website-to-hyperframes
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseWebsite to HyperFrames
网站转HyperFrames视频
Capture a website, then produce a professional video from it.
Users say things like:
- "Capture https://... and make me a 25-second product launch video"
- "Turn this website into a 15-second social ad for Instagram"
- "Create a 30-second product tour from https://..."
The workflow has 7 steps. Each produces an artifact that gates the next.
捕获网站内容,然后生成专业视频。
用户的常见需求如下:
- "捕获https://...并为我制作一个25秒的产品发布视频"
- "把这个网站转换成适合Instagram的15秒社交广告"
- "基于https://...制作一个30秒的产品导览视频"
该流程包含7个步骤,每个步骤生成的成果是进入下一步的前提条件。
Step 1: Capture & Understand
步骤1:捕获与理解
Read: references/step-1-capture.md
Run the capture, read the extracted data, and build a working summary using the write-down-and-forget method.
Gate: Print your site summary (name, top colors, fonts, key assets, one-sentence vibe).
阅读参考文档: references/step-1-capture.md
执行捕获操作,读取提取的数据,并使用“记录后暂存”方法构建一份可用的摘要。
进入下一步的前提: 输出网站摘要(名称、主色调、字体、关键资源、一句话风格描述)。
Step 2: Write DESIGN.md
步骤2:编写DESIGN.md
Read: references/step-2-design.md
Write a simple brand reference for the captured website. 6 sections, ~90 lines. This is a cheat sheet, not the creative plan — that comes in Step 4.
Gate: exists in the project directory.
DESIGN.md阅读参考文档: references/step-2-design.md
为捕获的网站编写一份简洁的品牌参考文档,包含6个部分,约90行内容。这是一份速查手册,而非创意方案——创意方案将在步骤4中完成。
进入下一步的前提: 项目目录中存在文件。
DESIGN.mdStep 3: Write SCRIPT
步骤3:编写脚本
Read: references/step-3-script.md
Write the narration script. The story backbone. Scene durations come from the narration, not from guessing.
Gate: exists in the project directory.
SCRIPT.md阅读参考文档: references/step-3-script.md
编写旁白脚本,这是视频的故事核心。场景时长由旁白内容决定,而非主观猜测。
进入下一步的前提: 项目目录中存在文件。
SCRIPT.mdStep 4: Write STORYBOARD
步骤4:编写分镜脚本
Read: references/step-4-storyboard.md
Write per-beat creative direction: mood, camera, animations, transitions, assets, depth layers, SFX. This is the creative north star — the document the engineer follows to build each composition.
Gate: exists with beat-by-beat direction and an asset audit table.
STORYBOARD.md阅读参考文档: references/step-4-storyboard.md
为每个节拍编写创意指导:氛围、镜头、动画、转场、资源、分层深度、音效。这是创意的核心基准——工程师将依据此文档构建每个画面组合。
进入下一步的前提: 存在包含逐节拍指导和资源审核表的文件。
STORYBOARD.mdStep 5: Generate VO + Map Timing
步骤5:生成旁白音频 + 映射时间轴
Read: references/step-5-vo.md
Generate TTS audio, transcribe for word-level timestamps, and map timestamps to beats. Update STORYBOARD.md with real durations.
Gate: (or .mp3) + exist. Beat timings in STORYBOARD.md updated.
narration.wavtranscript.json阅读参考文档: references/step-5-vo.md
生成TTS(文本转语音)音频,转录得到逐词时间戳,并将时间戳映射到各个节拍。更新中的实际时长。
STORYBOARD.md进入下一步的前提: 存在(或.mp3)文件和文件,且中的节拍时间已更新。
narration.wavtranscript.jsonSTORYBOARD.mdStep 6: Build Compositions
步骤6:构建画面组合
Read: The skill (invoke it — every rule matters)
Read: references/step-6-build.md
/hyperframesBuild each composition following the storyboard. After each one: self-review for layout, asset placement, and animation quality.
