negentropy

用 negentropy-perceives 的 parse_pdf_to_markdown 经 Knowledge Base Documents Ingest 将 PDF 一比一还原为可渲染 Markdown（文字、段落顺序、高清原图、图片显示尺寸、目录、表格、数学公式、代码块、注释），大文件分批，逐页浏览器对比、发现一处修一处，直至完全一致。Use when ingesting/restoring a PDF into a Knowledge corpus with high fidelity.

将 Knowledge / Documents 文档的英文 Markdown 正文按段落分块高保真翻译为中文：代码块、行内代码、URL、图片路径、LaTeX 公式、HTML 标签、front-matter 键名逐字节保留不翻，Markdown 结构与原文一一对应，逐块翻译禁止合并/拆分/遗漏。Use when translating chunked Markdown documents (source/chunk_NNNN.md → translated/chunk_NNNN.md) in a translation workdir.

Manage large document processing by splitting into batches and coordinating the full translation workflow (extraction, translation, formatting). Use when handling documents larger than 30 pages, 60 paragraphs, or 6000 words.

对文档进行系统性 Review，包括但不限于：审计与熵减优化，确保架构正交、逻辑自洽、内容完整且直观。

将 PDF 格式或 Web Page 格式的源文档转换成保持原排版格式的 Markdown 格式精译中文文档。

仔细阅读并理解目标文档全文，输出一个对目标文档的理解摘要和读后感悟，将之保存到愫读文档中。

Format and optimize Markdown content, with special support for post-translation processing. Use when fixing Markdown syntax, adjusting layout, ensuring formatting consistency, or optimizing translated documents.

Extract text, images, tables, and formulas from PDF documents and convert them to Markdown format while preserving original structure. Use when processing PDF files, extracting content, or converting PDF to Markdown.

Extract web page content and convert to Markdown format while preserving structure, images, tables, and links. Use when converting web pages to Markdown for further processing.

Translate Markdown content from any language to Chinese while preserving formatting, code blocks, formulas, and special elements. Use when you need accurate Chinese translation of technical documents.