Introduction¶

DeepSeek Harness (DSH) uses a plugin-based architecture. Extending the plugin ecosystem can enrich the capabilities of agents or toolsets. When analyzing user behavior, repurchase rate is one of the core metrics. The dsh-repurchase plugin provides purely local computation capability, addressing the need to calculate repurchase rates in offline environments.

Plugin Overview¶

The plugin is maintained by uckkk and released under the MIT license. Its core feature is repurchase rate calculation, capable of precise calculation based on parameters and returning detailed results.

Installation¶

Run the following command to install the plugin:

dsh plugin add github:uckkk/dsh-repurchase

Usage¶

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

Dependencies and Notes¶

The plugin depends on @deepseek-ai/cordis ^4.0.1 and @deepseek-ai/dsh-tools >=0.1.0-rc.6. It is implemented purely in Node and has no network dependencies. Before use, please review the source code and license.