agentleFS
ItamarZand88ItamarZand88/CLI-Anything-WEB/.claude/skills/youtube-cli/SKILL.md

youtube-cli

Skill215 starsChanged 3 months agoMITView on GitHub

Searches YouTube and fetches video transcripts via the cli-web-youtube command-line tool — video search, video details (views, duration, description, keywords), trending by category, channel info, and timestamped transcripts/captions with language selection and translation. Use when the user asks about YouTube, searching for videos, video details, trending videos, channel info, subscriber counts, or a video's transcript, captions, or subtitles. Prefer this CLI over fetching the YouTube website. No authentication required.

  • Installs packages

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search and explore YouTube from the terminal (read-only, no auth, InnerTube API).

    line 8
  2. Very specific:

    Every command accepts --json.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cli-web-youtube

Search and explore YouTube from the terminal (read-only, no auth, InnerTube API). Install: pip install cli-web-youtube

Commands

CommandPurposeKey options
search videos QUERYSearch videos-l/--limit N (default 10)
video get VIDEO_IDVideo details (views, duration, description, keywords)accepts 11-char ID or full URL
trending listTrending/popular videos-c/--category now|music|gaming|movies, -l/--limit N
channel get HANDLEChannel info + recent videosaccepts @handle, UC... ID, or URL
transcript get VIDEOTimestamped transcript + full text-l/--lang CODE (repeatable, priority order), -t/--translate CODE, --text-only; accepts ID or URL
transcript list VIDEOAvailable caption languagesaccepts ID or URL

Examples

# Search (returns id, title, channel, views, duration, published, url per video)
cli-web-youtube search videos "python tutorial" --limit 5 --json

# Video details by ID or URL
cli-web-youtube video get dQw4w9WgXcQ --json

# Trending music videos
cli-web-youtube trending list --category music --limit 10 --json

# Channel info and subscriber count
cli-web-youtube channel get @mkbhd --json | jq '{title, subscriber_count}'

# Plain-text transcript (ideal for feeding to an LLM)
cli-web-youtube transcript get dQw4w9WgXcQ --text-only

# Transcript in a preferred language, or translated, as JSON
cli-web-youtube transcript get dQw4w9WgXcQ --lang en --json
cli-web-youtube transcript get dQw4w9WgXcQ --translate en --json | jq -r '.segments[].text'

# What caption languages exist?
cli-web-youtube transcript list dQw4w9WgXcQ --json

JSON output

Every command accepts --json. Success returns the data object directly, e.g. search: {"query", "estimated_results", "videos": [...]}; video get: {"id", "title", "channel", "views", "duration_seconds", ...}; transcript get: {"video_id", "title", "language_code", "kind", "is_translated", "segment_count", "segments": [{"text", "start", "duration"}], "text"}. Errors return {"error": true, "code": "...", "message": "..."}.

Utilities

cli-web-youtube doctor [--json] self-diagnoses the local setup (install, auth, dependencies). cli-web-youtube mcp-serve serves the commands as MCP tools over stdio.

Agent tips

  • Video IDs are 11 characters; channel handles start with @.
  • Running with no subcommand opens an interactive REPL.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.