prepare-ocr-sibling

star 1

Produce a clean-text .txt sibling for an OCR-scanned primary source via a VLM page-image read, then confirm it against PaddleOCR (a different tool). An OCR-scan source's pdftotext layer is corrupt, so verbatim quotes cannot be derived from it until a trustworthy sibling exists. Use before building or quoting a source flagged extraction_type ocr-scan / extraction-lossy that has no sibling; /build step 4b directs here.

By mufon609 schedule Updated 6/9/2026

play_arrow Run Skill in Manus View GitHub

Skill instructions (SKILL.md) could not be loaded from local cache or raw GitHub repository.

Install via CLI

npx skills add https://github.com/mufon609/UAP_OSINT-v0.1 --skill prepare-ocr-sibling

Repository Details

star Stars 1

call_split Forks 1

navigation Branch main

article Path SKILL.md