feat: add video tutorial scraping pipeline with per-panel OCR and AI enhancement
Add complete video tutorial extraction system that converts YouTube videos
and local video files into AI-consumable skills. The pipeline extracts
transcripts, performs visual OCR on code editor panels independently,
tracks code evolution across frames, and generates structured SKILL.md output.
Key features:
- Video metadata extraction (YouTube, local files, playlists)
- Multi-source transcript extraction (YouTube API, yt-dlp, Whisper fallback)
- Chapter-based and time-window segmentation
- Visual extraction: keyframe detection, frame classification, panel detection
- Per-panel sub-section OCR (each IDE panel OCR'd independently)
- Parallel OCR with ThreadPoolExecutor for multi-panel frames
- Narrow panel filtering (300px min width) to skip UI chrome
- Text block tracking with spatial panel position matching
- Code timeline with edit tracking across frames
- Audio-visual alignment (code + narrator pairs)
- Video-specific AI enhancement prompt for OCR denoising and code reconstruction
- video-tutorial.yaml workflow with 4 stages (OCR cleanup, language detection,
tutorial synthesis, skill polish)
- CLI integration: skill-seekers video --url/--video-file/--playlist
- MCP tool: scrape_video for automation
- 161 tests passing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
62071c4aa9