word-document-processor by qodex-ai/ai-agent-skills
npx skills add https://github.com/qodex-ai/ai-agent-skills --skill word-document-processor用户可能会要求您创建、编辑或分析 .docx 文件的内容。.docx 文件本质上是一个包含 XML 文件和其他资源的 ZIP 压缩包,您可以读取或编辑这些内容。针对不同的任务,您可以使用不同的工具和工作流程。
使用下面的“文本提取”或“原始 XML 访问”部分
使用“创建新的 Word 文档”工作流程
如果您只需要读取文档的文本内容,应使用 pandoc 将文档转换为 markdown。Pandoc 在保留文档结构和显示修订痕迹方面提供了出色的支持:
# 将文档转换为 markdown 并保留修订痕迹
pandoc --track-changes=all path-to-file.docx -o output.md
# 选项:--track-changes=accept/reject/all
对于以下情况,您需要原始 XML 访问:批注、复杂格式、文档结构、嵌入媒体和元数据。对于任何这些功能,您都需要解包文档并读取其原始 XML 内容。
python ooxml/scripts/unpack.py <office_file> <output_directory>
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
word/document.xml - 主要文档内容word/comments.xml - 在 document.xml 中引用的批注word/media/ - 嵌入的图像和媒体文件<w:ins>(插入)和 <w:del>(删除)标签从头开始创建新的 Word 文档时,请使用 docx-js,它允许您使用 JavaScript/TypeScript 创建 Word 文档。
docx-js.md(约 500 行)。阅读此文件时切勿设置任何范围限制。 在继续文档创建之前,请阅读完整的文件内容以了解详细语法、关键格式规则和最佳实践。编辑现有的 Word 文档时,请使用 Document 库(一个用于 OOXML 操作的 Python 库)。该库自动处理基础设施设置,并提供文档操作方法。对于复杂场景,您可以通过该库直接访问底层 DOM。
ooxml.md(约 600 行)。阅读此文件时切勿设置任何范围限制。 阅读完整的文件内容以了解 Document 库 API 和直接编辑文档文件的 XML 模式。python ooxml/scripts/unpack.py <office_file> <output_directory>python ooxml/scripts/pack.py <input_directory> <office_file>Document 库为常见操作提供了高级方法,也为复杂场景提供了直接的 DOM 访问。
此工作流程允许您在 OOXML 中实施修订之前,先使用 markdown 规划全面的修订痕迹。关键:为了完成修订痕迹,您必须系统地实施所有更改。
批处理策略:将相关的更改分组为每批 3-10 个更改。这使得调试易于管理,同时保持效率。在进入下一批之前测试每一批。
原则:最小化、精确的编辑 在实施修订痕迹时,只标记实际发生变化的文本。重复未更改的文本会使审阅编辑变得困难,并且显得不专业。将替换分解为:[未更改文本] + [删除] + [插入] + [未更改文本]。通过从原始内容中提取 <w:r> 元素并重用它,来保留未更改文本的原始运行 RSID。
示例 - 将句子中的“30 days”更改为“60 days”:
# 错误 - 替换整个句子
'<w:del><w:r><w:delText>The term is 30 days.</w:delText></w:r></w:del><w:ins><w:r><w:t>The term is 60 days.</w:t></w:r></w:ins>'
# 正确 - 只标记更改的部分,为未更改的文本保留原始的 <w:r>
'<w:r w:rsidR="00AB12CD"><w:t>The term is </w:t></w:r><w:del><w:r><w:delText>30</w:delText></w:r></w:del><w:ins><w:r><w:t>60</w:t></w:r></w:ins><w:r w:rsidR="00AB12CD"><w:t> days.</w:t></w:r>'
获取 markdown 表示:将文档转换为 markdown 并保留修订痕迹:
pandoc --track-changes=all path-to-file.docx -o current.md
识别并分组更改:审阅文档并识别所有需要的更改,将它们组织成逻辑批次:
定位方法(用于在 XML 中查找更改): * 章节/标题编号(例如,“Section 3.2”、“Article IV”) * 段落标识符(如果有编号) * 带有唯一周围文本的 Grep 模式 * 文档结构(例如,“第一段”、“签名块”) * 请勿使用 markdown 行号 - 它们不映射到 XML 结构
批次组织(每批分组 3-10 个相关更改): * 按章节:“批次 1:第 2 节修订”、“批次 2:第 5 节更新” * 按类型:“批次 1:日期更正”、“批次 2:参与方名称更改” * 按复杂度:从简单的文本替换开始,然后处理复杂的结构更改 * 按顺序:“批次 1:第 1-3 页”、“批次 2:第 4-6 页”
阅读文档并解包:
ooxml.md(约 600 行)。阅读此文件时切勿设置任何范围限制。 特别注意“Document 库”和“修订痕迹模式”部分。python ooxml/scripts/unpack.py <file.docx> <dir>分批实施更改:将更改按逻辑分组(按章节、按类型或按邻近性),并在单个脚本中一起实施。这种方法:
建议的批次分组: * 按文档章节(例如,“第 3 节更改”、“定义”、“终止条款”) * 按更改类型(例如,“日期更改”、“参与方名称更新”、“法律术语替换”) * 按邻近性(例如,“第 1-3 页的更改”、“文档前半部分的更改”)
对于每批相关更改:
a. 将文本映射到 XML:在 word/document.xml 中 grep 文本,以验证文本是如何跨 <w:r> 元素分割的。
b. 创建并运行脚本:使用 get_node 查找节点,实施更改,然后 doc.save()。有关模式,请参见 ooxml.md 中的 “Document 库” 部分。
注意:在编写脚本之前,务必立即 grep word/document.xml 以获取当前行号并验证文本内容。每次脚本运行后,行号都会改变。
打包文档:所有批次完成后,将解包的目录转换回 .docx:
python ooxml/scripts/pack.py unpacked reviewed-document.docx
最终验证:对完整文档进行全面检查:
pandoc --track-changes=all reviewed-document.docx -o verification.md
grep "original phrase" verification.md # 应该找不到
grep "replacement phrase" verification.md # 应该找到
为了可视化分析 Word 文档,请使用两步过程将其转换为图像:
将 DOCX 转换为 PDF:
soffice --headless --convert-to pdf document.docx
将 PDF 页面转换为 JPEG 图像:
pdftoppm -jpeg -r 150 document.pdf page
这将创建类似 page-1.jpg、page-2.jpg 等的文件。
选项:
-r 150:设置分辨率为 150 DPI(根据质量/大小平衡进行调整)-jpeg:输出 JPEG 格式(如果偏好 PNG,请使用 -png)-f N:要转换的起始页(例如,-f 2 从第 2 页开始)-l N:要转换的结束页(例如,-l 5 在第 5 页停止)page:输出文件的前缀特定范围的示例:
