doc-to-text

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Document to Text Converter

文档转文本转换器

Overview

概述

This skill acts as a universal converter to extract plain text and structured data from various binary and complex file formats. It enables Gemini to "read" files that are otherwise inaccessible.

该Skill是一个通用转换器，可从各种二进制和复杂文件格式中提取纯文本和结构化数据。它能让Gemini“读取”原本无法访问的文件。

Capabilities

功能特性

1. Document Extraction

1. 文档提取

PDF (
```
.pdf
```
): Extracts plain text.
Excel (
```
.xlsx
```
): Converts sheets to CSV and performs OCR on embedded images.
Word (
```
.docx
```
): Extracts text and performs OCR on embedded images.
PowerPoint (
```
.pptx
```
): Extracts slide text and performs OCR on embedded images.

PDF (
```
.pdf
```
)：提取纯文本。
Excel (
```
.xlsx
```
)：将工作表转换为CSV格式，并对嵌入图片执行OCR识别。
Word (
```
.docx
```
)：提取文本，并对嵌入图片执行OCR识别。
PowerPoint (
```
.pptx
```
)：提取幻灯片文本，并对嵌入图片执行OCR识别。

2. Image OCR

2. 图片OCR识别

Images (
```
.png
```
,
```
.jpg
```
,
```
.jpeg
```
,
```
.webp
```
): Uses Tesseract.js to perform OCR (Optical Character Recognition) and extract text from images. Supports English and Japanese.

图片 (
```
.png
```
,
```
.jpg
```
,
```
.jpeg
```
,
```
.webp
```
)：使用Tesseract.js执行OCR（光学字符识别），从图片中提取文本。支持英文和日文。

3. Data & Archives

3. 数据与压缩包处理

Email (
```
.eml
```
): Parses headers (From, To, Subject) and body text.
ZIP Archive (
```
.zip
```
): Lists files and extracts content of text-based files within the archive without extracting to disk.

电子邮件 (
```
.eml
```
)：解析邮件头（发件人、收件人、主题）和正文文本。
ZIP压缩包 (
```
.zip
```
)：列出包内文件，并提取其中文本类文件的内容，无需解压到磁盘。

Usage

使用方法

To read a file, execute the

extract.cjs

script with the file path.

bash

node scripts/extract.cjs <path/to/file>

Example: User: "What does the error screenshot say?" Action:

node scripts/extract.cjs error.png

要读取文件，请执行

extract.cjs

脚本并传入文件路径。

bash

node scripts/extract.cjs <path/to/file>

示例： 用户：“这个错误截图里写了什么？” 操作：

node scripts/extract.cjs error.png

Dependencies

依赖项

This skill requires Node.js packages. Run

npm install

in the skill directory before using.

该Skill需要Node.js包。使用前请在Skill目录下运行

npm install

。

Knowledge Protocol

知识协议

This skill adheres to the
```
knowledge/orchestration/knowledge-protocol.md
```
. It automatically integrates Public, Confidential (Company/Client), and Personal knowledge tiers, prioritizing the most specific secrets while ensuring no leaks to public outputs.

该Skill遵循
```
knowledge/orchestration/knowledge-protocol.md
```
协议。它会自动整合公开、保密（公司/客户）和个人知识层级，优先使用最具体的保密内容，同时确保不会泄露到公开输出中。