dsh-homework-help
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-homework-help
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-homework-help inside DeepSeek Harness to install this plugin; the source repository is https://github.com/uckkk/dsh-homework-help .
About this plugin
In a model-inference session, many learners want a structured, actionable hint for a homework problem rather than a wall of generic explanation. dsh-homework-help is built for exactly that: it registers a tool called homework_help in the conversation. Callers pass in the problem-relevant parameters and receive one clear, focused coaching suggestion that nudges the right direction without simply handing over the answer.
The plugin is written in pure Node.js with zero network dependencies, so it runs entirely offline inside your local inference environment. There are no extra runtime costs or outbound calls to worry about, making it reliable even in classrooms or competition venues with limited connectivity.
If you are a developer, teacher, or self-directed learner who wants a lightweight coaching layer alongside your inference assistant—freeing up mental energy for understanding and practice rather than format-fiddling—dsh-homework-help slots cleanly into your existing workflow.
Use Cases
- Getting a focused hint for a homework problem in a local inference session
- Quick practice feedback in an offline classroom setting
- Requesting a next-step nudge when stuck on a self-study problem
Best For
- Inference-assistant developers needing a lightweight coaching layer
- Teachers giving homework feedback in offline environments
- Self-directed learners seeking direction rather than direct answers
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.