youtube
YouTube Data API integration for searching videos, listing subscriptions, playlists, and video details. Use when the user wants to search YouTube, check their subscriptions, browse playlists, get video information, or list liked videos.
Why use this skill?
Master the YouTube skill for OpenClaw. Manage subscriptions, search videos, and browse playlists efficiently via command-line automation and the YouTube API.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/globalcaos/youtube-data-apiWhat This Skill Does
The YouTube skill for OpenClaw provides a robust interface for interacting with the YouTube Data API. It enables users to perform complex media management tasks directly from their terminal or via the OpenClaw agent. Whether you need to search for trending content, manage your subscriptions, or retrieve granular details about specific videos, this skill acts as a command-line wrapper that bridges the gap between your local environment and Google’s vast video platform. Beyond basic search, it supports advanced playlist management, account switching, and detailed metadata retrieval, making it an essential tool for power users and content curators alike.
Installation
To integrate the YouTube skill, first ensure you have the OpenClaw CLI configured. Run the following command in your terminal:
clawhub install openclaw/skills/skills/globalcaos/youtube-data-api
Once installed, you must perform the one-time OAuth authentication. Navigate to the Google Cloud Console to generate your Client ID credentials. Save the resulting JSON file to ~/.config/youtube-skill/credentials.json. Finally, initialize the connection by running uv run {baseDir}/scripts/youtube.py auth. This will trigger an OAuth browser prompt where you can grant the necessary permissions to your account. If you are a user of gogcli, your credentials will be detected and linked automatically.
Use Cases
This skill is perfect for developers building automation pipelines, researchers archiving metadata, and casual users who prefer the speed of a CLI over a web browser. Common use cases include:
- Automating the retrieval of channel metadata or subscriber counts.
- Batch-listing videos from specific playlists to pass into archival tools like yt-dlp.
- Quickly auditing liked videos to find long-forgotten bookmarks.
- Managing multiple identities (e.g., separating 'work' and 'personal' YouTube profiles) using the account flag.
Example Prompts
- "Search for the latest tutorials on Python 3.13 and list the top 10 results."
- "What are my recent subscriptions and are there any new uploads from my favorite tech channels?"
- "List all items in my 'Watch Later' playlist so I can keep track of my backlog."
Tips & Limitations
Note that this skill relies on the YouTube Data API, which has daily quota limits set by Google. Heavy usage, such as rapid searching or listing massive playlists, may hit these caps. For downloading media, this skill does not include a downloader by design; it is best paired with yt-dlp. Always use the -a flag if you manage multiple accounts to ensure actions are executed against the correct profile, preventing accidental data pollution between work and personal environments.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-globalcaos-youtube-data-api": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-read, external-api
Related Skills
jarvis-voice
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
shell-security-ultimate
Classify every shell command as SAFE, WARN, or CRIT before your agent runs it.
memory-pioneer
Benchmark your agent's memory. Contribute anonymized scores to open research. Citizen science for AI memory.
subagent-overseer
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automatic status reporting. Replaces manual heartbeat polling with a deterministic status file the agent reads every 3 minutes. Zero AI tokens for monitoring — pure OS-level process checks and filesystem diffs.
model-router
Automatic LLM model selection for sub-agent tasks. Classifies tasks by complexity and type, then routes to the optimal model (cost vs capability). Use when spawning sub-agents, choosing models for cron jobs, or deciding which model to use for any task. Eliminates manual model specification by providing a decision tree and optional cheap-model classifier for ambiguous cases.