dsh-teacher
Run the following command in DeepSeek Harness:
dsh plugin install Yihong89/dsh-teacher
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness using the command `dsh plugin install Yihong89/dsh-teacher`, with the full source code at https://github.com/Yihong89/dsh-teacher.
About this plugin
Traditional AI assistants often provide direct answers, but cognitive science shows that passive learning is less effective than active recall. dsh-teacher flips this approach: it turns the agent into a patient teacher that never gives answers directly. Instead, it uses Socratic questioning to guide you toward discovering solutions yourself. Along the way, it quietly logs gaps in your reasoning and employs spaced repetition to revisit those gaps at optimal intervals, ensuring deeper retention.
The plugin’s core strength lies in embedding educational principles into AI interactions. It lets you load question sets, engages you in a guided Q&A loop, and maintains a concise ledger of learning gaps. Whether you're starting a new topic or reinforcing known material, it adapts to your pace, making the learning process more robust and personalized.
dsh-teacher is ideal for educators seeking interactive tools, students aiming for thorough understanding, or lifelong learners who want to solidify knowledge. If you're tired of passive absorption and prefer a dynamic, evidence-based teaching method, this plugin transforms every conversation into a productive learning session, fostering genuine comprehension through dialogue.
Use Cases
- Students load Markdown question sets for self-directed learning.
- Teachers guide students in exploring concepts through questioning.
- Learners periodically review marked knowledge gaps.
Best For
- Self-directed students seeking deep understanding of course material.
- Educators looking for interactive teaching tools.
- Lifelong learners focused on knowledge retention and mastery.
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.