youtube-processor

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

YouTube Processor

YouTube Processor

What This Does

功能介绍

Takes a YouTube URL, extracts the transcript, and you (Claude) summarize it. Outputs Obsidian-ready markdown. Zero friction: share a link, get actionable notes.
输入YouTube链接,提取字幕文本,再由你(Claude)进行总结。输出可直接用于Obsidian的Markdown格式。全程无阻碍:分享链接,即可获得实用笔记。

When to Use

使用场景

  • "Summarize this video: [URL]"
  • "Turn this YouTube into notes"
  • "What's this video about?"
  • "Process this for my newsletter"
  • Any YouTube URL shared for processing
  • "总结这个视频:[URL]"
  • "把这个YouTube视频转成笔记"
  • "这个视频讲了什么?"
  • "处理这个内容用于我的通讯"
  • 任何用于处理的YouTube链接分享

Location

工具位置

This skill's tools live at:
/Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools/
本技能的工具存放路径:
/Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools/

How It Works

工作流程

Step 1: Python extracts the transcript (no API key needed) Step 2: You (Claude) summarize using your intelligence + context Step 3: You write the Obsidian-formatted output
This approach means you can use mission-context, newsletter-coach, and other skills during summarization.

步骤1: Python提取字幕文本(无需API密钥) 步骤2: 你(Claude)结合自身智能与上下文进行总结 步骤3: 生成Obsidian格式的输出内容
这种方式意味着你在总结过程中可以使用任务上下文、通讯指导等其他技能。

Instructions

操作指南

Which Method to Use

方法选择

EnvironmentMethod
Claude CodeLocal Python script (Step 1a)
Claude.ai / Mac ClientAPI via WebFetch (Step 1b)

环境方法
Claude Code本地Python脚本(步骤1a)
Claude.ai / Mac客户端通过WebFetch调用API(步骤1b)

Step 1a: Extract Transcript (Claude Code)

步骤1a:提取字幕文本(Claude Code)

Run the Python tool to get the transcript:
bash
cd /Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools && \
python3 get_transcript.py --url "[URL]"
For JSON output (easier to parse):
bash
python3 get_transcript.py --url "[URL]" --json
运行Python工具获取字幕:
bash
cd /Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools && \
python3 get_transcript.py --url "[URL]"
若要输出JSON格式(更易解析):
bash
python3 get_transcript.py --url "[URL]" --json

Step 1b: Extract Transcript (Claude.ai / Mac Client)

步骤1b:提取字幕文本(Claude.ai / Mac客户端)

Use the API endpoint via WebFetch:
WebFetch: https://youtube-processor-eight.vercel.app/transcript?url=[VIDEO_URL]
The API returns JSON:
json
{
  "success": true,
  "video_id": "abc123",
  "language": "en",
  "transcript": "...",
  "char_count": 5000,
  "word_count": 850
}
Example prompt for WebFetch: "Extract the transcript text from the response"

通过WebFetch调用API端点:
WebFetch: https://youtube-processor-eight.vercel.app/transcript?url=[VIDEO_URL]
API返回JSON格式数据:
json
{
  "success": true,
  "video_id": "abc123",
  "language": "en",
  "transcript": "...",
  "char_count": 5000,
  "word_count": 850
}
WebFetch示例提示词: "从响应中提取字幕文本"

Step 2: Summarize the Transcript

步骤2:总结字幕内容

Once you have the transcript, summarize it based on what the user needs:
Quick Summary:
  • Headline (1 sentence)
  • Key points (3-5 bullets)
  • Main takeaway
Detailed Analysis:
  • Headline summary
  • Key points with context
  • Main takeaways
  • Action items mentioned
  • How this relates to Ed's work (if relevant)
Newsletter Mining:
  • Hook ideas for an article
  • Core insight/framework
  • Story beats for anecdotes
  • Takeaways for readers
  • Newsletter angle for The Little Blue Report
获取字幕文本后,根据用户需求进行总结:
快速摘要:
  • 标题(一句话)
  • 关键点(3-5个项目符号)
  • 核心要点
详细分析:
  • 标题摘要
  • 带上下文的关键点
  • 核心要点
  • 提及的行动项
  • 与Ed工作的关联(如相关)
通讯内容挖掘:
  • 文章钩子思路
  • 核心见解/框架
  • 轶事的故事脉络
  • 给读者的要点
  • 《The Little Blue Report》的通讯角度

Step 3: Format for Obsidian

步骤3:Obsidian格式整理

Create markdown with this structure:
markdown
---
source: YouTube
video_id: [ID]
url: [URL]
processed: [YYYY-MM-DD HH:MM]
tags: [youtube, video-notes]
---
按照以下结构生成Markdown:
markdown
---
source: YouTube
video_id: [ID]
url: [URL]
processed: [YYYY-MM-DD HH:MM]
tags: [youtube, video-notes]
---

