agentmods.dev

babeldoc-trans

babeldoc-trans is a skill for Claude Code, Codex from kaixindelele/wechat_agent_bridge_skills. It costs 109 tokens per session (816 once invoked), scanned A, original, MIT.

A tool for translating English research-paper PDFs into Chinese while preserving their layout, including figures, formulas, and images. It accepts an arXiv link, arXiv ID, or local PDF file; arXiv is a website for sharing research papers.

In plain words
What is it for?
Use it when someone provides an arXiv reference or PDF and asks for a Chinese translation, optionally producing a bilingual version or translating selected pages.
Why use it?
It removes the need to translate a paper manually while keeping the translated document visually close to the original.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 20repo 6mo ago A scan 109 tokens original MIT

Good fit Use it when someone provides an arXiv reference or PDF and asks for a Chinese translation, optionally producing a bilingual version or translating selected pages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans
View source ↗ kaixindelele/wechat_agent_bridge_skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kaixindelele/wechat_agent_bridge_skills --skill babeldoc-trans
Clone the repo
git clone --depth 1 https://github.com/kaixindelele/wechat_agent_bridge_skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for babeldoc-trans

README.md
[![agentmods](https://agentmods.dev/badge/skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans/github.svg)](https://agentmods.dev/skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans)
Your own site
<a href="https://agentmods.dev/skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans"><img src="https://agentmods.dev/badge/skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for babeldoc-trans

Your own site · 80×15
<a href="https://agentmods.dev/skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans"><img src="https://agentmods.dev/badge/skills/kaixindelele/wechat_agent_bridge_skills/babeldoc-trans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.00816
Opus 5.5 $0.00044 $0.00326
Sonnet 5.5 $0.00022 $0.00163
Haiku 4.5 $0.00011 $0.00082

Measured 2mo ago against content hash 348a46b962c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

babeldoc-trans scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/setup.sh, scripts/translate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

babeldoc-trans/SKILL.md · 74 lines

What it actually says

BabelDOC 论文翻译

基于 BabelDOC 的论文 PDF 翻译封装。智能版式分析 + 公式保护 + 术语自动提取，输出自动以中文标题命名。

触发条件

  • 用户发送 arxiv 链接（https://arxiv.org/abs/xxxx.xxxxx 或 https://arxiv.org/pdf/xxxx.xxxxx）
  • 用户发送 arxiv ID（如 2412.13211）
  • 用户上传或指定 PDF 文件路径
  • 用户说"翻译这篇论文"、"translate this paper"等

工作流程

步骤 1：获取 SKILL 路径

确定本 skill 的安装路径（即包含此 SKILL.md 的目录），用于定位 scripts/translate.py。

步骤 2：执行翻译

python {SKILL_DIR}/scripts/translate.py "<输入>" --output-dir /tmp/babeldoc_output

输入可以是：

  • arxiv URL：https://arxiv.org/abs/2412.13211
  • arxiv PDF URL：https://arxiv.org/pdf/2412.13211
  • arxiv ID：2412.13211
  • 本地 PDF 路径：/path/to/paper.pdf

步骤 3：返回结果

脚本最后会打印 [DONE] {JSON}，包含：

  • title_en / title_zh — 英文/中文标题
  • output_pdf — 最终 PDF 绝对路径（已以中文标题命名）
  • size_kb — 文件大小

将翻译后的 PDF 文件发送给用户。

常用参数

参数 说明 默认值
--output-dir PDF 输出目录 /tmp/babeldoc_output
--pages 只翻译指定页，如 1-5 全部
--qps 翻译并发 QPS 8
--dual 额外输出双语对照 PDF off
--model OpenAI 模型 gpt-4o-mini
--api-base API base URL https://api.bltcy.ai/v1
--api-key API key 读取 $BABELDOC_API_KEY

环境变量

变量 说明 必须
BABELDOC_API_KEY OpenAI 兼容 API key 是
BABELDOC_API_BASE API base URL 否（默认 https://api.bltcy.ai/v1）
BABELDOC_MODEL 模型名 否（默认 gpt-4o-mini）

安装依赖

首次使用前运行：

bash {SKILL_DIR}/scripts/setup.sh

详细文档

更多参数说明、性能参考和常见问题排查，请查阅 references/usage_guide.md。

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 74 lines · 109 tokens per session scan A 348a46b962c5

Subscribe to this mod's changes

babeldoc-trans is a skill published in the GitHub repository kaixindelele/wechat_agent_bridge_skills (20 stars, last pushed 6mo ago), licensed MIT. It adds 109 tokens to every session and 816 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DocumentsLocalizationPDF
Related

babeldoc-trans compared with skills from other repositories

babeldoc-trans next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
babeldoc-transkaixindelele/wechat_agent_bridge_skillsSkill206mo agoMITA109Claude Code, Codex
translate-bookdeusyu/translate-bookSkill2.3k8d agoMITA42Claude Code
pdf_translatorForceInjection/AI-fundamentalsSkill3.3kyesterdayApache-2.0A47Claude Code, Codex
docutranslateznlgis/opengis-skillsSkill7610d agoMITA119Claude Code, Codex
lov-academic-translatorlovstudio/skillsSkill723d agoMITA87Claude Code, Codex
hebrew-document-generatorskills-il/localizationSkill264d agoMITA242Claude Code
pdf-translatebreslee1707/VI-TranslateSkill73916d agoAGPL-3.0A77Codex