dsh-teacher-preset
Run the following command in DeepSeek Harness:
dsh plugin install AIMarshallLee/dsh-teacher-preset
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install AIMarshallLee/dsh-teacher-preset; the source is available at https://github.com/AIMarshallLee/dsh-teacher-preset .
About this plugin
Lesson planning, test design, rubrics, parent notices, and student progress tracking tend to live in separate tools—Word, spreadsheets, various SaaS apps—making it hard to close the loop from designing a lesson to improving the next one with concrete evidence.
dsh-teacher-preset turns DeepSeek Harness into a local-first teaching workstation. It ships two mode-isolated template sets (14 templates total for school and tutoring teachers), supports batch template loading, full-text search, and A4-ready HTML export. More importantly, it chains teaching context, one-click unit packages (with SHA-256 checksums and quality gates), per-student per-objective assessment diagnostics, and next-lesson adjustments into a single traceable evidence loop, all stored entirely on the local machine with no cloud dependency.
If you are an in-service school teacher or a tutoring-center instructor who wants to run a full prepare, teach, reflect, and adjust cycle inside one AI assistant while keeping sensitive student data off the cloud, this plugin is worth a look.
Use Cases
- Generate a lesson plan, worksheet, and rubric in one call to build a traceable unit package
- Record per-student per-objective scores, auto-compute mastery levels, and produce next-lesson adjustments
- Export Markdown materials to A4-formatted, printable HTML with Chinese font support
Best For
- In-service teachers in public or private schools
- Course and curriculum staff at tutoring institutions
- Educators who want all student data to stay on their local machine
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.