youtube – OpenClaw Skill

---

name: youtube description: | The most comprehensive YouTube skill for AI agents. Extract transcripts for FREE (zero API quota!), search with filters, batch video details, read comments, download videos/audio. We analyzed 15+ YouTube tools and built the one that does everything. homepage: https://github.com/openclaw/openclaw/tree/main/skills/youtube metadata: { "openclaw": { "emoji": "📺", "requires": { "bins": ["uv"] }, "install": [ { "id": "uv-brew", "kind": "brew", "formula": "uv", "bins": ["uv"], "label": "Install uv (brew)", }, { "id": "ytdlp-brew", "kind": "brew", "formula": "yt-dlp", "bins": ["yt-dlp"], "label": "Install yt-dlp for downloads (optional)", }, ], }, }

YouTube Research Pro

The most comprehensive YouTube skill for AI agents.

We analyzed 15+ YouTube MCP servers and found each does one thing well, but none does everything. So we built the skill we wished existed.

Why This Skill?

What Others Do	What We Do
Transcripts OR search OR downloads	All three, unified
Burn API quota on transcripts	FREE transcripts (zero quota)
Single video at a time	Batch operations (50 videos)
Basic search	Filtered search (date, duration, order)
Text output only	JSON export for pipelines

The Killer Feature: FREE Transcripts

Most tools use the YouTube Data API for transcripts = 100 quota units per request. Daily limit is 10,000 units = only ~100 transcripts/day.

We use youtube-transcript-api — extracts directly from YouTube's frontend. Zero API quota. Unlimited transcripts.

Quick Reference

Command	Quota	What it does
transcript VIDEO	FREE	Get video transcript
transcript-list VIDEO	FREE	List available languages
download VIDEO	FREE	Download video (yt-dlp)
download-audio VIDEO	FREE	Extract audio only
search QUERY	100	Search videos
video ID [ID...]	1/video	Get details (batch!)
comments VIDEO	1	Get comments + replies
channel [ID]	1-3	Channel statistics

Setup (One Time)

# 1. Get credentials from Google Cloud Console
#    - Create OAuth 2.0 Client ID (Desktop app)
#    - Download JSON

# 2. Save credentials
mkdir -p ~/.config/youtube-skill
mv ~/Downloads/client_secret*.json ~/.config/youtube-skill/credentials.json

# 3. Authenticate
uv run {baseDir}/scripts/youtube.py auth

Transcripts (FREE!)

# Plain text transcript
uv run {baseDir}/scripts/youtube.py transcript VIDEO_ID

# With timestamps
uv run {baseDir}/scripts/youtube.py transcript VIDEO_ID --timestamps

# Specific language (falls back to available)
uv run {baseDir}/scripts/youtube.py transcript VIDEO_ID -l es

# List what's available
uv run {baseDir}/scripts/youtube.py transcript-list VIDEO_ID

# JSON output
uv run {baseDir}/scripts/youtube.py transcript VIDEO_ID --json

Works with URLs too:

uv run {baseDir}/scripts/youtube.py transcript "https://youtube.com/watch?v=dQw4w9WgXcQ"

Search

# Basic search
uv run {baseDir}/scripts/youtube.py search "AI news 2026"

# With filters
uv run {baseDir}/scripts/youtube.py search "tutorial" -l 20 --order date
uv run {baseDir}/scripts/youtube.py search "lecture" --duration long
uv run {baseDir}/scripts/youtube.py search "news" --published-after 2026-01-01T00:00:00Z

Video Details (Batch Supported)

# Single video
uv run {baseDir}/scripts/youtube.py video dQw4w9WgXcQ

# Multiple videos at once (up to 50)
uv run {baseDir}/scripts/youtube.py video id1 id2 id3 id4 id5

# JSON output for processing
uv run {baseDir}/scripts/youtube.py video id1 id2 --json

Comments

# Top comments
uv run {baseDir}/scripts/youtube.py comments VIDEO_ID

# With replies
uv run {baseDir}/scripts/youtube.py comments VIDEO_ID --replies

# Recent comments
uv run {baseDir}/scripts/youtube.py comments VIDEO_ID --order time -l 50

Downloads (requires yt-dlp)

