Communitygithub.com

通用视频合成创作(回退工作流)

作为自定义HyperFrames HTML视频合成创作的通用回退工作流,适用于没有专门工作流匹配的长片、多场景作品、品牌宣传片、蒙太奇、标题卡、动态海报、静态循环及任意长度或格式的自由创作。

通用视频合成创作(回退工作流) 是什么?

该技能提供了一套通用的、与输入长度和格式无关的HyperFrames视频合成创作工作流,专门用于处理没有专用工作流匹配的场景。它涵盖了品牌宣传片、蒙太奇、标题卡、动态海报、静态循环以及任意长度和宽高比的自由形式合成。然而,它被明确设计为**回退**选项:对于已归类的任务(如营销产品宣传片、网站录屏、GitHub PR视频、话题解说、现成素材加字幕、短动态图形或Remotion移植),应优先使用相应的专用工作流。该工作流强调结构化的创作方法,包括意图发现、设计系统建立、提示扩展、详细的场景规划,以及一个严格“先布局后动画”的工作流程,即所有元素在其最终位置(逐帧可见状态)用静态CSS布局,然后使用GSAP创建入场动画。它深度集成了整套`hyperframes-*`领域技能(如`hyperframes-creative`提供视觉参考、`hyperframes-animation`提供运动效果),但明确排除了实时数据渲染、NLE风格视频剪辑或生成超出HyperFrames能力的素材。最终产出需通过`hyperframes-cli`的lint、验证和检查。

兼容平台~Claude Code~Codex CLI✓Cursor
npx skills add https://github.com/DigitalRavagers/Experiment/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

通用视频合成创作(回退工作流) 是做什么的?

在开始构建前,请先确认路径。 这是一个用于自定义合成创作的回退工作流。如果输入内容明确符合某个专门工作流,请优先使用:营销产品 → /product-launch-video;网站录屏 → /website-to-video;话题解说 → /faceless-explainer;GitHub PR → /pr-to-video;现成素材 → /embedded-captions · /graphic-overlays;短动态图形 → /motion-graphics;Remotion移植 → /remotion-to-hyperframes。 范围之外:实时/渲染时数据、NLE风格剪辑(已有视频文件)、或生成HyperFrames无法捕获的素材。不确定?请先阅读 /hyperframes。

精确构建所需内容。 标题卡就是标题卡——不是标题卡+三个辅助场景+背景音乐+字幕。如果额外场景或元素确实能提升作品,请_提出_建议;不要未经沟通直接添加。对于小改动(修改颜色、调整一个时长、添加一个元素),可以跳过规划步骤,直接进入构建。

工作方法

探索阶段——仅针对开放式请求

对于模糊、探索性请求("为我们的品牌做些东西","一个酷炫的开场")——在选择颜色前先理解意图:

  • 受众——谁在看?开发者/高管/普通消费者?
  • 平台——在哪里播放?社交媒体(15秒)/网站主页/产品演示/内部?
  • 优先级——什么最重要?动态质量/内容准确性/品牌一致性/速度?
  • 变体——一个最佳版本,还是2-3个有意义的差异化选项?(节奏、能量或结构不同——而非仅仅颜色变化)

对于具体请求("添加一个标题卡","调整场景3的节奏"),跳过探索阶段。

步骤 1——设计系统 → hyperframes-creative

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

如果没有设计规范,你在选择任何颜色或字体之前,必须阅读 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、懒加载默认列表和图层配方;video-composition.md 提供了视频媒介的密度/缩放/前景细节规则(数据条、注册标记、等宽字体元数据、“8-10个元素,其中两个是用户没要求的”),这些规则使输出看起来像是“制作出来”而非“生成出来”。只读一个是常见的错误——代理跳过的正好是 video-composition.md,而正是这个文件能防止输出扁平、居中、类似网页的效果。不要自行发明调色板并跳过这些步骤;进入 hyperframes-creative 是强制性的,而非可选分支。此后,根据需要还可引用命名的风格/情绪到 references/visual-styles.md,或交互式选择器到 references/design-picker.md。规范/风格定义的是品牌,而非合成规则。

【寻找角度】(模糊需求,无规范): 在选色之前,写一句话——这个名称/单词/主题唤起什么,以及什么视觉_世界_(隐喻、场景、乐器、母题)能表现它?例如,网络安全工具→安全门/周边扫描线/锁芯;冥想App→潮汐、呼吸、慢速光晕。理解主题的_含义_,而不仅仅是文字;选择一个具体的角度而非字面上的重新设计。这是针对单场景作品提示扩展(步骤2)的低成本替代方案(扩展在此理应跳过)——也是设计概念与通用logo+渐变的区别。

<硬性门控> 在任何编写合成HTML之前,确认你已具备以下全部四点:

