Communitygithub.com

1345AbhishekKumar/starter-nextjs

捕获一个通用网站/URL,并将其转化为 HyperFrames 视频(网站导览、展示或来自网站视觉元素的社会媒体短片)。使用 headless Chrome 截图和品牌资产。适用于通用意图——展示作品集、博客或着陆页,或制作网站的社交媒体短片。

starter-nextjs 是什么?

该技能是一个专门为 AI 代理(如 Claude Code、Cursor、Codex)设计的工具,用于将任何通用网站转化为专业视频。它通过 7 个明确的协作步骤实现:从捕获网站并理解其品牌身份开始,然后定义设计规范和叙事策略,编写故事板和脚本,生成配音和字幕,构建合成画面,最后验证并交付最终视频。技能支持两种模式:默认的协作模式(在关键决策点等待用户输入)和自主模式(代理在质量验证保持不可跳过的情况下,代用户决定偏好设置)。它通过读取 `references/` 目录中的详细文档来指导每个步骤,确保设计决策基于从网站提取的真实计算值。虽然视频类型(如社交媒体广告、产品演示)和格式(横屏 1920×1080、竖屏 1080×1920、方形 1080×1080)灵活,但它有严格的规则:如果用户意图是推广产品/SaaS(应使用 `/product-launch-video`)、解释主题没有网站(应使用 `/faceless-explainer`)或编辑现有视频(超出范围),则会拒绝执行。它使用 HeyGen 进行配音和音乐(支持登录以使用在线引擎,或选择离线继续),并在整个过程中强制进行质量检查,包括资产审核、逐拍 HTML 审查和可访问性(WCAG)验证。

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

媒体用途:在获取音频/图片前,先调用 /media-use 从 HeyGen 目录中解决背景音乐/音效/图片。先运行 --adopt 注册已有资产。参见 /media-use 技能。

网站转 HyperFrames 视频

捕获一个网站,然后从中制作一个专业视频。

在步骤 0 之前确认编排路线。 此技能制作的是针对 / 来自一个通用网站的视频。如果用户实际上是在营销/发布/推广一个产品(即使是从这个 URL,即使说是“我们网站的推广视频”)→ /product-launch-video。有主题但没有网站的解说 → /faceless-explainer;一个 GitHub PR → /pr-to-video;重新剪辑/重新着色/重新排序一个已有的视频文件 → 超出范围。如果因为模糊的“制作一个视频”需求而被导向这里,或者不确定是发布还是通用网站?先阅读 /hyperframes(完整的编排路由表 + § HyperFrames 不能做什么)。

用户通常会这样说:

  • “把这个网站变成一个 15 秒的 Instagram 社交短片”
  • “从 https://... 制作一个 30 秒的网站导览/展示视频”
  • “捕获我们的首页,并利用它自己的视觉效果制作一个视频”

工作流程有 7 个步骤。每个步骤都会产生一个用于进入下一步的产物。默认情况下是协作的——标记为 💬 的关卡会停止并询问用户。如果用户发出自主模式信号(“替我做决定”、“给我个惊喜”),用户偏好相关的门控会被跳过;参见 step-2-brief.md 了解如何传播此设置。

自主模式不是“跳过所有门控。” 自动模式涵盖用户偏好问题(TTS 提供商、语音、色彩重点、节拍计数、音乐是/否、字幕是/否——在这些问题上,代理代用户决定)。它不涵盖质量验证门控。以下内容即使在自动模式下仍不可跳过:

  • 资产审计(步骤 3)——查看样片并为每个资产证明使用/跳过
  • 逐拍 HTML 阅读(步骤 5)——每个节拍的结构化证据块
  • 完成定义清单(步骤 6)——包括动画映射、逐告警的 WCAG 验证、音频/动效播放
  • 诚信披露部分(步骤 6)——“我未验证的内容”必须出现在你的最终摘要中

如果你发现自己认为“自动模式说倾向于行动,所以我要跳过 X”——而 X 是一个验证门控,而不是一个偏好问题——那么这个推理是错误的。倾向于行动适用于决定构建什么,而不是决定是否要验证。


步骤 0:捕获与理解品牌

阅读: references/step-0-capture.md

捕获网站,然后阅读提取的数据以理解品牌和产品——它是做什么的,为谁服务的,用什么声音说话,处于什么情绪氛围中。捕获到的资产是后期使用的品牌工具箱,而不是构成视频的构建块。

在撰写简报前显示登录状态——运行 npx hyperframes auth status 并逐字输出其结果(不要解释或重写)。 它会报告配音/背景音乐将使用 HeyGen 还是本地引擎,以及当未登录时如何登录。如果未登录,请停止并等待用户选择——登录,或者说“go”/“offline”以使用本地引擎继续——然后再询问简报或任何其他事项。 将其视为一个真正的决策点,而不是一个旁注;不要把这个选择塞进简报问题中,也不要把密钥写进每个仓库的 .env 文件中。(在自主模式下,注明状态并继续以离线模式操作。)参见 ../hyperframes-media → 预检以获取官方指导。

门控: 打印了网站摘要——策略优先(产品做什么、为谁服务、品牌声音),然后是资产/颜色/字体清单;显示了登录状态(已登录,或继续以离线模式操作)。


步骤 1:品牌身份

阅读: references/step-1-design.md

编写 DESIGN.md——一份品牌备忘单,涵盖视觉身份:颜色、排版、组件样式、布局原则。使用 design-styles.json 获取精确的计算值。

速度选项: 对于快节奏的视频(广告牌式逐拍),DESIGN.md 可以是一份 50 行的颜色 + 字体 + 注意事项的摘要——而不是一份 300 行的文档。步骤 5 中的子代理提示会直接粘贴品牌值,所以 DESIGN.md 的深度只对复杂构图才重要。

