youtube-processor
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseYouTube 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
| Environment | Method |
|---|---|
| Claude Code | Local Python script (Step 1a) |
| Claude.ai / Mac Client | API 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]" --jsonStep 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
undefinedStep 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.mdError Handling
错误处理
| Error | Meaning | What to Do |
|---|---|---|
| "Transcripts disabled" | Creator turned off captions | Video can't be processed |
| "No transcript found" | No English captions available | Try a different video |
| "Video unavailable" | Private, deleted, or age-restricted | Check 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_IDYou do:
- Run:
python3 get_transcript.py --url "https://www.youtube.com/watch?v=VIDEO_ID" - Read the transcript output
- 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:
- 运行:
python3 get_transcript.py --url "https://www.youtube.com/watch?v=VIDEO_ID" - 读取字幕输出
- 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:
- Extract transcript with the Python tool
- Summarize the content
- Format as Obsidian markdown
- Use Write tool to save to Zettelkasten
- 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:
- 使用Python工具提取字幕
- 总结内容
- 整理为Obsidian格式的Markdown
- 使用Write工具保存到Zettelkasten
- 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:
- Extract transcript
- Analyze for newsletter angles (hooks, insights, story beats)
- Present the angles
- 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:
- 提取字幕
- 分析通讯内容角度(钩子、见解、故事脉络)
- 呈现角度建议
- 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-apiInstall if needed:
bash
pip3 install youtube-transcript-apiPython工具需要:
youtube-transcript-api如需安装:
bash
pip3 install youtube-transcript-apiVersion History
版本历史
| Version | Date | Changes |
|---|---|---|
| 1.1 | 2026-01-03 | Added Vercel API for Claude.ai/Mac client support |
| 1.0 | 2026-01-02 | Initial build with transcript extraction |
| 版本 | 日期 | 变更内容 |
|---|---|---|
| 1.1 | 2026-01-03 | 新增Vercel API支持,适配Claude.ai/Mac客户端 |
| 1.0 | 2026-01-02 | 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