agentleFS
Sign inStart free
AbilityaiAbilityai/cornelius/.claude/skills/get-youtube-transcript/SKILL.md

get-youtube-transcript

Skill109 starsChanged 37 days agoMITView on GitHub

Extract the transcript from a YouTube video by URL or video ID. Use when the user shares a YouTube link and wants the transcript, captions, or text content of the video. Falls back automatically if the requested language isn't available.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the wrapper script with the URL or video ID the user provided:

    line 26
  2. Distinctive:

    If the script fails:

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Get YouTube Transcript

Extract a full transcript from any YouTube video using the local youtube-transcript-api (no rate limits, no API key required).

State Dependencies

SourceLocationReadWrite
Scriptscripts/utilities/yt-transcript.sh✓-
Venvscripts/utilities/yt_transcript_venv/✓-
YouTubeExternal (via youtube-transcript-api)✓-

Process

Step 1: Extract the transcript

Run the wrapper script with the URL or video ID the user provided:

$PROJECT_ROOT/scripts/utilities/yt-transcript.sh "<url-or-id>"

Options:

  • -l <lang> — language code (default: en). If user specifies a language, pass it.
  • -f text — plain text output (default, best for reading)
  • -f json — structured output with timestamps (use when user needs timestamps)

Step 2: Handle errors

If the script fails:

  1. Language not found — retry without -l flag (auto-selects any available language)
  2. Video unavailable — inform user the video may be private, deleted, or region-restricted
  3. No transcript available — inform user the video has no captions

Step 3: Present the transcript

Return the full transcript text to the user. If it's long (>500 lines), summarize what the video covers first, then provide the full text.

Example

User: "get me the transcript of https://youtu.be/abc123"

$PROJECT_ROOT/scripts/utilities/yt-transcript.sh "https://youtu.be/abc123"

Notes

  • Uses youtube-transcript-api Python package — works locally with no quota
  • Falls back to any available language if English isn't found
  • The MCP youtube-transcript tool hits rate limits; always prefer this script

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free