PD

pdf-to-video

Extracts content from PDFs and renders MP4 video files using Remotion configurations.

Install

mkdir -p .claude/skills/pdf-to-video && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5782" && unzip -o skill.zip -d .claude/skills/pdf-to-video && rm skill.zip

Installs to .claude/skills/pdf-to-video

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when user wants to convert a PDF document into a showcase video, extract key points from PDF, or create video presentation from PDF file
140 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Read local PDF files
  • Analyze PDF content to extract titles and core points
  • Generate configuration files for video rendering
  • Copy PDF files to a public directory
  • Render MP4 videos from PDF content
  • Create videos with different presentation modes like stack, focus, switch, or fan

How it works

The skill reads a PDF, analyzes its content to identify key information like titles and important pages, then generates a JSON configuration file. It copies the PDF to a public directory and uses Remotion to render an MP4 video based on the configuration.

Inputs & outputs

You give it
Local PDF file path
You get back
MP4 video file (out/<name>.mp4) with 1920x1080 resolution at 30fps

When to use pdf-to-video

  • Creating video summaries from reports
  • Automating document showcases
  • Extracting key points for video presentations
  • Generating MP4 from PDF files

About this skill

PDF to Video

将 PDF 文档转换为展示视频,自动提取核心观点并生成动态展示。

工作流程

digraph pdf_to_video {
    rankdir=TB;
    "接收 PDF 路径" -> "读取 PDF 内容";
    "读取 PDF 内容" -> "分析提取核心观点";
    "分析提取核心观点" -> "生成 props.json";
    "生成 props.json" -> "复制 PDF 到 public";
    "复制 PDF 到 public" -> "执行 remotion render";
    "执行 remotion render" -> "输出 MP4 视频";
}

步骤详解

1. 读取 PDF 文件

使用 Read 工具读取用户提供的本地 PDF 文件路径。

2. 分析并提取核心观点

从 PDF 内容中识别:

  • 标题:文档主标题,通常在首页
  • 副标题:可选,如"核心内容概览"
  • 核心观点:3-5 个关键页面及其标题
  • 内容描述:每个关键页面的简要说明(1-2 句话),用于底部打字机效果展示

分析时关注:

  • 章节标题和大纲
  • 重点段落(加粗、高亮)
  • 摘要和结论部分
  • 图表和数据页面

3. 生成配置并渲染

目录结构:

props/           # 配置文件目录
  glm45.json     # 以文档名命名
  report-2024.json
out/             # 输出视频目录
  glm45.mp4
  report-2024.mp4
public/          # 源 PDF 文件
  document.pdf

创建 props/<name>.json

{
  "src": "/document.pdf",
  "title": "文档标题",
  "subtitle": "核心内容概览",
  "highlights": [1, 3, 7, 12, 15],
  "pageTitles": {
    "1": "封面",
    "3": "执行摘要",
    "7": "市场分析"
  },
  "pageDescriptions": {
    "1": "这是文档的封面页,展示了报告的主题和作者信息。",
    "3": "执行摘要概述了报告的核心发现和建议。",
    "7": "市场分析部分详细分析了当前市场趋势和竞争格局。"
  }
}

执行命令:

# 复制 PDF 到 public 目录
cp /path/to/source.pdf ./public/document.pdf

# 写入配置到 props 目录(使用 Write 工具)

# 渲染视频(配置和输出使用相同命名)
npx remotion render PdfShowcase out/<name>.mp4 --props=./props/<name>.json

Props 参数说明

参数类型必填说明
srcstringPDF 文件路径,相对于 public 目录
titlestring主标题
subtitlestring副标题
highlightsnumber[]要聚焦展示的页码
pageTitlesRecord<string, string>每页的标题
pageDescriptionsRecord<string, string>每页的内容描述,底部打字机效果展示
scriptScriptItem[]自定义脚本,完全控制展示流程

场景类型

可通过 script 参数使用不同的展示模式:

类型说明默认时长
stack卡片堆叠展示60 帧
focus聚焦放大某页120 帧
switch滑动切换120 帧
fan扇形轮盘展示150 帧

扇形模式示例:

{
  "script": [
    { "type": "stack", "duration": 60 },
    { "type": "fan", "page": 1, "duration": 150 },
    { "type": "fan", "page": 3, "duration": 150 },
    { "type": "stack", "duration": 120 }
  ]
}

输出

  • 视频文件:out/<name>.mp4
  • 格式:MP4
  • 分辨率:1920x1080
  • 帧率:30fps

示例交互

用户: 帮我把这个 PDF 转成展示视频:/Users/me/docs/report-2024.pdf

执行:

  1. 读取 PDF 内容
  2. 分析识别:标题"2024年度报告",核心观点在第1、3、7、12、15页
  3. 复制 PDF 到 public/report-2024.pdf
  4. 生成配置 props/report-2024.json
  5. 执行 npx remotion render PdfShowcase out/report-2024.mp4 --props=./props/report-2024.json
  6. 告知用户视频已生成在 out/report-2024.mp4

Prerequisites

Remotion

How it compares

This skill automates the creation of a video presentation directly from a PDF document, transforming static content into a dynamic showcase without manual video editing.

Compared to similar skills

pdf-to-video side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pdf-to-video (this skill)36moReviewIntermediate
sora26moReviewIntermediate
ai-media02moNo flagsIntermediate
video-editing04moCautionAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

sora

davila7

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

23

ai-media

arcasilesgroup

Generates images, videos, and audio via AI models (fal-ai MCP): cheap iteration models, expensive production finals, cost-estimate before generation. Trigger for 'generate an image', 'create a thumbnail', 'make a voiceover', 'AI video', 'text to speech for'. Not for design composition; use /ai-visua

00

video-editing

DrinkBoooz

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video

00

general-video

Sma1lboy

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 mar

00

nano-pdf

openclaw

Edit PDFs with natural-language instructions using the nano-pdf CLI.

63300

video-downloader

ComposioHQ

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

101255

Search skills

Search the agent skills registry