Free, local YouTube operations using yt-dlp. No API keys required, no per-video costs. Works offline after installation.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionyoutube-toolsExecute the skills CLI command in your project's root directory to begin installation:
Fetches youtube-tools from casper-studios/casper-marketplace and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate youtube-tools. Access via /youtube-tools in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
10
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
10
stars
Free, local YouTube operations using yt-dlp. No API keys required, no per-video costs. Works offline after installation.
┌─────────────────────────────────────────────────────────────────┐
│ DECISION: YouTube Tools (yt-dlp) vs Apify │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Use youtube-tools (FREE) when: │
│ ├── Downloading videos to local storage │
│ ├── Extracting transcripts/subtitles │
│ ├── Getting video metadata (title, duration, views, etc.) │
│ ├── Bulk downloading playlists or channels │
│ ├── Converting to audio-only (MP3) │
│ └── You want zero API costs │
│ │
│ Use apify-scrapers when: │
│ ├── Scraping YouTube SEARCH results │
│ ├── Getting comments at scale │
│ ├── Channel analytics and statistics │
│ ├── Trending video discovery │
│ └── You need cloud-based processing │
│ │
└─────────────────────────────────────────────────────────────────┘
What do you need?
│
├── Download video(s)
│ ├── Single video → scripts/download_video.py URL
│ ├── Multiple videos → scripts/download_video.py --urls-file list.txt
│ ├── Playlist → scripts/download_video.py "playlist_url"
│ ├── Audio only → scripts/download_video.py URL --audio-only
│ └── Specific quality → scripts/download_video.py URL --quality 720p
│
├── Get transcript/subtitles
│ ├── Auto-generated captions → scripts/get_transcript.py URL
│ ├── Manual subtitles → scripts/get_transcript.py URL --manual-only
│ ├── Specific language → scripts/get_transcript.py URL --lang es
│ └── All available → scripts/get_transcript.py URL --all-langs
│
├── Get video metadata
│ ├── Single video → scripts/get_video_info.py URL
│ ├── Multiple videos → scripts/get_video_info.py --urls-file list.txt
│ └── Playlist info → scripts/get_video_info.py "playlist_url"
│
└── Advanced
├── Age-restricted → scripts/download_video.py URL --cookies-from-browser chrome
├── Private videos → Requires authentication (see references/yt-dlp-guide.md)
└── Live streams → scripts/download_video.py URL --live-from-start
# Install yt-dlp (required)
pip install yt-dlp
# Optional: Install ffmpeg for format conversion
# macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt install ffmpeg
# Windows
winget install ffmpeg
No API keys required! This is completely free.
python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID"
python scripts/download_video.py "https://youtu.be/VIDEO_ID" --quality 1080p
python scripts/download_video.py "https://youtube.com/watch?v=VIDEO_ID" --audio-only
python scripts/download_video.py "https://youtube.com/playlist?list=PLAYLIST_ID" --output-dir ./videos
# Create urls.txt with one URL per line
python scripts/download_video.py --urls-file urls.txt --output-dir ./downloads
python scripts/get_transcript.py "https://youtube.com/watch?v=VIDEO_ID"
python scripts/get_transcript.py "https://youtu.be/VIDEO_ID" --lang es
python scripts/get_video_info.py "https://youtube.com/watch?v=VIDEO_ID"
python scripts/get_video_info.py --urls-file videos.txt --output metadata.json
All outputs save to .tmp/youtube/ by default:
.tmp/youtube/videos/.tmp/youtube/audio/.tmp/youtube/transcripts/.tmp/youtube/metadata/FREE - No API keys, no per-video costs, no subscriptions.
.tmp/ directory--sleep-interval 5 to avoid throttlingCause: Video is private, age-restricted, or region-locked
Solution: Use --cookies-from-browser chrome for age-restricted content
Cause: YouTube changed their page structure
Solution: Update yt-dlp: pip install -U yt-dlp
Cause: Video has no captions (auto or manual)
Solution: Use --list-subs to see available subtitles first
Cause: YouTube throttling or network issues
Solution: Try --concurrent-fragments 4 for faster downloads
Cause: ffmpeg not installed Solution: Install ffmpeg (see Environment Setup)
# 1. Download video
python scripts/download_video.py "URL" --output-dir .tmp/video
# 2. Get transcript
python scripts/get_transcript.py "URL" --output .tmp/transcript.txt
# 3. Use content-generation to summarize
# (transcript file is now ready for summarization)
# 1. Get metadata for research videos
python scripts/get_video_info.py --urls-file research_videos.txt --output .tmp/metadata.json
# 2. Download transcripts for text analysis
python scripts/get_transcript.py --urls-file research_videos.txt --output-dir .tmp/transcripts
# 3. Use parallel-research to analyze content
# Download entire playlist as course modules
python scripts/download_video.py "PLAYLIST_URL" --output-dir .tmp/course --quality 720p
# Get all transcripts for notes
python scripts/get_transcript.py "PLAYLIST_URL" --output-dir .tmp/course/transcripts
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
ailabs-393/ai-labs-claude-skills
Registry listing for youtube-tools matched our evaluation — installs cleanly and behaves as described in the markdown.
Solid pick for teams standardizing on skills: youtube-tools is focused, and the summary matches what you get after install.
Useful defaults in youtube-tools — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
We added youtube-tools from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Keeps context tight: youtube-tools is the kind of skill you can hand to a new teammate without a long onboarding doc.
youtube-tools is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
I recommend youtube-tools for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
youtube-tools fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Registry listing for youtube-tools matched our evaluation — installs cleanly and behaves as described in the markdown.
youtube-tools has been reliable in day-to-day use. Documentation quality is above average for community skills.
showing 1-10 of 47