Introduction

The core design philosophy of DeepSeek Harness (DSH) is “everything is a plugin”. Developers can extend model inference capabilities by installing community plugins. This article introduces dsh-ingredient, a plugin focused on ingredient recognition.

Plugin Overview

  • Name: dsh-ingredient
  • Function: Ingredient recognition
  • Owner: uckkk
  • Category: Model inference
  • License: MIT

Core Capabilities

This plugin provides the ability to return facial skincare routines based on parameters.

Installation and Dependencies

Before installing, make sure the DeepSeek Harness environment and required dependencies are installed. This plugin is implemented purely in Node and has no network dependencies.

The installation command is as follows:

dsh plugin add github:uckkk/dsh-ingredient

Dependencies include:
* @deepseek-ai/cordis: ^4.0.1
* @deepseek-ai/dsh-tools: >=0.1.0-rc.6

Usage

After installation, you can invoke the tools registered by this plugin in your session.

Notes

  • Implemented purely in Node with no network dependencies.
  • The plugin runs with the permissions of the current DSH process. It is recommended to review the source code and license (MIT) before use.

Summary

dsh-ingredient adds a vertical-domain inference tool to the DSH plugin ecosystem, suitable for scenarios that require quickly obtaining skincare routines. For more details, see:
* GitHub repository
* Plugin directory