Communitygithub.com

delorenj/skills

捕获网站并从中创建 HyperFrames 视频。当用户提供 URL 并希望获得视频,或要求“捕获此网站”、“将其转为视频”、“从我的网站制作推广视频”,或想要基于现有网站制作社交广告、产品演示等任何视频内容时使用。即使只是粘贴一个 URL——这也是应该使用的技能。

skills 是什么?

该技能是一个基于 Claude Code (或兼容 IDE 的 AI 代理) 的专业视频制作工作流,能够将任意网站 URL 转换为专业级 HyperFrames 视频项目。它支持多种视频类型,包括社交广告、产品演示、功能公告、品牌展示和发布预告。工作流分为七个严格的步骤:捕获与分析、撰写 DESIGN.md、撰写脚本、创作分镜、生成配音并映射时间、构建合成以及验证交付。每个步骤都产生一个关键产物,并作为下一步的“门控”条件。该技能支持横屏、竖屏和方形格式,并内置了严格的验证流程(lint 和 validate),确保交付前零错误。最终会提供一个可交互预览的 Studio 项目 URL,仅在用户明确要求时才渲染为 MP4。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/delorenj/skills/tree/HEAD/website-to-hyperframes

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

网站转 HyperFrames 视频

捕获一个网站,然后从中制作出专业视频。

用户会这样说:

  • “捕获 https://... 并为我制作一个 25 秒的产品发布视频”
  • “把这个网站变成一个 15 秒的 Instagram 社交广告”
  • “从 https://... 创建一个 30 秒的产品导览”

该工作流包含 7 个步骤。每个步骤都会产生一个产物,作为下一步的“门控”条件。


步骤 1:捕获与理解

阅读: references/step-1-capture.md

运行捕获,读取提取的数据,并使用“写下来然后忘记”的方法构建一个工作摘要。

门控: 打印你的网站摘要(名称、主要颜色、字体、关键资产、一句话氛围)。


步骤 2:编写 DESIGN.md

阅读: references/step-2-design.md

为捕获的网站编写一个简单的品牌参考文档。包含 6 个部分,约 90 行。这是一份速查表,不是创意方案——创意方案在第 4 步。

门控: 项目目录中存在 DESIGN.md。


步骤 3:编写剧本

阅读: references/step-3-script.md

编写旁白剧本。这是故事的主干。场景时长来自旁白,而不是猜测。

门控: 项目目录中存在 SCRIPT.md。


步骤 4:编写分镜

阅读: references/step-4-storyboard.md

编写每个节拍的创意指导:情绪、镜头、动画、转场、素材、深度图层、音效。这是创意的北极星——工程师将依据该文档构建每个合成。

门控: STORYBOARD.md 存在,包含逐节拍的指导和一个资产审核表。


步骤 5:生成配音 + 映射时间

阅读: references/step-5-vo.md

生成 TTS 音频,进行逐词转录并获取时间戳,然后将时间戳映射到各个节拍。用实际时长更新 STORYBOARD.md。

门控: narration.wav(或 .mp3)+ transcript.json 存在。STORYBOARD.md 中的节拍时间已更新。


步骤 6:构建合成

阅读: hyperframes 技能(加载它——每条规则都很重要) 阅读: references/step-6-build.md

按照分镜构建每个合成。每个完成后进行自查:布局、素材放置和动画质量。

门控: 每个合成都已自查通过。无重叠元素,无错位素材,无静态图像缺少运动。


步骤 7:验证与交付

阅读: references/step-7-validate.md

进行检查、验证、快照、预览。首先向用户提供本地 Studio 项目的 URL(http://localhost:<port>/#project/<project-name>),仅在用户明确要求时才渲染为 MP4。请勿将 index.html 视为项目移交链接;它仅作源代码上下文参考。

门控: npx hyperframes lint 和 npx hyperframes validate 通过且无错误,最终回复中包含有效的 Studio 项目 URL。


快速参考

视频类型

类型时长节拍旁白
社交广告 (IG/TikTok)10-15秒3-4可选钩子句
产品演示30-60秒5-8完整旁白
功能公告15-30秒3-5完整旁白
品牌展示20-45秒4-6可选,以音乐为主
发布预告10-20秒2-4最少,高能量

格式

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

参考文件

文件何时阅读
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 —— 逐节拍创意指导
step-5-vo.md步骤 5 —— TTS、转录、时间映射
step-6-build.md步骤 6 —— 构建合成与自查
step-7-validate.md步骤 7 —— 检查、验证、快照、预览
techniques.md步骤 4 和 6 —— 11 种视觉技术及其代码模式(SVG 绘制、Canvas 2D、3D、字体排印、Lottie、视频、打字效果、可变字体、MotionPath、转场、音频响应)

Individual skills in this repo

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

delorenj/skills

Plan and generate terminal ASCII animations/screensaver-style output (FPS, refresh rules, loop policy, low-flicker guidance), with a static poster frame and an optional local demo script.

delorenj/skills

ASCII video: convert video/audio to colored ASCII MP4/GIF.

delorenj/skills

Plan, build and quality-check a premium short commercial for a real business (roofing, property, ecommerce, B2B software) using AI-generated footage, code-built motion (HTML/GSAP), selective Three.js and an independent-critic "Gauntlet" loop. Use when asked to make a launch-style / SaaS-style video, business ad, explainer, sample reel or pitch video, or to review and improve one. Encodes motion principles distilled from 28 professional launch films, a quality bar, audio rules and a business-offer playbook.

delorenj/skills

CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that HyperFrames must seek deterministically during preview and rendering.

delorenj/skills

Generate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery. Includes single scene regeneration for fine-tuning.

delorenj/skills

HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.

delorenj/skills

Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.

delorenj/skills

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, and registry discovery.

delorenj/skills

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.

delorenj/skills

Manim CE animations: 3Blue1Brown math/algo videos.

delorenj/skills

Join a Google Meet or Zoom call as a video meeting agent via PikaStreaming. Trigger: user drops a Google Meet or Zoom link, or asks to join a meeting.

delorenj/skills

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh HyperFrames build. When in doubt, default to the `hyperframes` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.

delorenj/skills

Generate speech using the self-hosted voxxy (vox) TTS service at https://vox.delo.sh. Use when the user asks to speak, say, narrate, synthesize speech, clone a voice, create a voice, add or register a voice, pipe TTS, or control voice qualities by description (e.g. "a young woman with a cheerful voice"). Handles HTTP API usage, voice profile management, description-based voice design, cloning, MCP registration, and integration patterns for new platforms.

delorenj/skills

YouTube transcripts to summaries, threads, blogs.

相关技能