video-transcriptlisted
Install: claude install-skill titouannwtt/claude-tools
# video-transcript
Objective: turn a YouTube video into timestamped text, then understand it from that text.
The script does all the work (zero model tokens). Your role: run it, read the result, repair the script if needed.
## Commands
Script: `~/.claude/skills/video-transcript/scripts/transcript.py`. It always writes JSON to stdout.
1. **Route A, existing subtitles (try first, fast and no video download)**:
`python3 <script> subs "<url>" --lang fr,en --out <folder>`
2. **Route B, audio then local transcription (if route A found nothing)**:
`python3 <script> audio "<url>" --lang fr --model small --out <folder>`
3. **Audio file already present**: `python3 <script> transcribe <file> --out <folder>`
4. **Check the dependencies**: `python3 <script> doctor`
## Exit codes and reaction
| Code | Meaning | Action |
|---|---|---|
| 0 | Success | Read the `.txt` (lines `[hh:mm:ss] text`) or the `.json` (segments). |
| 3 | No subtitles | Run route B (`audio`). |
| 4 | Download blocked (429, 403, "not a bot", blocked IP) | 1. Update yt-dlp (`brew upgrade yt-dlp` or `pip install -U yt-dlp`): a 403 often comes from an outdated version. 2. Rerun. 3. If it still blocks, rerun **only once** with `--use-proxy`. Never use the proxy without a block. |
| 5 | Missing dependency | Install what the message indicates (`pip install -U yt-dlp`, `pip install faster-whisper`, ffmpeg). |
| 2 | Invalid URL or file | Ask for the correct URL. |
| 1 | Unexpected error | Read the message, fix the sc