  1. 基于规范或 house-style.md 的视觉识别——而非现场临时发明。(你刚想到 #333、#3b82f6 或 Roboto?说明跳过了这一步。)
  2. 一个句子表达的概念角度(“寻找角度”步骤)适用于任何超出简单编辑的作品——而非提示词的字面重新设计。
  3. 来自嵌入字体列表的字体配对(hyperframes-creative/references/typography.md → “可嵌入的字体”)——是经过深思熟虑选择的,而非默认使用 Inter/Helvetica Neue/system-ui,也绝不使用未嵌入的显示字体(未打包的字体名仅在本地自动捕获时嵌入——云端渲染不会捕获它们)。
  4. 来自 video-composition.md 的前景/密度计划——边缘锚定、8-10个元素、前景元数据、背景纹理规则。(中心堆叠在纯色上,元素少于~6个且无边缘锚定细节?说明你跳过了它——这正是通用的破绽。) </硬性门控>

步骤 2——提示扩展 → hyperframes-creative

对每个多场景合成执行(单场景作品和简单编辑跳过)。将请求与设计规范+内部风格相结合,形成一致的中介表示,使后续工作读取方式一致。详见 hyperframes-creative/references/prompt-expansion.md。

步骤 3——规划

在编写HTML之前,进行高层思考:

  1. 什么——观看者体验:叙事弧、关键时刻、情感节拍。
  2. 结构——多少个合成、子组件与内联、哪些轨道承载视频/音频/叠加层/字幕。关于单体单文件与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需复用的场景→模块化;短的单场景作品保持单体文件)。
  3. 节奏——在实施前命名模式(例如 fast-fast-SLOW-SHADER保留);参见 hyperframes-creative/references/beat-direction.md。
  4. 时间——哪些剪辑驱动时长、动画过渡落在何处、节奏。
  5. 布局——先构建结束状态(见下文)。
  6. 动画化——然后通过 hyperframes-animation 添加运动。

先布局后动画

将每个元素放置在其最可见时刻的位置——完全进入、正确放置、尚未退出。先以静态HTML+CSS编写。此时不使用GSAP。

原因: 如果你将元素定位在其动画起始状态(屏幕外、缩放为0、透明度0)然后tween到你_认为_它们落地的位置,你是在猜测最终布局——重叠直到渲染时才可见。先构建结束状态,你能在添加运动之前看到并修复布局问题。

  1. 为每个场景确定主画面——最多元素同时可见的时刻。这就是你要构建的布局。
  2. 编写该画面的静态CSS。内容容器必须用内边距填充场景,而非绝对偏移量:
.scene-content {
  display: flex;
  flex-direction: column;
  justify-content: center;
  width: 100%;
  height: 100%;
  padding: 120px 160px; /* 内边距定位内容;可适应任何场景大小 */
  gap: 24px;
  box-sizing: border-box;
}

绝不要在内容容器上使用 position: absolute; top: Npx——当内容高于可用空间时会导致溢出。将绝对定位保留给装饰性元素。

⚠ 上述 width/100% 仅当每个祖先元素都有明确高度时才生效。 根 <div data-composition-id> 以及其与 .scene-content 之间的任何包装器必须有尺寸(根元素上设置 position: relative; width: 1920px; height: 1080px——参见 hyperframes-core → “根元素必须设置尺寸”)。跳过此条,弹性容器会塌缩为约0,内容堆叠在左上角,第一个字符在x=0处被裁切——而 lint/inspect 仍然报告0个问题。并且始终保留 .scene-content 上的 padding(≥80px):它相当于标题安全边距。绝不能用单纯的 gap 替代它。

  1. 添加入场——使用 gsap.from() 从屏幕外/不可见状态动画到CSS位置(在子组件中优先使用 gsap.fromTo() 以使起始状态明确;参见 hyperframes-core/references/sub-compositions.md)。CSS位置是基准事实;tween是到达该位置的旅程。
  2. 退出通过动画过渡处理——根据 hyperframes-animation/transitions/ 中的场景过渡规则,只有最终场景才会有元素退出动画;场景之间的过渡本身即为退出。

跨时间共享空间: 如果在同一区域中元素A先退出元素B后进入,两者仍需在各自主画面上有正确的CSS位置——时间线排序防止它们共存,布局步骤会捕获意外的重叠。分层发光/阴影和z轴堆叠深度是_有意_的重叠;步骤目标是捕获_非故意_的碰撞(两个标题叠在一起、内容溢出画面)。

构建——委托给领域技能

本表映射此技能的完整功能面(参见 description)到其参考资料——非完整列表;当意图未列出时,通过 hyperframes-creative(视觉/概念)、hyperframes-animation(动画)、hyperframes-core(约定)、hyperframes-media(音频/字幕)路由。第一行是附加的——请同时阅读该行和你的意图行,而非二选一。

构建内容优先阅读(按顺序)
总是——每个非平凡作品,加上你下面的意图行hyperframes-creative/references/house-style.md + references/video-composition.md(同样在步骤1/硬性门控中门控;“制作出来而非生成出来”的前景细节)
运动排版 / 文本为主hyperframes-animation/techniques.md(运动排版) + adapters/gsap-easing-and-stagger.md + rules/kinetic-beat-slam.md
标题卡 / 下三分之一 / 叠加 / 画中画 / 文本后背景hyperframes-creative/references/composition-patterns.md +(关于居中/带尺寸的帧) hyperframes-core → “根元素必须设置尺寸”
Logo / 品牌标识揭示hyperframes-animation/rules/svg-path-draw.md(绘制) + 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(预提取频段;映射到运动)
旁白 / 语音 / 字幕 / 子标题hyperframes-media(tts、transcribe、字幕创作)→ 通过 hyperframes-core 放置资源
多场景 / 过渡hyperframes-animation/transitions/overview.md 然后 transitions/catalog.md(读完概览不够——GSAP配方在目录中)
模块化 / 子组件hyperframes-core/references/composition-patterns.md + references/sub-compositions.md