# Video (best quality)
uv run {baseDir}/scripts/youtube.py download VIDEO_ID

# Specific resolution
uv run {baseDir}/scripts/youtube.py download VIDEO_ID -r 720p

# With subtitles
uv run {baseDir}/scripts/youtube.py download VIDEO_ID -s en

# Audio only (MP3)
uv run {baseDir}/scripts/youtube.py download-audio VIDEO_ID

# Audio as M4A
uv run {baseDir}/scripts/youtube.py download-audio VIDEO_ID -f m4a

User Data

uv run {baseDir}/scripts/youtube.py subscriptions
uv run {baseDir}/scripts/youtube.py playlists
uv run {baseDir}/scripts/youtube.py playlist-items PLAYLIST_ID
uv run {baseDir}/scripts/youtube.py liked
uv run {baseDir}/scripts/youtube.py channel

Command Aliases

Full	Alias
transcript	tr
search	s
video	v
comments	c
download	dl
download-audio	dla

Use Cases

Research: Fetch transcript → analyze with LLM → extract insights

Learning: Batch transcripts from playlist → create study notes

Monitoring: Search recent videos → extract transcripts → track trends

Podcasts: Download audio for offline listening

Analysis: Get channel stats → compare competitors

Multi-Account

uv run {baseDir}/scripts/youtube.py -a work subscriptions
uv run {baseDir}/scripts/youtube.py -a personal liked

Why We Built This

We surveyed the landscape:

• kimtaeyoon83/mcp-server-youtube-transcript (463⭐) — Great transcripts, no search
• kevinwatt/yt-dlp-mcp (211⭐) — Great downloads, no transcripts
• dannySubsense/youtube-mcp-server (9⭐) — Most functions, but uses paid API for transcripts
• kirbah/mcp-youtube (9⭐) — Batch ops, but no free transcripts

None combined free transcripts + search + downloads + batch ops.

Now one does.

📺 YouTube Research Pro

The most comprehensive YouTube skill for AI agents.

Extract transcripts for FREE, search videos, analyze channels, download content — all from one unified interface.

---

Why This Skill?

We analyzed 15+ YouTube MCP servers and found that each one does one thing well, but none does everything. So we built the skill we wished existed.

What Others Do	What We Do
Transcripts OR search OR downloads	All three, unified
Burn API quota on transcripts	FREE transcripts (zero quota)
Single video at a time	Batch operations (50 videos)
Basic search	Filtered search (date, duration, order)
Text output only	JSON export for pipelines

The Killer Feature: FREE Transcripts

Most YouTube tools use the official YouTube Data API for transcripts, which costs 100 quota units per request. With a daily limit of 10,000 units, you can only fetch ~100 transcripts per day.

We use youtube-transcript-api — a library that extracts transcripts directly from YouTube's frontend, costing zero API quota. Fetch unlimited transcripts, every day.

---

What Can Your Agent Do With This?

🔍 Research & Analysis

• Search YouTube with filters (date, duration, view count)
• Get video details in batch (up to 50 at once)
• Extract full transcripts for content analysis
• Read comments to gauge audience sentiment

📝 Content Extraction

• Pull transcripts in any available language
• Get timestamped transcripts for precise references
• Export everything as JSON for further processing

📥 Downloads

• Download videos at any resolution
• Extract audio only (podcasts, music, interviews)
• Grab subtitles as separate files

📊 Channel Intelligence

• Analyze channel statistics
• Track subscriber counts and view totals
• List and explore playlists

---

Quick Examples

# Get a video transcript (FREE - no API quota!)
uv run youtube.py transcript dQw4w9WgXcQ

# With timestamps
uv run youtube.py transcript dQw4w9WgXcQ --timestamps

# Search with filters
uv run youtube.py search "machine learning" --duration long --order viewCount

# Batch video details
uv run youtube.py video id1 id2 id3 id4 id5 --json

# Download audio as MP3
uv run youtube.py download-audio VIDEO_ID -f mp3

# Get top comments with replies
uv run youtube.py comments VIDEO_ID --replies

---

Complete Command Reference

Transcripts (FREE - Zero API Quota)

