dsh-body-type
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-body-type
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-body-type in the DeepSeek Harness terminal to install this plugin. The full source repository is available at https://github.com/uckkk/dsh-body-type.
About this plugin
As Traditional Chinese Medicine (TCM) wellness becomes part of everyday routines, identifying one's constitution and getting tailored health advice in a single step remains a practical pain point. dsh-body-type wraps TCM body-type identification into a lightweight tool that can be invoked directly inside an AI session, removing the need to dig through classical texts.
The core capability is a single tool, body_type, which takes input parameters and returns a corresponding TCM wellness plan. The entire plugin is implemented in pure Node.js with zero network dependencies, so it runs reliably offline and is trivially easy to deploy and maintain.
It is well suited for developers interested in TCM wellness, builders who need a local, self-contained inference capability, and any AI user who wants to build body-type identification into their personal workflow. Released under the MIT license for free use and modification.
Use Cases
- Identifying TCM body constitution and receiving wellness advice in an AI session
- Serving as the core inference module for an offline TCM wellness assistant
- Embedding body-type identification into a personal health management workflow
Best For
- AI developers interested in TCM wellness
- App builders who need local, network-free inference capabilities
- AI users looking to integrate body-type identification into their workflow
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.