dsh-geometric-series
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-geometric-series
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-geometric-series in your terminal to install the plugin; the full source code is available at https://github.com/uckkk/dsh-geometric-series
About this plugin
Geometric-series calculations keep showing up in model-inference or chat workflows—finding the nth term, summing a range, or deriving the common ratio—yet reaching for a full math library or an external API is overkill. dsh-geometric-series exists to keep that small class of arithmetic inside the conversation itself.
Built entirely in Node.js with zero third-party dependencies and zero network calls, the plugin registers its tools into the session as soon as it is installed. The model can then invoke them mid-reasoning to compute terms, partial sums, or ratios on demand, with everything resolving locally and instantly.
It is a natural fit if you are assembling conversation-first inference pipelines and occasionally need basic geometric-series operations. No extra service to deploy, no heavyweight math dependency to pull in—just a small, MIT-licensed tool that slots cleanly into any project.
Use Cases
- Ask the model in-chat to compute the nth term or partial sum of a geometric series
- Derive or verify the common ratio mid-reasoning with a single tool call
- Complete basic geometric-series arithmetic fully offline with no network access
Best For
- Developers building conversation-first inference pipelines that occasionally need sequence math
- Teams that prefer zero third-party dependencies over pulling in heavyweight math libraries
- Plugin users who want install-and-go tools with no external services or APIs required
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.