Youtube transcript

A curated list of skills designed to enhance AI Agents' capabilities across a range of instructions.

Install

npx -y skills add mdonmez/skills --skill youtube-transcript

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

One thing to look at

0 stars0 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

Extract YouTube video transcripts as markdown files using the defuddle CLI tool. Use when the user wants to download, save, or extract a YouTube video's transcript, subtitles, or spoken content as a text or markdown file. Also use when the user shares a YouTube URL and asks to save it, transcribe it, or convert it to notes.

SKILL.md

2.3 KB, 499 tokens by cl100k_base, as published. Nobody here has run it

YouTube Transcript Extractor

Extract YouTube video transcripts and save them as formatted markdown files using defuddle parse.

Workflow

1. Parse the video

Run defuddle parse with the YouTube URL to extract the transcript as markdown:

bunx defuddle parse "<youtube-url>" -m -o <output-path>

Use -m (or --md) to output in markdown format
Use -o to specify the output file path
URL should be a standard YouTube watch URL (e.g., https://www.youtube.com/watch?v=VIDEO_ID)

2. Read the output

Read the generated file to check if the transcript was successfully extracted. Some videos may not have accessible transcripts — in that case the file will only contain the video link.

3. Add title header

Prepend the video title (or user-provided name) and a markdown separator to the top of the file:

<Channel or Video Title>

---

![](https://www.youtube.com/watch?v=VIDEO_ID)

## Transcript
...

Use the edit tool to insert the title and --- separator before the first line of content.

Example

User shares: https://www.youtube.com/watch?v=abc123 and says "save this as notes"

Run: bunx defuddle parse "https://www.youtube.com/watch?v=abc123" -m -o notes.md
Read notes.md to verify transcript content exists
Edit file to add title header: Channel Name\n\n---\n\n![](https://www.youtube.com/watch?v=abc123)

Troubleshooting

Empty transcript (only video link): defuddle could not extract the transcript. This can happen if the video has no subtitles, uses dynamic loading, or has a non-standard page structure. Try re-running once. If it still fails, inform the user.
Debug mode: Add --debug flag to defuddle parse for more verbose output when troubleshooting.

Output format

The final markdown file should look like:

<Channel/Video Title>

---

![](https://www.youtube.com/watch?v=VIDEO_ID)

## Transcript

**0:00** · First line of transcript...
**0:15** · Next line...

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most video audio skills give in 499 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

read individual rule files for detailed explanationsin 21 of 622, across 10 files
render final videoin 13 of 622, across 6 files
Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
Use this skill when dealing with Remotion codein 11 of 622, across 4 files
save generated audio to a WAV filein 11 of 622, across 4 files
handle conversion errors gracefullyin 10 of 622, across 6 files
add captions to videos alwaysin 10 of 622, across 4 files
generate music from text descriptions using MusicGenin 9 of 622, across 2 files
do not skip pipeline layersin 9 of 622, across 3 files
do not make one tool do everythingin 9 of 622, across 3 files
use azure document intelligence for complex pdfsin 9 of 622, across 4 files
never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

run defuddle parse with the youtube url
read the generated file to verify content
prepend video title to the file
insert a separator after the title
re-run parse once if transcript is empty

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.