dsh-go-rules
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-go-rules
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-go-rules in the DeepSeek Harness terminal to install the plugin (source: https://github.com/uckkk/dsh-go-rules).
About this plugin
Go is a deep strategy game whose rules span opening patterns, mid-game tactics, and endgame technique, each demanding different study focus. Many learners and teaching systems lack a flexible, parameterized tool to generate targeted practice plans on the fly. dsh-go-rules was built to close that gap: it structures Go rules into configurable parameters so that educators or automated systems can request tailored study tracks instantly.
The core tool, go_rules, accepts a set of parameters and returns a Go study plan matched to that combination. The entire implementation runs on pure Node with zero external network dependencies, making it lightweight to deploy and immediate to call. It slots naturally into existing inference pipelines or teaching workflows as a rules-based evaluation layer.
Whether you are a Go teacher generating graded practice plans, a self-directed player building a systematic curriculum, or a developer adding an interpretable rules layer to an AI-assisted training pipeline, dsh-go-rules plugs in as a ready-to-use, reproducible source of structured learning-path output.
Use Cases
- Generating graded practice plans on the fly in a Go classroom
- Embedding an interpretable rules-based evaluation layer in AI-assisted training pipelines
- Obtaining structured stage-by-stage Go curriculum paths for self-directed learners
Best For
- Go teachers who need to batch-generate graded study plans
- Self-directed Go players building a systematic learning path
- Game or education app developers adding a rules layer to inference pipelines
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.