Introduction

DeepSeek Harness (DSH) follows an “everything is a plugin” architecture, allowing developers to extend the capabilities of an Agent through plugins. When building agents that involve chess knowledge, they usually need to rely on external APIs. The dsh-chess-open plugin provides Xiangqi opening plans and learning paths through local logic, without making network requests.

Plugin Overview

The plugin is maintained by uckkk and is an open-source tool implemented in pure Node.js. It primarily addresses the need to obtain Xiangqi opening information and supports generating chess learning plans based on parameters.

Core Features

  1. Xiangqi openings: Provides basic Xiangqi opening data.
  2. Parameter-based chess learning plans: Supports generating a chess learning plan based on input parameters.

Installation and Activation

Use the official installation command to add the plugin to the current environment:

dsh plugin add github:uckkk/dsh-chess-open

Typical Usage

After installation, simply invoke the tools registered by the plugin in a DSH session.

Applicable Scenarios and Notes

  • Applicable scenarios: Suitable for local applications that require chess opening knowledge or learning plans.
  • Notes: The plugin runs with the permissions of the current DSH process. Review the source code and license (MIT) before use. Ensure the environment meets the dependency requirements (@deepseek-ai/cordis ^4.0.1, @deepseek-ai/dsh-tools >=0.1.0-rc.6).

Summary

The plugin provides a local solution for obtaining Xiangqi openings and learning paths. For more details, refer to the plugin directory or the source code repository.