youtube transcript

Data Community

Skill notes

Purpose

Fetch a YouTube video's transcript using youtube-transcript-api. Reference: https://gist.github.com/intellectronica/6178110791dc19a05d7c0173118fd48e

Run

With timestamps: Save to a file:

Output Rules

Do not alter transcript wording. Without timestamps, it is acceptable to rewrap lines into complete paragraphs if the user asked for readable text. With timestamps, preserve one caption segment per line. If the user asks to save the transcript, write it to the requested path. If no output file is specified but a file is needed, use <video-id>-transcript.txt.

Supported Inputs

https://www.youtube.com/watch?v=VIDEO_ID https://youtu.be/VIDEO_ID https://youtube.com/embed/VIDEO_ID https://youtube.com/v/VIDEO_ID Raw 11-character video ID

Notes

Captions must be available on the video. The script first tries the default transcript fetch, then falls back to the first available transcript language.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Data
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@yutakobayashidev · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
External requests
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Author source file SKILL.md

# YouTube Transcript

## Purpose

Fetch a YouTube video's transcript using `youtube-transcript-api`.

Reference: https://gist.github.com/intellectronica/6178110791dc19a05d7c0173118fd48e

## Run

```bash
nix-shell -p 'python312.withPackages (ps: [ ps.youtube-transcript-api ])' --run 'python {baseDir}/scripts/get_transcript.py "VIDEO_URL_OR_ID"'
```

With timestamps:

```bash
nix-shell -p 'python312.withPackages (ps: [ ps.youtube-transcript-api ])' --run 'python {baseDir}/scripts/get_transcript.py "VIDEO_URL_OR_ID" --timestamps'
```

Save to a file:

```bash
nix-shell -p 'python312.withPackages (ps: [ ps.youtube-transcript-api ])' --run 'python {baseDir}/scripts/get_transcript.py "VIDEO_URL_OR_ID" --timestamps' > transcript.txt
```

## Output Rules

- Do not alter transcript wording.
- Without timestamps, it is acceptable to rewrap lines into complete paragraphs if the user asked for readable text.
- With timestamps, preserve one caption segment per line.
- If the user asks to save the transcript, write it to the requested path.
- If no output file is specified but a file is needed, use `<video-id>-transcript.txt`.

## Supported Inputs

- `https://www.youtube.com/watch?v=VIDEO_ID`
- `https://youtu.be/VIDEO_ID`
- `https://youtube.com/embed/VIDEO_ID`
- `https://youtube.com/v/VIDEO_ID`
- Raw 11-character video ID

## Notes

- Captions must be available on the video.
- The script first tries the default transcript fetch, then falls back to the first available transcript language.

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.