youtube▌

Enable reliable video and audio downloads from YouTube and HLS streaming platforms (Mux, Vimeo, etc.) using yt-dlp and ffmpeg. This skill provides workflows for:

Fetch transcripts from YouTube videos to enable summarization, QA, and content extraction.

This skill helps download transcripts (subtitles/captions) from YouTube videos using yt-dlp.

Extract YouTube transcripts and generate detailed, comprehensive summaries using structured analysis frameworks. \n \n Validates video availability and extracts transcripts using the youtube-transcript-api Python library, with automatic dependency installation if needed \n Applies the STAR + R-I-S-E summarization framework to produce thorough, reference-quality documentation capturing all insights, arguments, and key points \n Supports multiple YouTube URL formats and handles language preference

Download YouTube videos in customizable quality and format with audio-only MP3 support. \n \n Supports six quality presets (best, 1080p, 720p, 480p, 360p, worst) and three video formats (MP4, WebM, Matroska) \n Audio-only downloads extract video as MP3 files for music or podcast extraction \n Automatically installs and uses yt-dlp for robust stream selection and merging \n Configurable output directory; defaults to /mnt/user-data/outputs/ with auto-generated filenames from video titles \n

This skill conducts pure research for YouTube video topics. Execute all steps to produce actionable insights that identify content gaps and analyze competitors. This skill focuses ONLY on research - it does not generate titles, thumbnails, or hooks.

Free, local YouTube operations using yt-dlp. No API keys required, no per-video costs. Works offline after installation.

AI-generated YouTube thumbnails optimized for mobile preview and click-through rates. \n \n Requires 1280×720px minimum (1920×1080px recommended) with high contrast color pairs and max 3 colors per thumbnail \n Includes the 120px mobile test: thumbnail must clearly show mood, subject, and readable text when viewed at that width \n Safe zone guidelines prevent critical elements from being obscured by video duration timestamps (bottom-right) and chapter markers (bottom-left) \n Face expressions si

Intelligent YouTube video clipper with AI-powered chapter analysis, subtitle translation, and batch processing. \n \n Downloads videos and English subtitles, then uses Claude to generate fine-grained chapters (2–5 minute segments) by analyzing subtitle semantics and identifying natural topic transitions \n Supports bilingual subtitle generation (English + Chinese), subtitle burning to video with styled overlays, and social media summary generation for each clip \n Handles environment detection f

Downloads transcripts (subtitles/captions) from YouTube videos. Works with both manually created and auto-generated transcripts. No API key or browser required — uses YouTube's InnerTube API directly and automatically falls back to yt-dlp when YouTube blocks the direct API path.