门控: DESIGN.md 存在(任意长度),至少包含:色调板、字体选择以及注意事项。


步骤 2:策略与信息传达

阅读: references/step-2-brief.md,references/capabilities.md(扫描目录——仅在需要时深入阅读章节)

在讨论视觉效果或资产之前,先与用户就视频必须传达什么信息达成一致。解析用户的提示——他们可能已经提供了视频类型和风格。只询问缺失的部分:这个视频必须说的一件事、叙事弧线和目标受众。

门控: 视频类型、时长、格式,以及关键的——信息和叙事弧线——要锁定。没有这些,步骤 3 就无法编写概念优先的故事板。


步骤 3:故事板 + 脚本 💬

阅读: references/step-3-storyboard.md

编写概念优先的故事板:信息 → 叙事弧线 → 服务于该弧线的节拍 → 每个节拍的技术 → 最后通过品牌强调。然后编写匹配的配音脚本。向用户展示这两者,并附带逐拍摘要。迭代直到用户批准。

门控: STORYBOARD.md + SCRIPT.md 存在并且用户已经批准了计划。


步骤 4:配音、时间控制 + 字幕 💬

阅读: references/step-4-vo.md

如果步骤 2 说没有配音——询问背景音乐,然后跳到步骤 5。否则:询问用户使用哪个 TTS 提供商(HeyGen TTS、ElevenLabs 或 Kokoro),生成音频,转录音频,将时间戳映射到节拍。然后询问字幕。

门控: (a) 未要求配音并且故事板有手动的节拍时间;或 (b) narration.wav + transcript.json 存在并且节拍时间已用实际时长更新。


步骤 5:构建合成画面

阅读: hyperframes 技能(加载它——每个规则都很重要) 阅读: references/step-5-build.md

按照故事板(步骤 3)中选择的架构和节奏构建 index.html 和合成画面。子代理在报告前,对每个节拍运行 hyperframes lint 和 hyperframes snapshot。

门控: 主代理已根据 DESIGN.md 和 STORYBOARD.md 从头到尾阅读了每个 compositions/beat-N.html。逐拍检查表位于 step-5-build.md 中。


步骤 6:验证与交付

阅读: references/step-6-validate.md

进行代码检查、验证、根据视频长度按比例截取快照(公式:max(节拍数 × 3, ceil(时长_秒 / 2))),并逐一审查。在交付前修复问题。交付 localhost Studio 项目的 URL——仅在用户明确要求时才渲染为 MP4。仅在交接时显示该 Studio URL——它是最终、稳定的预览;构建阶段的快照是无头生成的,因此不要在构建中途弹出预览。

交付一个你为之自豪的作品。 在交接前,问自己:我会把这个发布到社交媒体上并署上自己的名字吗?如果不是,那就修复问题。

门控: npx hyperframes lint 和 npx hyperframes validate 通过且零错误,并且最终响应中包含活动的 Studio 项目 URL。


快速参考

视频类型

按视频类型划分的典型约束——作为起点,而不是公式。节拍数应跟随内容与配音,而非来自目标范围。

类型典型时长时长驱动因素配音
社交媒体广告 (IG/TikTok)10–15 秒平台限制可选
产品演示30–60 秒脚本长度完整配音
功能公告15–30 秒功能复杂度完整配音
品牌展示片20–45 秒音乐轨道可选,侧重音乐
发布预告片10–20 秒钩子能量极少

节拍数特意不在本表格中——它应该来自故事板,而不是来自“社交媒体广告 = 3-4 个节拍”。一个复杂产品的社交媒体广告可能需要 5 个节奏恰当的节拍。一个只有一个强烈视觉主题的品牌展示片可能只需要 3 个。

格式

  • 横屏:1920x1080(默认)
  • 竖屏:1080x1920(Instagram 故事、TikTok)
  • 方形:1080x1080(Instagram 信息流)

参考文件

文件阅读时机
step-0-capture.md步骤 0——捕获、理解品牌和产品,编写策略优先的网站摘要
step-1-design.md步骤 1——编写 DESIGN.md 品牌备忘单(5 个部分,250-350 行;对于广告牌风格的社交媒体广告,50 行快速通道)
step-2-brief.md步骤 2——与用户就信息、叙事弧线和目标受众达成一致
capabilities.md步骤 2 和 5——HyperFrames 能做什么的完整清单(24 个章节)。在简报期间扫描目录,在构建期间深入阅读特定章节
step-3-storyboard.md步骤 3——故事板 + 脚本(合并),带用户审查门控
step-4-vo.md步骤 4——TTS 提供商选择、生成、时间控制
step-5-build.md步骤 5——构建 index.html + 合成画面
step-6-validate.md步骤 6——代码检查、验证、快照(按视频长度比例缩放)、预览
techniques.md步骤 3 和 5——13 种基础动画技术及其代码模式(需适配,不要复制粘贴)
html-in-canvas-patterns.md步骤 5——HTML 在 Canvas 中效果的完整代码模式(位于 hyperframes 技能中)

Individual skills in this repo

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

1345AbhishekKumar/starter-nextjs

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-nextjs

The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see /hyperframes); use this only as the general fallback when none fit.

1345AbhishekKumar/starter-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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-nextjs

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.

相关技能