Borrowing it
Nothing to install: this file belongs to ZimoLiao/scholaraio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ZimoLiao/scholaraio/main/.claude/skills/translate/SKILL.mdgit clone --depth 1 https://github.com/ZimoLiao/scholaraioWrote 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.
[](https://agentmods.dev/skills/zimoliao/scholaraio/translate)<a href="https://agentmods.dev/skills/zimoliao/scholaraio/translate"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/translate/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.
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/translate"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/translate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.01294 |
| Opus 5.5 | $0.00012 | $0.00518 |
| Sonnet 5.5 | $0.00006 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
translate 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.
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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
论文翻译
将论文 Markdown 翻译为目标语言(默认中文),保留 LaTeX 公式、代码块、图片引用和 Markdown 格式。翻译结果保存为论文目录内的 paper_{lang}.md,原文保持不变;如需可携带分享,可额外导出到 workspace/_system/translation-bundles/<Author-Year-Title>/。
当前实现支持:
- 单篇翻译时按
config.translate.concurrency并发请求多个分块,并在终端显示块级进度 - 在论文目录下创建临时工作目录,按块写入
parts/*.md - 网络抖动时对单块做超时重试与指数退避(默认最多 5 次尝试)
- 中途中断后可从临时工作目录继续续翻
--force会清理旧的临时翻译目录并从头重新翻译--portable会额外生成workspace/_system/translation-bundles/<Author-Year-Title>/paper_{lang}.md和对应的images/
配置
config.yaml 中可设置默认行为:
translate:
auto_translate: false # 入库时是否自动翻译(默认关闭)
target_lang: zh # 目标语言(zh/en/ja/ko/de/fr/es)
chunk_size: 4000 # 分块大小(字符数)
concurrency: 20 # 总翻译并发预算(单篇时用于 chunk 并发,批量时会在论文间分摊)
每次调用时可通过 CLI 参数覆盖默认值。
执行逻辑
单篇翻译
scholaraio translate "<paper-id>" [--lang zh] [--force] [--portable]
批量翻译
scholaraio translate --all [--lang zh] [--force] [--portable]
查看翻译
scholaraio show "<paper-id>" --layer 4 --lang zh
作为 pipeline 步骤
scholaraio pipeline --steps toc,l3,translate
注意:
translate默认不在预设(full/ingest/enrich/reindex)中;可通过--steps显式指定。若config.translate.auto_translate=true且 pipeline 包含 inbox 步骤,translate会在 papers 阶段自动注入。
工作流程
- 检测论文原文语言(基于字符集启发式检测)
- 如果已是目标语言,跳过
- 将 Markdown 按段落边界分块(保留代码块和公式完整性)
- 通过 LLM 逐块翻译,保留所有格式标记
- 单篇翻译会并发请求多个分块,但只按原顺序推进最终输出
- 在论文目录下创建临时工作目录(如
.translate_zh/),将每块分别写入parts/*.md - 状态写入
state.json/chunks.json;失败块会记录错误并在下次续翻时单独补跑 - 每个分块带超时重试和指数退避
- 若已有连续成功前缀,则同步刷新
paper_{lang}.md,方便中途查看已完成部分 - 若指定
--portable,则额外复制一份到workspace/_system/translation-bundles/<Author-Year-Title>/,并复制images/以保证脱离原目录后图片仍可用 - 若前面某块失败但后面某些块已成功,这些成功块仍会保留在临时工作目录里;下次续翻时会跳过已成功块,只补失败或未完成的块
- 全部完成后删除临时工作目录,并在
meta.json中记录翻译元数据
进度与续翻
单篇翻译会输出:
- 总块数
- 当前块进度(如
翻译进度: 3/12) - 中断位置
- 是否可续翻
如果中途中断:
scholaraio translate "<paper-id>" --lang zh
会自动检测论文目录下的临时翻译工作目录(如 .translate_zh/),并从未完成或失败的块继续。
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.
- 2mo ago First seen · 117 lines · 30 tokens per session scan A 02502617d79c
translate is a skill published in the GitHub repository ZimoLiao/scholaraio (584 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 1,294 once invoked, about $0.0001 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.
translate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| translateZimoLiao/scholaraio | Skill | 584 | 10d ago | MIT | A | 30 | Claude Code |
| infrastructure-validationdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| provenance-dagdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 103 | Claude Code, Codex |
| scientific-connectorsdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 87 | Claude Code, Codex |
| infrastructure-search-literaturedocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 123 | Claude Code, Codex |
| template-academic-paper-reviewerdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |
| template-reproducibility-auditdocxology/template | Skill | 23 | yesterday | Apache-2.0 | A | 70 | Claude Code, Codex |