Communitygithub.com

1345AbhishekKumar/starter-supabase

将通用网站/URL 转换为 HyperFrames 视频(网站导览、展示或基于网站视觉素材的社交媒体短片)。使用无头 Chrome 截图 + 品牌素材。

starter-supabase 是什么?

此技能专为将通用网站/URL 转换为专业视频而设计,适用于网站导览、作品集展示或基于网站自身视觉的社交媒体短片。它使用 Headless Chrome 捕获网站截图,并结合品牌素材生成视频。该技能包含一个全面的 7 步工作流程:捕获并理解品牌、建立品牌标识、确定策略和信息、制作故事板和脚本、生成旁白和时间线、构建合成以及最终验证和交付。它支持自主模式(用户偏好决策由 AI 代理完成)和协作模式(在关键关卡等待用户确认),但非跳过所有质量控制步骤(如资产审核、逐拍 HTML 检查、完成度核对和诚实披露)。支持 HeyGen 和本地引擎进行旁白和背景音乐,并明确指示在何种情况下应使用其他更专门的技能(如产品发布视频、无网站的主题讲解视频、GitHub PR 转视频等)。

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

media-use: 在获取音频/图片资源前,请先调用 /media-use 以从 HeyGen 目录中获取 BGM/SFX/图片。先运行 --adopt 注册已有资源。详情参见 /media-use 技能。

网站转 HyperFrames

捕获一个网站,然后为其制作专业视频。

在进入第 0 步前确认路线。 此技能为通用网站制作视频。如果用户实际意图是营销/发布/推广产品(即使是从此 URL,即使是“为我们网站做推广”)→ 使用 /product-launch-video。无网站的主题讲解 → 使用 /faceless-explainer;GitHub PR → 使用 /pr-to-video;重新剪辑/调色/排序现有视频文件 → 超出范围。如果用户模糊地说“做个视频”,或不确定是发布还是通用网站?请先阅读 /hyperframes(包含完整路由表 + § HyperFrames 不能做什么)。

用户可能会说:

  • “把这个网站做成一个 15 秒的 Instagram 社交媒体短片”
  • “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素材制作一个视频”

工作流程包含 7 个步骤。每个步骤产生一个供下一步使用的产物。默认情况下是协作模式——标记为 💬 的关卡会停下来询问用户。如果用户指示自主模式(“你决定”、“给我惊喜”),则跳过 💬 用户偏好关卡;参见 step-2-brief.md 了解这一点的传播方式。

自主模式并不意味着“跳过所有关卡”。 自动模式涵盖用户偏好问题(TTS 提供商、声音、颜色重点、节拍数、是否使用音乐、是否使用字幕——即代理代表用户进行决策)。它不涵盖质量验证关卡。以下内容在自动模式下仍不可跳过:

  • 资产审核(第 3 步)——查看缩略图工作表并证明每个资产是“使用”还是“跳过”
  • 逐拍 HTML 读取(第 5 步)——每个节拍的结构化证据块
  • 完成度核对清单(第 6 步)——包括动画映射、每个警告的 WCAG 验证、音频/动作回放
  • 诚实披露部分(第 6 步)——“我未验证的内容”必须出现在您的最终摘要中

如果您发现自己认为“自动模式说偏向行动,所以我会跳过 X”——而 X 是一个验证关卡,而不是偏好问题——那么这个想法是错误的。偏向行动适用于决定要构建什么,而不是决定是否要验证。


第 0 步:捕获并理解品牌

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——它的功能、目标用户、表达方式和情绪基调。捕获的资源是后续的品牌工具包,而不是组成视频的基础模块。

在简报之前显示登录状态——运行 npx hyperframes auth status 并逐字输出其结果(不要转述或重写)。 它报告将使用 HeyGen 还是本地引擎进行语音/BGM,以及未登录时如何登录。如果未登录,请停下来,等待用户选择——登录,或说“继续”/“离线”以使用本地引擎继续——然后再询问简报或其他任何事情。 将其视为一个真实的决策点,而不是一个简单的注释;不要将选择内容合并到简报问题中,也不要将密钥写入仓库特定的 .env 文件。(在自主模式下,记录状态并以离线模式继续。)参见 ../hyperframes-media → Preflight 以获取规范指导。

关卡: 打印了网站摘要——以策略为优先(产品的功能、目标用户、品牌语调),然后是资源/颜色/字体清单;已显示登录状态(已登录,或正在以离线模式继续)。


第 1 步:品牌标识

阅读: references/step-1-design.md

编写 DESIGN.md——一份涵盖视觉标识的品牌备忘单: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: 对于快节奏视频(每节拍一个广告牌),DESIGN.md 可以是一个约 50 行的摘要,仅包含颜色 + 字体 + 注意事项——而不是一个 300 行的文档。第 5 步的子代理提示会直接粘贴品牌值,因此 DESIGN.md 的深度只对复杂构图有影响。

