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> |
||
|---|---|---|
| .. | ||
| audit.profile | ||
| backend.profile | ||
| design.profile | ||
| dev.profile | ||
| full.profile | ||
| minimal.profile | ||
| qa.profile | ||
| seo.profile | ||
| web-full.profile | ||
| web.profile | ||