pdf-translate-review
llms.txt0 starsChanged 41 days agoMITView on GitHub
Agent skills and local Python / Node.js tools for translating academic PDF papers into Chinese Markdown and self-contained offline HTML, with source-aligned translation review and checks for equations, figures, and tables. Canonical repository: https://github.com/Marco0431/pdf-translate-review The agent performs translation and semantic review. Scripts provide PDF extraction, figure cropping, formula and structure checks, offline HTML rendering, resumable workflow state, and optional Zotero attachment handling. Automated checks do not establish translation accuracy or complete visual verification. "Review" means translation review, not academic peer…
Files
# pdf-translate-review > Agent skills and local Python / Node.js tools for translating academic PDF papers into Chinese Markdown and self-contained offline HTML, with source-aligned translation review and checks for equations, figures, and tables. Canonical repository: https://github.com/Marco0431/pdf-translate-review The agent performs translation and semantic review. Scripts provide PDF extraction, figure cropping, formula and structure checks, offline HTML rendering, resumable workflow state, and optional Zotero attachment handling. Automated checks do not establish translation accuracy or complete visual verification. "Review" means translation review, not academic peer review. Documentation is primarily in Chinese. The repository is MIT-licensed. ## Start here - [README and installation](https://github.com/Marco0431/pdf-translate-review/blob/main/README.md): Overview, dependencies, usage examples, and Markdown / HTML pipelines. - [Single-paper skill](https://github.com/Marco0431/pdf-translate-review/blob/main/SKILL.md): Full translation, source comparison, equation and figure verification, and delivery workflow. - [Batch translation skill](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/SKILL.md): Batch processing, resumable state, quality status, and optional Zotero archiving. ## Workflow references - [Verification guide](https://github.com/Marco0431/pdf-translate-review/blob/main/reference/verification-guide.md): Formula inspection, figure checks, and review commands. - [Agent execution flow](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/references/agent-flow.md): Preparation, translation, source-aligned review, correction, and risk review. - [Translation quality](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/references/translation-quality.md): Source evidence, terminology, and final-version verification. - [HTML quality checks](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/references/quality.md): Delivery criteria and remaining visual checks. - [Zotero archiving](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/references/zotero.md): Deduplication, attachment import, and read-back checks. ## Implementation and examples - [Scripts](https://github.com/Marco0431/pdf-translate-review/tree/main/scripts): Extraction, verification, HTML building, and attachment utilities. - [Synthetic translation fixture](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/tests/fixtures/translation-case.json): Small regression input, explicitly not a real paper. - [Matching translation fixture](https://github.com/Marco0431/pdf-translate-review/blob/main/skills/paper-translate-html/tests/fixtures/translation-good.json): Translation data used by the regression tests, not a published paper translation. - [License](https://github.com/Marco0431/pdf-translate-review/blob/main/LICENSE): MIT license.
In this repository2 other files it gives its agents.
- pdf-translate-reviewSkill
- paper-translate-htmlSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.