Command	Description
transcript VIDEO	Extract transcript as plain text
transcript VIDEO --timestamps	Include [MM:SS] timestamps
transcript VIDEO -l es,en	Prefer Spanish, fall back to English
transcript VIDEO --json	Output as JSON array
transcript-list VIDEO	List all available languages

Search & Discovery

Command	Description
search QUERY	Search YouTube videos
search QUERY -l 20	Return 20 results (default: 10)
search QUERY --order date	Sort by upload date
search QUERY --order viewCount	Sort by popularity
search QUERY --duration short	Under 4 minutes
search QUERY --duration long	Over 20 minutes
search QUERY --published-after 2026-01-01T00:00:00Z	Filter by date

Video Information

Command	Description
video ID	Get video details
video ID1 ID2 ID3	Batch mode (up to 50)
video ID --json	JSON output
video ID -v	Include full description

Comments

Command	Description
comments VIDEO	Get top comments
comments VIDEO -l 50	Get 50 comments
comments VIDEO --replies	Include reply threads
comments VIDEO --order time	Sort by newest

Channel & User Data

Command	Description
channel	Your channel info
channel CHANNEL_ID	Specific channel
subscriptions	Your subscriptions
playlists	Your playlists
playlist-items PLAYLIST_ID	Videos in a playlist
liked	Your liked videos

Downloads (requires yt-dlp)

Command	Description
download VIDEO	Download best quality
download VIDEO -r 720p	Specific resolution
download VIDEO -s en	Include subtitles
download VIDEO -o ~/Videos	Custom output folder
download-audio VIDEO	Audio only (MP3)
download-audio VIDEO -f m4a	Audio as M4A

---

API Quota Costs

Operation	Quota Cost	Notes
Transcripts	0	Uses youtube-transcript-api
Downloads	0	Uses yt-dlp
Search	100	Per request
Video details	1	Per video
Comments	1	Per request
Channel info	1-3	Varies

Daily free quota: 10,000 units

Pro tip: For research tasks, always start with transcripts — they're free and contain the most information.

---

Setup

1. Install dependencies

brew install uv yt-dlp  # macOS
# or
pip install uv && pip install yt-dlp  # other

2. Get YouTube API credentials

1. Go to Google Cloud Console
2. Create a project (or select existing)
3. Enable "YouTube Data API v3"
4. Create OAuth 2.0 Client ID (Desktop app)
5. Download JSON → save as ~/.config/youtube-skill/credentials.json

3. Authenticate

uv run youtube.py auth

---

Command Aliases

For faster typing:

Full	Alias
transcript	tr
transcript-list	trl
search	s
video	v
comments	c
channel	ch
subscriptions	subs
playlists	pl
playlist-items	pli
download	dl
download-audio	dla

---

Comparison with Other Tools

Feature	YouTube Research Pro	kimtaeyoon83	kevinwatt/yt-dlp	dannySubsense	kirbah
Free transcripts	✅	✅	❌	❌	❌
Search	✅	❌	✅	✅	✅
Filtered search	✅	❌	✅	❌	❌
Batch operations	✅	❌	❌	❌	✅
Comments	✅	❌	❌	✅	✅
Downloads	✅	❌	✅	❌	❌
Audio extraction	✅	❌	✅	❌	❌
JSON output	✅	❌	❌	❌	✅
Multi-language	✅	✅	✅	❌	❌
URL + ID support	✅	❌	✅	❌	❌

Result: No other skill covers all these capabilities in one package.

---

Use Cases

📚 Research Assistant

"Summarize the key points from this conference talk" → Fetch transcript, analyze with LLM, extract insights

🎓 Learning Helper

"Create study notes from this lecture series" → Batch fetch transcripts from playlist, synthesize content

📰 News Monitoring

"What are people saying about [topic] this week?" → Search recent videos, extract transcripts, analyze trends

🎵 Music/Podcast

"Download this interview as audio for my commute" → Extract audio, convert to MP3

📊 Competitor Analysis

"How is [channel] performing?" → Get channel stats, analyze recent videos, track growth

---

License

MIT — use it, fork it, improve it.

---

Built by Oscar Serra for the OpenClaw community.