Introduction

The core design philosophy of DeepSeek Harness (DSH) is “everything is a plugin.” In practical agent development, in addition to online information retrieval, cleaning, formatting, or statistical analysis of raw text are often necessary preprocessing steps. xby-text-transformer is designed to address this need by providing a lightweight set of text transformation tools.

Plugin Introduction

This plugin is maintained by xby-skill and belongs to the online tools category. It connects to DSH as an MCP server, providing a range of text processing capabilities without requiring you to write your own regular expressions or string processing logic at the application layer.

Core Features

The plugin provides the following tool functions:

set_xby_apikey    - 设置 API 密钥（自动持久化，重启有效）
lowercase         - 转换为小写
uppercase         - 转换为大写
reverse           - 反转字符顺序
isPalindrome      - 检测是否为回文
countWords        - 统计单词数量
countCharacters   - 统计字符数量
trim              - 去除首尾空格
capitalize        - 单词首字母大写

Installation and Configuration

Installation

Add the plugin using the official installation command:

dsh plugin --profile web add github:xby_skill/xby-text-transformer

Prerequisites for Configuration

Before using this plugin, you must register on the Xiao Benyang website and obtain an API key. This key is used for calling the plugin’s backend services.

Typical Usage

In DSH chat or scripts, you can directly invoke the tools above.

For example, to check whether a piece of text is a palindrome:

使用 isPalindrome 工具检测："A man a plan a canal Panama"

Or to count the number of characters in a text:

使用 countCharacters 工具统计："Hello World"

Notes

  • This plugin depends on the API services provided by Xiao Benyang.
  • The license is MIT, allowing free use and modification.
  • It is recommended to check the source code before installation to ensure it meets the runtime environment requirements of the current DSH version.

Conclusion

xby-text-transformer provides basic yet efficient text processing capabilities, making it suitable for DSH projects that require quick integration of text cleaning, statistics, or formatting features. To view the source code or submit issues, you can access its GitHub repository.