技能 youtube-transcript-extractor-api-skill
🌐

youtube-transcript-extractor-api-skill

低风险 🌐 网络访问🔑 环境变量

Extract YouTube Transcripts and Metadata

Users struggle to extract text content from YouTube videos efficiently for analysis. This skill connects to the BrowserAct API to automatically fetch transcripts, titles, likes counts, and channel metadata from any YouTube video URL.

支持: Claude Codex Code(CC)
🥉 73 青铜
1

下载技能 ZIP

2

在 Claude 中上传

前往 设置 → 功能 → 技能 → 上传技能

3

开启并开始使用

测试它

正在使用“youtube-transcript-extractor-api-skill”。 Extract transcript from https://www.youtube.com/watch?v=st534T7-mdE

预期结果:

Returns video title, publisher, channel link, likes count, and complete transcript text ready for analysis

正在使用“youtube-transcript-extractor-api-skill”。 Get metadata for this video without watching it

预期结果:

Provides structured data with video_title, publisher, video_likes_count, and transcript in clean text format

正在使用“youtube-transcript-extractor-api-skill”。 Build a dataset from these video transcripts

预期结果:

Sequential extraction produces clean transcript text from multiple videos, formatted for dataset use

安全审计

低风险
v1 • 4/28/2026

The skill uses environment variable access for API key configuration and makes outbound HTTP requests to the BrowserAct API. These are legitimate patterns for external API integrations. No command injection, code execution, or credential exfiltration risks were confirmed. The skill is safe for publication with low risk profile.

2
已扫描文件
176
分析行数
4
发现项
1
审计总数
中风险问题 (1)
scripts/youtube_transcript_extractor_api.py:92
API Key Required for Operation
The skill requires BROWSERACT_API_KEY environment variable to function. This is legitimate credential management, not a security risk.
低风险问题 (1)
scripts/youtube_transcript_extractor_api.py:15scripts/youtube_transcript_extractor_api.py:32scripts/youtube_transcript_extractor_api.py:53scripts/youtube_transcript_extractor_api.py:78scripts/youtube_transcript_extractor_api.py:101
Hardcoded API Endpoint URL
The script uses a hardcoded BrowserAct API base URL. This is expected for a skill designed to work with a specific external service.

风险因素

🌐 网络访问 (5)
scripts/youtube_transcript_extractor_api.py:32 scripts/youtube_transcript_extractor_api.py:53 scripts/youtube_transcript_extractor_api.py:78 scripts/youtube_transcript_extractor_api.py:15 scripts/youtube_transcript_extractor_api.py:101
🔑 环境变量 (1)
scripts/youtube_transcript_extractor_api.py:92
审计者: claude

质量评分

45
架构
100
可维护性
87
内容
50
社区
83
安全
91
规范符合性

你能构建什么

Video Content Analysis

Extract transcript text from YouTube videos for AI-powered analysis, summarization, or sentiment analysis without manual transcription.

Dataset Building

Automate collection of video transcripts and metadata to build training datasets for machine learning models.

Content Summarization Pipeline

Integrate transcript extraction into automated workflows that feed video content into summarization or note-taking systems.

试试这些提示

Basic Transcript Extraction 
Use the youtube-transcript-extractor-api-skill to extract the transcript from this YouTube video: [VIDEO_URL]
Extract with Metadata 
Extract the transcript, title, likes count, and channel information from [VIDEO_URL] using the youtube-transcript-extractor-api-skill.
Batch Processing Setup 
I need to extract transcripts from multiple YouTube videos for analysis. Set up a workflow using youtube-transcript-extractor-api-skill to process these URLs: [URL_1], [URL_2], [URL_3]
Summarization Pipeline 
Use youtube-transcript-extractor-api-skill to get the transcript from [VIDEO_URL], then summarize the key points.

最佳实践

  • Always verify BROWSERACT_API_KEY is configured before attempting extraction
  • Check error messages for authorization issues versus task failures to retry appropriately
  • Allow sufficient time for task completion as automated browser operations may take several minutes

避免

  • Do not attempt extraction without a valid API key configured
  • Do not retry on authorization errors; guide user to check API key instead
  • Do not assume transcripts exist for all videos (private or restricted videos may fail)

常见问题

What API key do I need?
You need a BrowserAct API key. Sign up at browseract.com and get your key from the integrations page.
Does this work with private videos?
No. This skill cannot extract transcripts from private, unlisted, or age-restricted YouTube videos.
How long does extraction take?
The automated browser operations typically take 1-5 minutes depending on video length and server load.
What data does it return?
It returns the video title, publisher name, channel link, likes count, and the complete transcript text.
Can I extract from multiple videos?
Yes. Call the skill multiple times with different URLs, or use the skill in a loop for batch processing.
What happens if the task fails?
If it is an authorization error, do not retry. For other errors, the skill will retry once automatically before reporting the issue.

开发者详情

许可证

MIT

仓库

https://github.com/browser-act/skills/tree/main/solutions/video-platforms/youtube-transcript-extractor-api-skill

引用

main

文件结构

📁 scripts/

📄 youtube_transcript_extractor_api.py

📄 SKILL.md