pdftoppm -jpeg -r 150 -f 2 -l 5 document.pdf page # 仅转换第 2-5 页
重要:为 DOCX 操作生成代码时:
必需的依赖项(如果不可用则安装):
sudo apt-get install pandoc(用于文本提取)npm install -g docx(用于创建新文档)sudo apt-get install libreoffice(用于 PDF 转换)sudo apt-get install poppler-utils(用于 pdftoppm 将 PDF 转换为图像)pip install defusedxml(用于安全的 XML 解析)每周安装
1.2K
仓库
GitHub 星标
5
首次出现
Jan 22, 2026
安全审计
安装于
opencode1.1K
gemini-cli1.1K
codex1.1K
cursor1.1K
github-copilot1.1K
amp1.1K
A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.
Use "Text extraction" or "Raw XML access" sections below
Use "Creating a new Word document" workflow
Your own document + simple changes Use "Basic OOXML editing" workflow
Someone else's document Use "Redlining workflow" (recommended default)
Legal, academic, business, or government docs Use "Redlining workflow" (required)
If you just need to read the text contents of a document, you should convert the document to markdown using pandoc. Pandoc provides excellent support for preserving document structure and can show tracked changes:
# Convert document to markdown with tracked changes
pandoc --track-changes=all path-to-file.docx -o output.md
# Options: --track-changes=accept/reject/all
You need raw XML access for: comments, complex formatting, document structure, embedded media, and metadata. For any of these features, you'll need to unpack a document and read its raw XML contents.
python ooxml/scripts/unpack.py <office_file> <output_directory>
word/document.xml - Main document contentsword/comments.xml - Comments referenced in document.xmlword/media/ - Embedded images and media files<w:ins> (insertions) and <w:del> (deletions) tagsWhen creating a new Word document from scratch, use docx-js , which allows you to create Word documents using JavaScript/TypeScript.
docx-js.md (~500 lines) completely from start to finish. NEVER set any range limits when reading this file. Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with document creation.When editing an existing Word document, use the Document library (a Python library for OOXML manipulation). The library automatically handles infrastructure setup and provides methods for document manipulation. For complex scenarios, you can access the underlying DOM directly through the library.
ooxml.md (~600 lines) completely from start to finish. NEVER set any range limits when reading this file. Read the full file content for the Document library API and XML patterns for directly editing document files.python ooxml/scripts/unpack.py <office_file> <output_directory>python ooxml/scripts/pack.py <input_directory> <office_file>The Document library provides both high-level methods for common operations and direct DOM access for complex scenarios.
This workflow allows you to plan comprehensive tracked changes using markdown before implementing them in OOXML. CRITICAL : For complete tracked changes, you must implement ALL changes systematically.
Batching Strategy : Group related changes into batches of 3-10 changes. This makes debugging manageable while maintaining efficiency. Test each batch before moving to the next.
Principle: Minimal, Precise Edits When implementing tracked changes, only mark text that actually changes. Repeating unchanged text makes edits harder to review and appears unprofessional. Break replacements into: [unchanged text] + [deletion] + [insertion] + [unchanged text]. Preserve the original run's RSID for unchanged text by extracting the <w:r> element from the original and reusing it.
