Menü
Download transcripts for all data folders sequentially. Use for overnight batch processing or when you need to download pending transcripts across all channels and collections.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
| name | download-all-transcripts |
| description | Download transcripts for all data folders sequentially. Use for overnight batch processing or when you need to download pending transcripts across all channels and collections. |
Why? Manually downloading transcripts folder-by-folder is tedious and error-prone. This skill automates overnight batch processing across all channels and collections with built-in rate limiting and resumability.
# Run the unified CLI command
ytscriber download-all
That's it. The command finds all folders with videos.csv, downloads pending transcripts, and resumes safely if interrupted.
Before running, ensure:
videos.csv fileytscriber CLI is installed (pip install -e .)# Check for valid data folders
ls ~/Documents/YTScriber/*/videos.csv
[!TIP] If no
videos.csvfiles exist, first runextract-videosorsync-all-channelsto populate them.
ytscriber download-all
The command will:
videos.csv<folder>/transcripts/[!CAUTION] This is a long-running operation. For a channel with 500 videos, expect 8+ hours. Run overnight or in a
tmux/screensession.
The command outputs real-time progress:
YTScriber - Download All Transcripts
=======================================
Started at: Thu Dec 26 09:00:00 PST 2024
Delay between videos: 60s
Found 12 folders with videos.csv
────────────────────────────────────────
[1/12] Processing: lex-fridman
CSV: ~/Documents/YTScriber/lex-fridman/videos.csv
Output: ~/Documents/YTScriber/lex-fridman/transcripts
On successful completion:
All transcripts downloaded!
Finished at: Thu Dec 26 17:30:00 PST 2024
Summary of folders processed:
- lex-fridman: 342 transcripts
- huberman-lab: 156 transcripts
...
On interruption or IP block:
Simply run the command again. It automatically skips videos where transcript_downloaded=success in the CSV.
Transcripts are saved as markdown with YAML frontmatter:
~/Documents/YTScriber/huberman-lab/
├── videos.csv
└── transcripts/
├── 2024-01-15-abc123XYZ00.md
├── 2024-01-20-def456ABC11.md
└── ...
Each transcript file contains:
---
video_id: abc123XYZ00
video_url: https://www.youtube.com/watch?v=abc123XYZ00
title: "Sleep Optimization Toolkit"
author: Huberman Lab
published_date: 2024-01-15
length_minutes: 135.5
views: 1234567
description: "..."
is_generated: True
---
[Transcript text as continuous paragraph]
| Problem | Cause | Solution |
|---|---|---|
| IP blocked message | YouTube detected automated requests | Switch VPN server, wait 1-2 hours, then resume |
No videos.csv files found | Empty or missing data folders | Run ytscriber extract or ytscriber sync-all first |
| Command exits immediately | No pending transcripts | Check CSVs - all may already be downloaded |
ytscriber: command not found | CLI not installed | Run pip install -e . from repo root |
| Partial download (some videos skipped) | Videos without transcripts/captions | Check YouTube - video may have no captions available |
Running without checking disk space - Transcripts are small (~50KB each), but 10,000 videos = ~500MB. Verify space before overnight runs.
Interrupting during a download - Safe to Ctrl+C between videos. If you interrupt mid-download, that video's transcript may be incomplete. The CSV won't mark it as downloaded, so it will retry.
Running multiple instances - Don't run the command twice simultaneously. The 60s delay assumes single-threaded operation to respect rate limits.
Expecting instant results - The 60s delay is intentional. Faster rates trigger IP blocks. Plan for overnight runs.
Before considering batch download complete:
.md files have valid contenttranscript_downloaded column reflects actual downloads| Scenario | Use |
|---|---|
| Download ALL pending transcripts across all channels | ytscriber download-all (this skill) |
| Download transcripts for a single specific folder | ytscriber download --folder <name> |
transcript_downloaded column in each CSVytscriber CLI (pip install -e .)Basierend auf der SOC-Berufsklassifikation
Generate AI summaries for downloaded YouTube transcripts. Use when you want to add summaries to existing transcript files, batch process transcripts for summarization, summarize a channel's videos, generate frontmatter summaries, or when the user mentions summarize, AI summaries, OpenRouter, or transcript metadata.
Manually add individual YouTube URLs to a custom collection CSV. Use when adding one-off videos to folders like library-of-minds or random, not from a channel extraction.
Consolidate transcripts from a channel into a single file, sorted by date (newest first), up to 800K tokens. Use when preparing transcripts for LLM context or bulk analysis.
Download YouTube transcripts for videos tracked in a CSV file. Use when you need to download transcripts in bulk with progress tracking, fetching transcripts overnight, processing video libraries, or when the user mentions "get transcripts", "download captions", or "bulk transcript download".
Extract video metadata from a YouTube channel and save to CSV for tracking. Use when adding a new channel, extracting conference videos, populating video lists, or when the user mentions "extract videos", "get videos from channel", "add channel", or "video metadata".
Extract videos from all enabled YouTube channels in channels.yaml. Use for batch updating video lists before downloading transcripts overnight, when the user mentions "sync channels", "update video lists", "refresh channels", or before running download-all-transcripts.
