video-clip-pipeline

1# Long-Form Video Clip Pipeline
2 
3## Preamble (runs on skill start)
4 
5```bash
6# Version check (silent if up to date)
7python3 telemetry/version_check.py 2>/dev/null || true
8 
9# Telemetry opt-in (first run only, then remembers your choice)
10python3 telemetry/telemetry_init.py 2>/dev/null || true
11```
12 
13> **Privacy:** This skill logs usage locally to `~/.ai-marketing-skills/analytics/`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry/README.md`.
14 
15---
16 
17AI-powered pipeline that converts long-form YouTube episodes into standalone highlight clips. Download → Transcribe → AI Segment → Cut → Upload. A 60-minute episode becomes 3–5 clips in ~15 minutes.
18 
19## When to Use
20 
21Use this skill when:
22- Converting long-form YouTube content (podcasts, interviews, talks) into highlight clips
23- Processing a YouTube back catalog into a clips channel
24- Finding the best standalone segments from video transcripts
25- Cutting video clips with verified sentence boundaries
26- Running a high-volume clip publishing operation ($0.50–1.00 per episode)
27 
28## Prerequisites
29 
30### System Tools
31 
32```bash
33brew install yt-dlp ffmpeg        # macOS
34# Or: apt install ffmpeg && pip install yt-dlp  # Linux
35pip install openai-whisper
36```
37 
38### Environment Variables
39 
40- `ANTHROPIC_API_KEY` — Claude API key (required for segmentation)
41- YouTube Data API credentials (optional, for automated upload)
42 
43## Tools
44 
45### End-to-End Pipeline
46 
47| Script | Purpose | Key Command |
48…