Gate: Every composition has been self-reviewed. No overlapping elements, no misplaced assets, no static images without motion.
阅读参考文档: 技能(调用该技能——所有规则均需遵守)
阅读参考文档: references/step-6-build.md
/hyperframes按照分镜脚本构建每个画面组合。完成每个组合后,自行检查布局、资源位置和动画质量。
进入下一步的前提: 所有画面组合均已完成自我审核,无元素重叠、资源错位或无动态效果的静态图片。
Step 7: Validate & Deliver
步骤7:验证与交付
Read: references/step-7-validate.md
Lint, validate, preview. Create a HANDOFF.md for multi-session continuity.
Gate: and pass with zero errors.
npx hyperframes lintnpx hyperframes validate阅读参考文档: references/step-7-validate.md
检查、验证、预览视频。创建文件以保证多会话的连续性。
HANDOFF.md进入下一步的前提: 和命令执行无错误。
npx hyperframes lintnpx hyperframes validateQuick Reference
快速参考
Video Types
视频类型
| Type | Duration | Beats | Narration |
|---|---|---|---|
| Social ad (IG/TikTok) | 10-15s | 3-4 | Optional hook sentence |
| Product demo | 30-60s | 5-8 | Full narration |
| Feature announcement | 15-30s | 3-5 | Full narration |
| Brand reel | 20-45s | 4-6 | Optional, music focus |
| Launch teaser | 10-20s | 2-4 | Minimal, high energy |
| 类型 | 时长 | 节拍数 | 旁白要求 |
|---|---|---|---|
| 社交广告(IG/TikTok) | 10-15秒 | 3-4 | 可选钩子语句 |
| 产品演示视频 | 30-60秒 | 5-8 | 完整旁白 |
| 功能发布视频 | 15-30秒 | 3-5 | 完整旁白 |
| 品牌宣传视频 | 20-45秒 | 4-6 | 可选,以音乐为主 |
| 发布预告视频 | 10-20秒 | 2-4 | 极简风格,高能量 |
Format
视频格式
- Landscape: 1920x1080 (default)
- Portrait: 1080x1920 (Instagram Stories, TikTok)
- Square: 1080x1080 (Instagram feed)
- 横屏:1920x1080(默认)
- 竖屏:1080x1920(Instagram Stories、TikTok)
- 方形:1080x1080(Instagram动态)
Reference Files
参考文件
| File | When to read |
|---|---|
| step-1-capture.md | Step 1 — reading captured data |
| step-2-design.md | Step 2 — writing DESIGN.md |
| step-3-script.md | Step 3 — writing the narration script |
| step-4-storyboard.md | Step 4 — per-beat creative direction |
| step-5-vo.md | Step 5 — TTS, transcription, timing |
| step-6-build.md | Step 6 — building compositions with self-review |
| step-7-validate.md | Step 7 — lint, validate, preview, handoff |
| techniques.md | Steps 4 & 6 — 10 visual techniques with code patterns (SVG drawing, Canvas 2D, 3D, typography, Lottie, video, typing, variable fonts, MotionPath, transitions) |
| 文件 | 阅读时机 |
|---|---|
| step-1-capture.md | 步骤1——读取捕获的数据 |
| step-2-design.md | 步骤2——编写DESIGN.md |
| step-3-script.md | 步骤3——编写旁白脚本 |
| step-4-storyboard.md | 步骤4——编写逐节拍创意指导 |
| step-5-vo.md | 步骤5——生成TTS音频、转录、时间轴映射 |
| step-6-build.md | 步骤6——构建画面组合并完成自我审核 |
| step-7-validate.md | 步骤7——检查、验证、预览、交付 |
| techniques.md | 步骤4和6——包含10种视觉技术及代码模式(SVG绘制、Canvas 2D、3D、排版、Lottie、视频、打字动画、可变字体、MotionPath、转场) |