Preface¶
The DeepSeek Harness (DSH) ecosystem follows the “everything is a plugin” philosophy, allowing developers to install community plugins to extend the specific capabilities of agents. When building workflows for vertical domains, plugins are often needed to provide support for specific business logic. dsh-insur-plan aims to solve the automated generation of household insurance configurations.
Plugin Overview¶
This is a workflow plugin maintained by uckkk. It is a pure Node.js implementation that does not initiate network requests at runtime, making it suitable for deployment in offline environments or environments with strict network restrictions.
Core Features¶
The plugin registers a tool named insur_plan. Its core function is to accept parameters and return a household insurance plan based on those parameters.
Installation and Activation¶
Run the following command in the terminal to complete the installation:
dsh plugin add github:uckkk/dsh-insur-plan
The installation process automatically handles dependencies and configuration. After the plugin is registered, it can be called directly in a session.
Typical Usage¶
After installation, you can use the plugin by directly calling the tool it registers within a DSH chat session. The specific invocation method depends on DSH’s interface specification; typically, commands are issued directly using the tool name.
Use Cases and Notes¶
- Use Cases: Suitable for scenarios that require automatically generating household insurance configuration recommendations within a conversational flow.
- Environment Requirements: Before use, ensure your local environment satisfies the following PeerDependencies:
@deepseek-ai/cordis:^4.0.1@deepseek-ai/dsh-tools:>=0.1.0-rc.6
- Runtime Permissions: The plugin runs with the permissions of the current DSH process. It is recommended to review the source code and license (MIT) before installation.
Summary¶
dsh-insur-plan provides structured generation of household insurance configurations and has no network dependency. For more technical details and source code, refer to the GitHub repository or the DSH community directory.