关卡: 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。


第 2 步:策略与信息

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

在讨论视觉或资源之前,先与用户就视频必须传达的信息达成一致。解析用户的提示——他们可能已经给出了视频类型和风格。只询问缺失的部分:这个视频必须说的一件事,叙事弧线,以及目标受众。

关卡: 视频类型、时长、格式,以及关键的——信息和叙事弧线已锁定。没有这些,第 3 步无法编写以概念为先的故事板。


第 3 步:故事板 + 脚本 💬

阅读: references/step-3-storyboard.md

以概念为先编写故事板:信息 → 叙事弧线 → 服务于弧线的节拍 → 每个节拍使用的技术 → 最后进行品牌重点润色。然后编写匹配的旁白脚本。向用户逐节拍展示摘要。迭代直到用户批准。

关卡: STORYBOARD.md + SCRIPT.md 已存在并且用户已批准计划。


第 4 步:旁白、时间线 + 字幕 💬

阅读: references/step-4-vo.md

如果第 2 步要求无旁白——询问背景音乐,然后跳到第 5 步。否则:询问用户选择哪个 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。然后询问字幕相关事宜。

关卡: 要么 (a) 未要求旁白且故事板包含手动节拍时间,要么 (b) narration.wav + transcript.json 已存在且节拍时间已用实际时长更新。


第 5 步:构建合成

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

按照故事板中选择的架构和节奏(第 3 步)构建 index.html 和合成文件。在报告返回之前,子代理对每个节拍运行 hyperframes lint 和 hyperframes snapshot。

关卡: 主代理已针对 DESIGN.md 和 STORYBOARD.md 从头到尾阅读了每个 compositions/beat-N.html。逐节拍检查清单位于 step-5-build.md 中。


第 6 步:验证与交付

阅读: references/step-6-validate.md

进行 lint 检查、验证、根据视频时长缩放后拍摄快照(公式:max(节拍数 × 3, ceil(时长秒数 / 2))),并检查每个快照。修复问题后再交付。交付 localhost Studio 项目 URL——仅在用户明确要求时才渲染为 MP4。仅在交接时展示该 Studio URL——它是最终、稳定的预览版本;构建阶段的快照是无头的,因此不要在构建过程中弹出预览。

交付您引以为傲的作品。 在交接之前,问问自己:我会把这个发到社交媒体上并署上我的名字吗?如果不是,那么修复问题。

关卡: npx hyperframes lint 和 npx hyperframes validate 通过且零错误,最终响应包含活动的 Studio 项目 URL。


快速参考

视频类型

各类视频的典型约束——作为起点,而非公式。节拍数应源自内容和旁白,而非目标范围。

类型典型时长时长决定因素旁白
社交媒体广告 (IG/TikTok)10–15 秒平台限制可选
产品演示30–60 秒脚本长度完整旁白
功能发布15–30 秒功能复杂度完整旁白
品牌宣传片20–45 秒音乐轨可选,侧重音乐
发布预告10–20 秒钩子吸引力最少

节拍数故意不在此表中——它应来自故事板,而非“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 个精心安排时机的节拍。一个有单一强视觉主题的品牌宣传片可能只需要 3 个节拍。

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

文件何时阅读
step-0-capture.md第 0 步——捕获、理解品牌和产品,编写以策略为先的网站摘要
step-1-design.md第 1 步——编写 DESIGN.md 品牌备忘单(5 个部分,250-350 行;针对广告牌式社交媒体广告可使用 50 行的快速路径)
step-2-brief.md第 2 步——与用户就信息、叙事弧线和目标受众达成一致
capabilities.md第 2 步和第 5 步——HyperFrames 所有能力的完整清单(24 个部分)。在简报期间扫描目录,在构建期间深入阅读特定部分
step-3-storyboard.md第 3 步——故事板 + 脚本(合并),含用户审核关卡
step-4-vo.md第 4 步——TTS 提供商选择、生成、时间线
step-5-build.md第 5 步——构建 index.html + 合成文件
step-6-validate.md第 6 步——lint 检查、验证、快照(按视频时长缩放)、预览
techniques.md第 3 步和第 5 步——13 种基础动画技术及代码模式(需要适配,不要直接复制粘贴)
html-in-canvas-patterns.md第 5 步——Canvas 中 HTML 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-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

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-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.

相关技能