Rare find
TransCrab. Turn any web link into a translated reading page that your AI assistant can publish.
transcrab.onev.cat
Vaya's read on this project
Problem, audience, market, and the verdict — sign in to see it.
Updates
April 2026
- Improve footer visibility and add top About link
March 2026
- Preserve inline SVG in-place and absolutize extracted asset URLs (#12)
- Refactor add-url by extracting source resolver module (#11)
- Add robust extraction fallback chain for dynamic pages (#10)
- Merge pull request #7 from onevcat/feat/refined-auto-topic-pipeline
- feat: add punctuation quality gate and auto-fix in apply stage
- refactor: normalize prompt artifact naming with canonical promptPath
- docs: sync plan with refined-first and topic-style decisions
- docs: align README and skill with refined auto publish workflow
- feat: implement draft/final apply loop for refined translation
- feat: wire add-url into orchestrator artifact materialization
- feat: infer topic-driven style profile for refined auto mode
- feat: add translation orchestrator and layered config defaults
- test: add translation quality baseline fixtures and evaluator scaffold
- feat(x-article): recover inline media from fxtwitter blocks
- Merge pull request #5 from onevcat/fix/substack-heading-preservation
- Normalize linked image markdown emitted by Turndown
- Preserve Substack headings during article extraction
February 2026
- render: disable fixStrongAdjacency (content now normalized)
- render: fix strong adjacency - only add space after ASCII