Back to search
medical-paper-translator
SkillGitHub
医学翻译 | 医学论文翻译工作台:汉译英/英译汉(中英互译),结构保真,表格与原文一一对应;本地部署 FastAPI + Agent 技能,适配 SCI 论文写作
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/jameslijing--medical-paper-translator)HTML
<a href="/listings/jameslijing--medical-paper-translator"><img src="/api/listings/jameslijing--medical-paper-translator/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Prereq **Python 3.10+**; first run auto-installs deps (network), then offline.
cd workbench && ./start.sh # or double-click 启动工作台.command / .bat
Open printed URL (default http://localhost:8899). Configure model in 模型设置, test, translate.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 40 lines
- # Medical Paper Translator · 医学论文翻译工作台
- **面向中文医学工作者的论文汉译英 / 英译汉工具** —— 中文用户请见 [README.zh.md](README.zh.md)。
- An open-source medical paper translation toolkit for Chinese-speaking researchers: **汉译英 (Chinese→English)** for SCI submission and **英译汉 (English→中文)** for reading comprehension.
- Topics: `medical-translation` `zh-en-translation` `汉译英` `英译汉` `医学论文` `SCI` `translation-workbench` `agent-skill`
- Domain-specific medical/scientific paper translation, delivered as **two services** sharing one skill source (`skill/`):
- | Service | Form | For | Guide |
- |---|---|---|---|
- | **① Translation skill** (`skill/`) | Markdown methodology + optional scripts, installed into an agent | **Agents** (QwenWork/Codex/Claude Code/Cursor…) | [docs/usage-skill.md](docs/usage-skill.md) |
- | **② Local workbench** (`workbench/`) | Self-contained local web app, double-click to run | **Humans** (browser, no agent needed) | [docs/usage-workbench.md](docs/usage-workbench.md) |
- > The skill does not run by itself — an agent reads and executes it. The workbench is a standalone program. Both use the same translation rules. 中文见 [README.zh.md](README.zh.md)。
- ## Documentation (unified)
- Start at **[docs/README.md](docs/README.md)** (index by audience). Developers/agents: [AGENTS.md](AGENTS.md) → [docs/development.md](docs/development.md) → [docs/decisions.md](docs/decisions.md) → [docs/architecture.md](docs/architecture.md) → [CONTRIBUTING.md](CONTRIBUTING.md).
- ## Features
- ZH→SCI-English / EN→ZH / SCI polishing / QA; five-step workflow; **structure-fidelity pipeline** (numbered atomic blocks — headings/paragraphs/tables/lists — translated per block and reassembled by code, so the translation mirrors the source layout exactly; tables never move or split); fidelity contract; offline MeSpEn term base (~72k, CC-BY) + user glossary (add/edit/delete, polysemy, context-aware); journal-PDF intake (column order, running-head removal, OCR, tables); docx intake with in-place table extraction; EQUATOR routing; optional opt-in MeSH check; clean body + separate appendix files; export MD/HTML/Word/PDF/ZIP.
- ## Quick start (workbench)
- Prereq **Python 3.10+**; first run auto-installs deps (network), then offline.
- ```bash
- cd workbench && ./start.sh # or double-click 启动工作台.command / .bat
- ```
- Open printed URL (default http://localhost:8899). Configure model in 模型设置, test, translate.
- ## Use the skill in an agent
- Copy `skill/` into the agent's skills dir (Codex: project root via AGENTS.md), or paste SKILL.md + references. See [docs/usage-skill.md](docs/usage-skill.md).
- ## Build & test
- ```bash
- python scripts/build.py # -> dist/medical-workbench.zip, dist/medical-skill.zip/.skill
- python -m unittest discover -s tests -v
- ```
- ## License & attribution
- Code MIT; MeSpEn CC-BY-4.0, Noto Sans SC OFL-1.1 ([NOTICE.md](NOTICE.md)). No secrets / personal glossaries / copyrighted papers.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.