agentleFS
Sign inStart free
feiskyerfeiskyer/codex-settings/skills/youtube-transcribe-skill/SKILL.md

youtube-transcribe-skill

Skill248 starsChanged 4 months agoMITView on GitHub

Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally. Use when the user wants the spoken content of a YouTube video as text.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the bundled scripts/transcribe_youtube.py wrapper for the primary workflow.

    line 8
  2. Distinctive:

    Keep the output in the user's current working directory unless they request another location.

    line 14
  3. Distinctive:

    Run without browser cookies first:

    line 20
  4. Distinctive:

    Do not read browser cookies by default.

    line 46
  5. Distinctive:

    Ask the user which browser profile they approve using.

    line 49
  6. Distinctive:

    Never print, copy, or persist browser cookies in the transcript or logs.

    line 59
  7. Very specific:

    Use browser automation only when yt-dlp is unavailable or cannot obtain subtitles and an appropriate browser-control capability is …

    line 63
  8. Distinctive:

    If neither CLI extraction nor browser automation is available, report the missing capability instead of claiming success.

    line 70

≈ “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

YouTube Transcript Extraction

Use the bundled scripts/transcribe_youtube.py wrapper for the primary workflow. It downloads subtitles with yt-dlp, selects the preferred language, converts WebVTT cues into timestamped plain text, and reports the output path and line count.

Requirements

  1. Install yt-dlp and confirm yt-dlp --version succeeds.
  2. Resolve the absolute directory containing this SKILL.md; refer to it as <skill-dir>.
  3. Keep the output in the user's current working directory unless they request another location.

The Python wrapper itself uses only the standard library. It can display --help without yt-dlp being installed.

Primary workflow

Run without browser cookies first:

python3 "<skill-dir>/scripts/transcribe_youtube.py" \
  "<youtube-url>" \
  --output-dir "$PWD"

The default language preference is Simplified Chinese, Traditional Chinese, other Chinese variants, then English. Override it when the user requests another language:

python3 "<skill-dir>/scripts/transcribe_youtube.py" \
  "<youtube-url>" \
  --languages "ja.*,en.*" \
  --output-dir "$PWD"

The wrapper supports normal watch URLs plus youtu.be, Shorts, live, and embed URLs. A successful run writes one .txt file whose non-empty lines use this shape:

00:03 Subtitle text
00:08 Next subtitle text

Cookie retry

Do not read browser cookies by default. If the initial command fails specifically because the video requires sign-in, age verification, membership, or another authenticated session:

  1. Explain that the retry will let yt-dlp read YouTube cookies from a local browser profile.
  2. Ask the user which browser profile they approve using.
  3. Retry only after approval:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
  "<youtube-url>" \
  --cookies-from-browser chrome \
  --output-dir "$PWD"

Never print, copy, or persist browser cookies in the transcript or logs.

Browser fallback

Use browser automation only when yt-dlp is unavailable or cannot obtain subtitles and an appropriate browser-control capability is available.

  1. Inspect the tools available in the current session; do not assume fixed MCP server or tool names.
  2. Open the video, reveal the transcript panel, and extract visible timestamp/text pairs.
  3. Save the result as <sanitized-video-title>.txt in the requested directory.
  4. Close pages or sessions opened solely for this task.

If neither CLI extraction nor browser automation is available, report the missing capability instead of claiming success.

Completion report

Return:

  1. Absolute transcript path
  2. Selected subtitle language
  3. Number of transcript lines
  4. Whether browser cookies or browser automation were used

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