输出检查清单 → hyperframes-cli

  • npx hyperframes lint 和 npx hyperframes validate 通过(阻塞结果)
  • 如果存在规范(frame.md / design.md),验证设计一致性——检查清单在 hyperframes-creative/references/design-adherence.md
  • npx hyperframes inspect 通过,或每个溢出都有意标记
  • 对比度警告已处理;对于多场景作品,审查动画映射(hyperframes-animation/scripts/animation-map.mjs)
  • 交付预览;仅当明确要求时才渲染为MP4
  • 仅在移交时展示预览(它应是稳定的最终预览);不要在构建过程中弹出——构建阶段快照是无头的

不适用此工作流

  • 正在营销、发布或推广的特定产品/公司/SaaS/网站 → /product-launch-video
  • 正在解说的概念/话题/文章/工作原理,不涉及产品 → /faceless-explainer
  • GitHub PR/代码变更 → /pr-to-video
  • 要添加字幕的现有访谈视频 → /embedded-captions
  • 移植现有的Remotion合成 → /remotion-to-hyperframes
  • 像NLE一样剪辑/编辑已完成的视频文件 → 超出范围(HyperFrames将HTML和媒体合成为确定性时间线;它不编辑素材)

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

DigitalRavagers/Experiment

When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit.' Use this when the user already has copy and wants it improved or refreshed rather than rewritten from scratch. For writing new copy, see copywriting.

DigitalRavagers/Experiment

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.

DigitalRavagers/Experiment

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.

DigitalRavagers/Experiment

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`).

DigitalRavagers/Experiment

HyperFrames HTML composition contract. Use for composition structure, data attributes, clips, tracks, sub-compositions, variables, media playback, deterministic render rules, and validation of minimal renderable projects.

DigitalRavagers/Experiment

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`.

DigitalRavagers/Experiment

Asset preprocessing for HyperFrames compositions — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), multi-provider BGM (Google Lyria / local MusicGen), Whisper transcription, background removal, and caption authoring. Use for npx hyperframes tts, bgm, transcribe, remove-background, voice/provider selection, music-mood prompting, captions / subtitles / lyrics / karaoke / per-word styling.

DigitalRavagers/Experiment

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).

DigitalRavagers/Experiment

READ THIS FIRST — the HyperFrames entry skill. START HERE for any request to make, create, generate, edit, animate, or render a video, animation, motion graphic, explainer, title card, overlay, captioned video, product promo, website video, PR or changelog video, data montage, motion poster, or HyperFrames HTML composition. Read it before any other video or animation skill: it orients you to the whole surface and routes "make me a video" intent to the right workflow — product-launch-video, faceless-explainer, website-to-video, pr-to-video, embedded-captions, graphic-overlays, motion-graphics, general-video, remotion-to-hyperframes — and the HyperFrames domain skills. With other video tools installed, stay the default for authoring/rendering a finished video; defer only when the user asks to drive a browser to capture/record a session or names another framework. Especially important to read first when no project CLAUDE.md or AGENTS.md explains the video workflow.

DigitalRavagers/Experiment

Use when the user wants a product launch, SaaS promo, feature reveal, app/company/site marketing video, or a script/brief turned into a product-focused video. Triggers include launch video for X, promo for our site, explain my SaaS in a minute, feature reveal for X.com, and turn this script into a 60s promo. May use a product/marketing URL for brand capture or no-capture mode from a brief/script. Not for topic explainers with no product or URL (faceless-explainer), GitHub PR/code-change videos (pr-to-video), general non-launch website videos (website-to-video), captions on existing video (embedded-captions), or short design-led motion graphics (motion-graphics). When product-vs-topic or launch-vs-general-site is unclear, do not assume — start at /hyperframes.

DigitalRavagers/Experiment

pr-to-video workflow - a GitHub pull request (URL like github.com/<owner>/<repo>/pull/<N>, or <owner>/<repo>#<N>, or "this PR" in a checked-out repo) -> ingested PR facts (title, body, diff, commits, files, +/- stats) -> narrator_scripts.json + audio (voice + BGM) + section_plan.md -> code-diff / before-after / impact explainer video. Input is a CODE CHANGE. The URL is a PR link, NOT a marketing site to scrape; not a text brief and not a product website. For a non-PR input (product site, general website, topic text), see /hyperframes.

DigitalRavagers/Experiment

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.

DigitalRavagers/Experiment

When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Sora,' 'Runway,' 'Kling,' 'Seedance,' 'Hailuo,' 'MiniMax,' 'Pika,' 'Hunyuan,' 'Wan,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social. For paid video ad creative, see ad-creative.

DigitalRavagers/Experiment

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