This skill helps users automatically extract YouTube video transcripts and metadata in batch via the BrowserAct API. The Agent should proactively apply this skill when users express needs like batch extract full transcripts from YouTube videos for specific keywords, scrape YouTube subtitles for a list of videos, get batch video metadata and likes counts for analysis, automate YouTube search and subtitle extraction, collect multiple video transcripts published this week, download bulk YouTube vid
SkillScore82Maintained
Automatic
◆Data Engineer pack
Last verified 8/9/2026
What it changes
Passed 16 of 19 test cases with the skill, and 4 of 19 without it.
Without skill23%
With skill82%
Checks it passed that the model alone missed
Sets the Datelimit argument to 5 by default
Limits automatic retry attempts to exactly one rerun
Sets the Upload_date argument to This week by default
and 15 more in the full report
13 fixed5 passed either way4 still failing0 broke
Pass-rate lift
+59 pp
Tokens
+12%
Agent turns
0%
Response time
-58%
Model gemini-3.6-flashMeasured 8/9/2026v118 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
Where is the standalone YouTube batch transcript extractor script located within the project repository?
What was checked, without and with the skill
Checked
Without skill
With skill
Refers to ./scripts/youtube_batch_transcript_extractor_api.py
Missed
Passed
case-19 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md70 lines2 filesincludes scripts
YouTube Batch Transcript Extractor API Skill
📖 Introduction
This skill uses the BrowserAct YouTube Batch Transcript Extractor API template to provide users with an automated service for extracting YouTube video transcripts and metadata in batch. Simply by providing search keywords and filters, you can batch extract full video transcripts, likes, and channel metadata without writing crawler scripts.
✨ Features
No hallucinations, ensuring stable and accurate data extraction: Pre-set workflows avoid generative AI hallucinations.
No CAPTCHA issues: No need to handle reCAPTCHA or other verification challenges.
No IP access restrictions or geofencing: No need to deal with regional IP restrictions.
Faster execution: Tasks execute faster compared to pure AI-driven browser automation solutions.
High cost-effectiveness: Significantly reduces data acquisition costs compared to AI solutions that consume a large number of tokens.
🔑 API Key Guide Process
Before running, you must check the BROWSERACT_API_KEY environment variable. If it is not set, do not take any other actions; you should request and wait for the user to provide it collaboratively.
The Agent must inform the user at this time:
"Since you have not yet configured the BrowserAct API Key, please go to the BrowserAct Console to get your Key first."
🛠️ Input Parameters
When calling the script, the Agent should flexibly configure the following parameters based on user needs:
KeyWords
Type: string
Description: The keyword to search for on YouTube.
Example: OpenClaw, AI Automation
Upload_date
Type: string
Description: Filter for the upload date of the videos.
Optional values: Today, This week, This month, This year.
Default value: This week
Datelimit
Type: number
Description: The number of videos to extract. Adjust as needed.
Default value: 5
Recommendation: Set a smaller value (1-5) for quick tests and a larger value for bulk extraction.
🚀 Invocation Method (Recommended)
The Agent should execute the following independent script to achieve "one-line command to get results":
This skill helps users extract YouTube influencer profiles including social links, subscriber counts, and channel stats via the BrowserAct API. Agent should proactively apply this skill when users express needs like finding YouTube creators for specific keywords, discovering influencers for a marketing campaign, extracting YouTube channel contact emails, scraping YouTube influencer social media links, gathering subscriber counts for YouTube creators, researching top YouTube channels in a specifi