" }, // 省略 "mode" → 自动(如果存在 HeyGen 则检索,否则生成);设置为 "none" 以禁用
}
# <MEDIA_DIR> = 已安装的 hyperframes-media 技能目录(此技能的兄弟目录)
node <MEDIA_DIR>/scripts/audio.mjs --request ./audio_request.json --hyperframes . --out ./audio_meta.json

然后读取 audio_meta.json:将每个 voices[].path + (bgm.path, sfx[]) 挂载为 <audio> 轨道,并使用 voices[].words 制作字幕,全部依据 hyperframes-core(音频轨道 + 字幕编写)。如果 BGM 走了生成路径(bgm_pending: true),在最终渲染前运行 hyperframes-media/scripts/wait-bgm.mjs。

输出清单 → hyperframes-cli

…

[为翻译而截断]

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

1345AbhishekKumar/starter-supabase

Add captions to a talking-head video. ONE catalog (CATALOG.md) of 32 visual identities behind two engines: column-flow (captions composited INTO the scene — matte occlusion + mix-blend; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) and themed constitutions (anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity — e.g. a glyph-decode climax, a neon sign WRITTEN stroke by stroke, or the quiet `anchor` rail default). Route by identity, never by mode. Trigger on "captions/subtitles", "embed/cinematic captions", "VFX captions", "炸/特效/酷炫字幕", a named identity, or top-tier motion-graphics asks. Embedding every word is wrong for most talking-head content — `anchor` is the verbatim default. Pipeline: transcription → hyperframes remove-background matting → HTML render → ffmpeg overlay. Requires hyperframes and a single-subject clip.

1345AbhishekKumar/starter-supabase

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

1345AbhishekKumar/starter-supabase

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

1345AbhishekKumar/starter-supabase

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

1345AbhishekKumar/starter-supabase

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

1345AbhishekKumar/starter-supabase

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

1345AbhishekKumar/starter-supabase

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

1345AbhishekKumar/starter-supabase

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

1345AbhishekKumar/starter-supabase

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

1345AbhishekKumar/starter-supabase

turn a product or marketing URL, pasted script, or brief into a product launch video, including SaaS promos, feature reveals, app launches, company promos, and product marketing videos. Use this skill when the user wants to market, launch, promote, or reveal a product. Do not use it for general non-launch website tours, non-product topic explainers, GitHub pull requests, captioning existing footage, or short unnarrated motion graphics. If the intent is unclear, route through /hyperframes first. This is the new shot-sequence architecture: every visual frame is authored as a time-coded shot sequence picked from a menu of golden blueprints, so frames develop over their full duration instead of freezing after entrance.

1345AbhishekKumar/starter-supabase

turn a GitHub pull request (a PR URL like github.com/<owner>/<repo>/pull/<N>, an <owner>/<repo>#<N> ref, or 'this PR' in a checked-out repo) into a code-change explainer video, up to ~3 min (sweet spot 30-90s) — changelog, feature reveal, fix, or refactor walkthrough, rendered from the diff / commits / files. The input is a CODE CHANGE read via the gh CLI; there is no website capture. Use this skill for a GitHub PR. Do not use it for a product launch/promo (use /product-launch-video), a tour of a real website (use /website-to-video), a topic explainer with no PR (use /faceless-explainer), captions on existing footage (use /embedded-captions), or a short unnarrated motion graphic (use /motion-graphics). If the intent is unclear, route through /hyperframes first.

1345AbhishekKumar/starter-supabase

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

1345AbhishekKumar/starter-supabase

Capture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or social clip from the site's own visuals). Uses headless Chrome screenshots + brand assets. Use when intent is general — portfolio/blog/landing-page showcase or social clip from the site. NOT for: product/SaaS launch or promo (→ /product-launch-video, even from a URL); topic explainer with no site (→ /faceless-explainer); GitHub PR (→ /pr-to-video); adding captions to existing video (→ /embedded-captions); short unnarrated page-highlight motion graphic (→ /motion-graphics). Unclear launch-vs-general-site? Ask one question or start at /hyperframes.

相关技能