{"skill":{"slug":"hwp-extract-pipeline","displayName":"Hwp Extract Pipeline","summary":"HWP/HWPX/PDF extraction pipeline: attempt hwp-reader, then pyhwp, then OCR, with safe fallbacks. Use when agent needs reliable text extraction from Korean HW...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":154,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774774845223,"updatedAt":1774775820823},"latestVersion":{"version":"1.0.0","createdAt":1774774845223,"changelog":"Initial release of hwp-extract-pipeline.\n\n- Provides robust extraction of text from HWP/HWPX/PDF (including scanned) files using a prioritized fallback pipeline.\n- Supports extraction via hwp-reader, pyhwp, OCR (poppler+tesseract), and strings as last resort.\n- Outputs extracted text in JSON format to stdout and as a file.\n- Accepts local file paths as input for automated processing.\n- Documentation and example usage available in scripts/README.md.","license":"MIT-0"},"metadata":null,"owner":{"handle":"heoboong","userId":"s17dwrf2qtr2keamkprf9swwt983vznp","displayName":"developheo","image":"https://avatars.githubusercontent.com/u/73891817?v=4"},"moderation":null}