dsh-slope
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-slope
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install uckkk/dsh-slope; the full source code is available at https://github.com/uckkk/dsh-slope .
About this plugin
In model-inference and data-analysis workflows, slope calculation looks trivial but often means writing throwaway scripts or reaching out to external services every time. dsh-slope wraps that operation into a tool you can call directly inside a session, removing the recurring setup overhead.
Its core philosophy is extreme lightness: a pure Node.js implementation with zero network dependencies. No proxies, no remote APIs, no environment configuration—install the plugin and invoke the registered tool in your session to get the result. No extra dependencies, no complexity, ready to use out of the box.
If you are working on trend analysis, pre-computing inputs for regression fits, or simply need to verify the rate of change across a small set of values during a conversation, dsh-slope is a plug-and-play option. Released under the MIT license for free use and further development.
Use Cases
- Compute the overall slope across a set of data points in seconds
- Validate trend direction and magnitude before running regression fits
- Calculate on the fly within a session without deploying scripts or switching environments
Best For
- Quant and data engineers who run trend analysis frequently
- Developers who need quick numeric validation inside a chat session
- Users who prefer zero-network, plug-and-play lightweight utilities
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
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.