xby-math
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-math
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-math in the DeepSeek Harness terminal to install; the source is available at https://github.com/xby-skill/xby-math .
About this plugin
When a chat with an LLM calls for expression evaluation, matrix inversion, or solving for an IRR, guessing is slow and error-prone. xby-math pulls those computations directly into the DSH chat, giving instant precise results without switching to a calculator or a Notebook.
The plugin covers a full mathematical toolchain: SymPy-powered symbolic and numeric expression evaluation (variables, trigonometry, logarithms); Polars-based array operations, multi-axis statistics, pivot tables, outlier detection, and Pearson / Spearman correlation matrices; NumPy BLAS matrix arithmetic plus five decompositions (eigen, SVD, QR, Cholesky, LU); SciPy linear-system solvers including overdetermined least-squares; higher-order and partial symbolic differentiation; and a complete finance module for time-value-of-money, compound interest (discrete and continuous), and perpetuities.
Data analysts can build pivot tables and normalize arrays on the fly; finance professionals can invert IRR or discount a growing annuity in one call; STEM students can verify matrix decompositions and solve linear systems; ML engineers can slot L2 normalization, Z-scoring, and log transforms into their pipelines. If you need precise numeric results the moment you ask, without leaving the chat window, xby-math has you covered.
Use Cases
- Solving expressions, matrix operations, and linear systems in chat
- Inverting interest rates, discounting growing annuities, and valuing perpetuities
- Handling normalization, pivot tables, and correlation on the fly
Best For
- Analysts who need precise numeric results instantly in chat
- Finance professionals and students
- STEM and data-science engineers
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.