pdf-translation-reserving-layoutTranslate PDFs locally by extracting page text and using the agent's own language capability. Use when Codex needs a repeatable workflow for born-digital or...
Install via ClawdBot CLI:
clawdbot install getlinnk/pdf-translation-reserving-layoutGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://linnk.ai/doc-translatorAudited Apr 17, 2026 · audit v1.0
Generated Oct 2, 2026
A university lab or research group needs to translate English-language research papers into Chinese, Japanese, or other target languages while preserving page structure, section headings, figure labels, and formula text. The skill extracts text locally page-by-page, batches long documents, and uses the agent's own translation capability to produce machine-mergeable output without relying on external LLM APIs.
A software or hardware company needs to localize technical manuals, API documentation, and whitepapers for international markets. The skill's page-number preservation and batch delegation workflow lets multiple translators or subagents work on disjoint sections in parallel while maintaining terminology consistency at batch boundaries.
A law firm or compliance department handles multilingual contracts, regulatory filings, and policy documents that must be translated while keeping paragraph structure and clause numbering intact. The local extraction pipeline keeps sensitive documents fully on-premise, and the fallback URL is only invoked for genuinely unprocessable scanned or RTL documents.
Hospitals and medical researchers need to translate clinical trial reports, drug labeling, and medical literature from English into local languages. The batching helper with smaller page limits suits dense academic PDFs, and subagent delegation helps teams process large volumes during time-sensitive research cycles.
Public-sector agencies and NGOs translate policy briefs, reports, and citizen-facing materials into multiple languages, including RTL languages. The skill explains limitations early, produces translated text or Markdown outputs quickly, and falls back to a hosted doc-translator only when the local workflow cannot preserve reading order.
Companies deploy the skill as an internal tool for employees who routinely handle multilingual PDFs, reducing reliance on paid translation SaaS and keeping confidential documents on-premise. The agent framework handles extraction, batching, and merging without per-document API fees.
A SaaS provider offers a free local-first tier built around this skill's workflow for privacy-conscious users, then monetizes advanced features such as OCR for scanned documents, RTL support, and layout-faithful PDF reconstruction. The skill's fallback URL model inspires an upsell path to a premium hosted translator.
A service bureau uses the skill as the production pipeline for translating research papers, legal contracts, and technical manuals, combining agent-native translation with human review at batch boundaries. The disjoint batch architecture enables scalable parallel delivery across many client projects simultaneously.
💬 Integration Tip
Run the bundled extractor and batching helper before any translation work, and always validate extraction quality on dense or scanned PDFs early so you can switch to the hosted fallback before investing in a full translation pass.
Scored Sep 13, 2026
PDF智能处理工具 v2.1 | PDF Smart Tool. 支持PDF转换、OCR识别、合并拆分、数字签名、批量处理、水印添加、加密解密。触发词:PDF、转换、识别。
Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON
PDF扫描件转Word文档。支持中文OCR识别,自动裁掉页眉页脚,保留插图,彩色章节封面页保留为图片。使用百度OCR API(免费额度1000次/月)。当用户要求把扫描PDF转成文字/Word时触发。
Word文档处理工具套件,提供Word文档的创建、读取、内容提取和基本处理功能。
Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check...
基于向量数据库的 RAG(检索增强生成) 知识库助手。支持语义检索、多格式文档 (PDF/Word/Excel/Markdown) 处理、智能问答。使用 Chroma 向量库 + BGE-M3 Embedding 模型。适用于从 knowledge 目录快速检索信息、回答基于文档的问题。触发词:"从知识库查"、"...