pdf2video: Skill for Claude Code

.claude/skills/pdf-to-video/SKILL.md

pdf-to-video is a skill for Claude Code from DangJin/pdf2video. It costs 31 tokens per session (1,221 once invoked), scanned A, original, MIT.

A workflow that turns a PDF document into a showcase video. It reads the document, selects key points and pages, and renders an MP4 video.

In plain words
What is it for?
Use it to extract a title, descriptions, important pages, and page titles from a PDF, create the video configuration, and render the final video.
Why use it?
It turns a static document into a presentation that can show its main content in sequence.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is DangJin/pdf2video's own configuration. It tells Claude Code how to work on pdf2video itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pdf2video configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cp /path/to/source.pdf ./public/document.pdf.

Reuse

Borrowing it

Nothing to install: this file belongs to DangJin/pdf2video. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DangJin/pdf2video/main/.claude/skills/pdf-to-video/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DangJin/pdf2video

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pdf-to-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/dangjin/pdf2video/pdf-to-video/github.svg)](https://agentmods.dev/skills/dangjin/pdf2video/pdf-to-video)
Your own site
<a href="https://agentmods.dev/skills/dangjin/pdf2video/pdf-to-video"><img src="https://agentmods.dev/badge/skills/dangjin/pdf2video/pdf-to-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pdf-to-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/dangjin/pdf2video/pdf-to-video"><img src="https://agentmods.dev/badge/skills/dangjin/pdf2video/pdf-to-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,221 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.01221
Opus 5.5 $0.00012 $0.00488
Sonnet 5.5 $0.00006 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured 2mo ago against content hash f3a6caaebb8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pdf-to-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pdf-to-video/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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
src string 是 PDF 文件路径,相对于 public 目录
title string 否 主标题
subtitle string 否 副标题
highlights number[] 否 要聚焦展示的页码
pageTitles Record<string, string> 否 每页的标题
pageDescriptions Record<string, string> 否 每页的内容描述,底部打字机效果展示
script ScriptItem[] 否 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 }
  ]
}

Read the full file on GitHub · 142 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 142 lines · 31 tokens per session scan A f3a6caaebb8c

Subscribe to this mod's changes

pdf-to-video is a skill published in the GitHub repository DangJin/pdf2video (395 stars, last pushed 9mo ago), licensed MIT. It adds 31 tokens to every session and 1,221 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

pdf-to-video compared with skills from other repositories

pdf-to-video next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pdf-to-videoDangJin/pdf2videoSkill3959mo agoMITA31Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49ktodayMITA48Claude Code
foundry-hosted-agent-validationmicrosoft/agent-frameworkSkill15kyesterdayMITA82Claude Code, Codex
skill-doc-deliverynyldn/claude-octopusSkill4.4kyesterdayMITA29Claude Code
meta-web-to-pdf-briefingopensquilla/opensquillaSkill7.1k6d agoApache-2.0A45Claude Code, Codex
paper-readerhuangkiki/dailypaper-skillsSkill1.3k5d agoApache-2.0A135Claude Code, Codex
chat-complex-documentsvellum-ai/vellum-assistantSkill1.5k2d agoMITA90Claude Code, Codex