xby-calculator-kel
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-calculator-kel
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-calculator-kel in your terminal to install the plugin into DeepSeek Harness from https://github.com/xby-skill/xby-calculator-kel.
About this plugin
Large language models frequently produce imprecise or outright wrong results when handling multi-step arithmetic, exponentiation, or factorials. xby-calculator-kel bridges the Model Context Protocol (MCP) to expose a set of deterministic numeric operations as independent tools, offloading computation to a dedicated backend and eliminating mathematical errors caused by LLM hallucination.
The plugin provides seven core operations: floating-point addition, subtraction, multiplication, division, power, square root, and integer factorial. Each operation is registered as a standalone tool that the model can freely compose. A built-in set_xby_apikey tool lets you configure the API key once in conversation, with automatic persistence across service restarts.
If your workflow involves formula solving, scientific-computation assistance, or step-by-step educational demonstrations where every number must be accurate and verifiable, this plugin is a lightweight bridge designed for exactly that need.
Use Cases
- Let the model execute multi-step arithmetic and verify each result in conversation
- Invoke deterministic operations to assist scientific computation or formula solving
- Demonstrate factorial, power, and other operations step by step in teaching
Best For
- Developers who need precise math operations inside LLM workflows
- Integration engineers building MCP toolchains and composing multiple tools
- Application builders creating scientific-computation or educational demos
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.