youtube-clip-extractor

原文涵盖的主题

• YouTube Clip Extractor
• Overview
• When to Use This Skill
• Prerequisites
• Required Tools (install via Homebrew)
• File Location
• The 4-Phase Workflow
• Phase 1: Download Video & Transcript

This skill downloads YouTube videos, analyzes transcripts for compelling clip moments, extracts clips using ffmpeg, and generates platform-ready on-screen text and captions. It integrates with the existing caption and social content skills to deliver complete, publishable assets. You have a YouTube URL and want to extract the best clips You want automated clip identification based on hook/coda criteria You need clips cut and ready for Descript or other editors You want on-screen text hooks and platform-specific captions for each clip Do NOT use for: Full podcast production workflow (use podcast-production skill instead) Text-only social posts (use social-content-creation skill) Already-downloaded videos (skip to Phase 2) -- All downloads go to your project's transcript folder (customizable). Structure: -- Goal: Get video and subtitles from YouTube URL Use H.264 format for Descript compatibility (NOT AV1): {videoid}.mp4 - Full video (H.264) {videoid}.en.vtt - Timestamped subtitles -- Goal: Identify 5-8 compelling clip moments with strong hooks and codas A good clip has: 1. Strong Hook (First 3 Seconds) Polarizing statement ("Most people get this completely wrong") Counter-intuitive

这里只展示节选，请以完整原文和当前要求为准。