Example - Changing "30 days" to "60 days" in a sentence:
# BAD - Replaces entire sentence
'<w:del><w:r><w:delText>The term is 30 days.</w:delText></w:r></w:del><w:ins><w:r><w:t>The term is 60 days.</w:t></w:r></w:ins>'
# GOOD - Only marks what changed, preserves original <w:r> for unchanged text
'<w:r w:rsidR="00AB12CD"><w:t>The term is </w:t></w:r><w:del><w:r><w:delText>30</w:delText></w:r></w:del><w:ins><w:r><w:t>60</w:t></w:r></w:ins><w:r w:rsidR="00AB12CD"><w:t> days.</w:t></w:r>'
Get markdown representation : Convert document to markdown with tracked changes preserved:
pandoc --track-changes=all path-to-file.docx -o current.md
Identify and group changes : Review the document and identify ALL changes needed, organizing them into logical batches:
Location methods (for finding changes in XML):
* Section/heading numbers (e.g., "Section 3.2", "Article IV")
* Paragraph identifiers if numbered
* Grep patterns with unique surrounding text
* Document structure (e.g., "first paragraph", "signature block")
* **DO NOT use markdown line numbers** \- they don't map to XML structure
Batch organization (group 3-10 related changes per batch):
* By section: "Batch 1: Section 2 amendments", "Batch 2: Section 5 updates"
* By type: "Batch 1: Date corrections", "Batch 2: Party name changes"
* By complexity: Start with simple text replacements, then tackle complex structural changes
* Sequential: "Batch 1: Pages 1-3", "Batch 2: Pages 4-6"
3. Read documentation and unpack :
* **MANDATORY - READ ENTIRE FILE** : Read [`ooxml.md`](https://github.com/qodex-ai/ai-agent-skills/blob/HEAD/skills/word-document-processor/ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Pay special attention to the "Document Library" and "Tracked Change Patterns" sections.
* **Unpack the document** : `python ooxml/scripts/unpack.py <file.docx> <dir>`
* **Note the suggested RSID** : The unpack script will suggest an RSID to use for your tracked changes. Copy this RSID for use in step 4b.
4. Implement changes in batches : Group changes logically (by section, by type, or by proximity) and implement them together in a single script. This approach:
* Makes debugging easier (smaller batch = easier to isolate errors)
* Allows incremental progress
* Maintains efficiency (batch size of 3-10 changes works well)
Suggested batch groupings:
* By document section (e.g., "Section 3 changes", "Definitions", "Termination clause")
* By change type (e.g., "Date changes", "Party name updates", "Legal term replacements")
* By proximity (e.g., "Changes on pages 1-3", "Changes in first half of document")
For each batch of related changes:
a. Map text to XML : Grep for text in word/document.xml to verify how text is split across <w:r> elements.
b. Create and run script : Use get_node to find nodes, implement changes, then doc.save(). See "Document Library" section in ooxml.md for patterns.
Note : Always grep word/document.xml immediately before writing a script to get current line numbers and verify text content. Line numbers change after each script run.
Pack the document : After all batches are complete, convert the unpacked directory back to .docx:
python ooxml/scripts/pack.py unpacked reviewed-document.docx
Final verification : Do a comprehensive check of the complete document:
Convert final document to markdown:
pandoc --track-changes=all reviewed-document.docx -o verification.md
Verify ALL changes were applied correctly:
grep "original phrase" verification.md # Should NOT find it
grep "replacement phrase" verification.md # Should find it
Check that no unintended changes were introduced
To visually analyze Word documents, convert them to images using a two-step process:
Convert DOCX to PDF :
soffice --headless --convert-to pdf document.docx
Convert PDF pages to JPEG images :
pdftoppm -jpeg -r 150 document.pdf page
This creates files like page-1.jpg, page-2.jpg, etc.
Options:
-r 150: Sets resolution to 150 DPI (adjust for quality/size balance)-jpeg: Output JPEG format (use -png for PNG if preferred)-f N: First page to convert (e.g., -f 2 starts from page 2)-l N: Last page to convert (e.g., -l 5 stops at page 5)page: Prefix for output filesExample for specific range:
pdftoppm -jpeg -r 150 -f 2 -l 5 document.pdf page # Converts only pages 2-5
IMPORTANT : When generating code for DOCX operations:
Required dependencies (install if not available):
sudo apt-get install pandoc (for text extraction)npm install -g docx (for creating new documents)sudo apt-get install libreoffice (for PDF conversion)sudo apt-get install poppler-utils (for pdftoppm to convert PDF to images)pip install defusedxml (for secure XML parsing)Weekly Installs
1.2K
Repository
GitHub Stars
5
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubFailSocketPassSnykWarn
Installed on
opencode1.1K
gemini-cli1.1K
codex1.1K
cursor1.1K
github-copilot1.1K
amp1.1K
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
102,200 周安装