OCR/image-based PDF pipeline: convert pages to PNGs, read with Claude Vision (bypasses unreliable OCR text layer), translate with cross-page glossary consistency, reconstruct faithful HTML via /design-html. 5 steps: deps check → page images + assets → style analysis → page-by-page read+translate → HTML reconstruction → visual QA. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| profiles | ||
| project-archetypes | ||
| animation-lib-check.sh | ||
| archetype-detector.md | ||
| design-gate.md | ||
| detect-plugins.sh | ||
| profile.sh | ||
| toggle-external.sh | ||