[Video Title or Topic]

[视频标题或主题]

Link: [URL] Processed: [Date]
链接: [URL] 处理时间: [日期]

Summary

摘要

[Your summary here]

[你的总结内容]

Full Transcript

完整字幕

[The transcript]

Generated by youtube-processor skill
undefined
[字幕文本]

Generated by youtube-processor skill
undefined

Step 4: Save (Optional)

步骤4:保存(可选)

Save to Ed's Zettelkasten:
/Users/eddale/Documents/COPYobsidian/MAGI/Zettelkasten/
Filename format:
YT - [Topic] - YYYY-MM-DD.md

保存到Ed的Zettelkasten:
/Users/eddale/Documents/COPYobsidian/MAGI/Zettelkasten/
文件名格式:
YT - [主题] - YYYY-MM-DD.md

Error Handling

错误处理

ErrorMeaningWhat to Do
"Transcripts disabled"Creator turned off captionsVideo can't be processed
"No transcript found"No English captions availableTry a different video
"Video unavailable"Private, deleted, or age-restrictedCheck the URL

错误信息含义处理方式
"Transcripts disabled"创作者关闭了字幕无法处理该视频
"No transcript found"无可用英文字幕尝试其他视频
"Video unavailable"视频私密、已删除或受年龄限制检查链接

Examples

示例

Example 1: Quick Summary

示例1:快速摘要

User says:
Summarize this: https://www.youtube.com/watch?v=VIDEO_ID
You do:
  1. Run:
    python3 get_transcript.py --url "https://www.youtube.com/watch?v=VIDEO_ID"
  2. Read the transcript output
  3. Provide a summary to the user
用户指令:
总结这个视频:https://www.youtube.com/watch?v=VIDEO_ID
操作流程:
  1. 运行:
    python3 get_transcript.py --url "https://www.youtube.com/watch?v=VIDEO_ID"
  2. 读取字幕输出
  3. 向用户提供摘要

Example 2: Save to Obsidian

示例2:保存到Obsidian

User says:
Turn this video into notes and save it: [URL]
You do:
  1. Extract transcript with the Python tool
  2. Summarize the content
  3. Format as Obsidian markdown
  4. Use Write tool to save to Zettelkasten
  5. Confirm: "Saved to [filepath]"
用户指令:
把这个视频转成笔记并保存:[URL]
操作流程:
  1. 使用Python工具提取字幕
  2. 总结内容
  3. 整理为Obsidian格式的Markdown
  4. 使用Write工具保存到Zettelkasten
  5. 确认:"已保存至[文件路径]"

Example 3: Newsletter Mining

示例3:通讯内容挖掘

User says:
I want to write about this video for the newsletter: [URL]
You do:
  1. Extract transcript
  2. Analyze for newsletter angles (hooks, insights, story beats)
  3. Present the angles
  4. Offer to hand off to newsletter-coach skill

用户指令:
我想把这个视频内容用于通讯:[URL]
操作流程:
  1. 提取字幕
  2. 分析通讯内容角度(钩子、见解、故事脉络)
  3. 呈现角度建议
  4. 可转交给newsletter-coach技能进一步处理

Integration Points

集成点

  • newsletter-coach: After extracting video insights, hand off for article development
  • mission-context: Use Ed's voice and style when summarizing
  • task-clarity-scanner: Action items from videos can be added to daily notes

  • newsletter-coach:提取视频见解后,可转交给该技能进行文章开发
  • mission-context:总结时可使用Ed的语气和风格
  • task-clarity-scanner:视频中的行动项可添加到每日笔记

Dependencies

依赖项

The Python tool requires:
youtube-transcript-api
Install if needed:
bash
pip3 install youtube-transcript-api

Python工具需要:
youtube-transcript-api
如需安装:
bash
pip3 install youtube-transcript-api

Version History

版本历史

VersionDateChanges
1.12026-01-03Added Vercel API for Claude.ai/Mac client support
1.02026-01-02Initial build with transcript extraction
版本日期变更内容
1.12026-01-03新增Vercel API支持,适配Claude.ai/Mac客户端
1.02026-01-02初始版本,支持字幕提取

Notes & Learnings

注意事项与经验总结

  • youtube-transcript-api works without API keys
  • Most videos have auto-generated English captions
  • Claude doing the summarization is better than Python calling the API (can use context)
  • ~3-5 second transcript extraction for typical videos
  • youtube-transcript-api无需API密钥即可使用
  • 大多数视频带有自动生成的英文字幕
  • 由Claude进行总结比Python调用API效果更好(可结合上下文)
  • 典型视频的字幕提取耗时约3-5秒