agentsclimarketplace

Youtube transcript extractor api skill

Skill Pyfagorass/bookofspells/skills/browseract/youtube-transcript-extractor-api-skill

📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.

Install
npx -y skills add Pyfagorass/bookofspells --skill youtube-transcript-extractor-api-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

This skill helps users automatically extract YouTube video transcripts and metadata via the BrowserAct API. The Agent should proactively apply this skill when users express needs like extracting full transcript from a specific YouTube video, getting subtitles and metadata for video content analysis, gathering video titles and likes counts, summarizing YouTube videos without watching them, collecting channel details from a video URL, tracking transcript automation for specific videos, scraping YouTube subtitles for internal knowledge bases, fetching full video content for AI summarization pipelines, downloading structured transcripts from YouTube links, analyzing video text content for media research, monitoring video publisher information and channel links, or building datasets from YouTube video transcripts.

SKILL.md

4.9 KB, 862 tokens by cl100k_base, as published. Nobody here has run it

YouTube Transcript Extractor API Skill

📖 Introduction

This skill provides a one-stop video transcript extraction service using BrowserAct's YouTube Transcript Extractor API template. It can directly extract full video transcripts and metadata from any YouTube video. By simply providing the TargetURL, you can get clean, ready-to-use transcript and metadata.

✨ Features

  1. No hallucinations, ensuring stable and accurate data extraction: Pre-set workflows avoid generative AI hallucinations.
  2. No CAPTCHA issues: No need to handle reCAPTCHA or other verification challenges.
  3. No IP access restrictions or geofencing: No need to deal with regional IP limits.
  4. Faster execution: Compared to pure AI-driven browser automation solutions, task execution is much faster.
  5. High cost-effectiveness: Significantly reduces data acquisition costs compared to AI solutions that consume large amounts of tokens.

🔑 API Key Setup

Before running, you must check the BROWSERACT_API_KEY environment variable. If it is not set, do not take any other actions; you must request and wait for the user to provide it. The Agent must inform the user at this point:

"Since you haven't configured the BrowserAct API Key yet, please go to the BrowserAct Console to get your Key first."

🛠️ Input Parameters

The Agent should configure the following parameter based on the user's needs when calling the script:

  1. TargetURL (Target URL)
    • Type: string
    • Description: The URL of the YouTube video you want to extract the transcript and metadata from.
    • Example: https://www.youtube.com/watch?v=st534T7-mdE

🚀 Usage (Recommended)

The Agent should execute the following independent script to achieve "one command, get results":

# Example Call
python -u ./scripts/youtube_transcript_extractor_api.py "TargetURL"

⏳ Running Status Monitoring

Since this task involves automated browser operations, it may take a long time (several minutes). While running, the script will continuously output status logs with timestamps (e.g., [14:30:05] Task Status: running). Agent Instructions:

  • While waiting for the script to return results, please keep an eye on the terminal output.
  • As long as the terminal continues to output new status logs, it means the task is running normally. Do not misjudge it as a deadlock or unresponsiveness.
  • Only if the status remains unchanged for a long time or the script stops outputting without returning a result, should you consider triggering the retry mechanism.

📊 Data Output Description

After successful execution, the script will parse and print the results directly from the API response. The results include:

  • video_title: The title of the YouTube video
  • video_url: The direct link to the original video
  • publisher: The name of the channel publishing the video
  • channel_link: The URL of the publisher's YouTube channel
  • video_likes_count: The number of likes the video has received
  • transcript: The complete extracted transcript/subtitles of the video

⚠️ Error Handling & Retry

During script execution, if an error occurs (such as network fluctuation or task failure), the Agent should follow this logic:

  1. Check output content:

    • If the output contains "Invalid authorization", it means the API Key is invalid or expired. In this case, do not retry, and guide the user to check and provide the correct API Key.
    • If the output does not contain "Invalid authorization" but the task execution fails (for example, the output starts with Error: or returns an empty result), the Agent should automatically try to execute the script one more time.

  2. Retry limits:

    • Automatic retry is limited to only once. If the second attempt still fails, stop retrying and report the specific error message to the user.

Gives 0 of the 12 instructions most research analysis skills give in 862 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-07

  • generate a markdown reportin 32 of 1063, across 23 files
  • cite each claim's sourcein 30 of 1063, across 15 files
  • define the ideal customer profilein 20 of 1063, across 2 files
  • search for companies matching the criteriain 20 of 1063, across 2 files
  • assign a fit score from one to tenin 20 of 1063, across 2 files
  • analyze the codebase to understand the productin 19 of 1063, across 1 file
  • ask clarifying questions about the value propositionin 19 of 1063, across 1 file
  • look for signals of immediate needin 19 of 1063, across 1 file
  • identify the target decision maker rolein 19 of 1063, across 1 file
  • suggest a personalized contact strategyin 19 of 1063, across 1 file
  • provide conversation starters for outreachin 19 of 1063, across 1 file
  • format results in a scannable markdown templatein 19 of 1063, across 1 file

Said here and by no other author read

  • inform the user to get a key from the console
  • execute the extraction script with a target URL
  • monitor the terminal output during script execution
  • consider continuous log output as normal operation
  • trigger a retry if the status is unchanged for a long time
  • do not retry if the output contains Invalid authorization

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.