dsh-k12-lesson-builder
Run the following command in DeepSeek Harness:
dsh plugin install shyboy/dsh-k12-lesson-builder
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install shyboy/dsh-k12-lesson-builder in your terminal to install; the source code is hosted at https://github.com/shyboy/dsh-k12-lesson-builder
About this plugin
Preparing a middle-school English lesson usually means shuttling between PowerPoint and Word: you lay out the 45-minute flow in slides, then retype the same content into a lesson-plan template, and any edit has to be made twice. dsh-k12-lesson-builder removes that duplication.
The plugin follows a blueprint-first pipeline. The DSH agent extracts knowledge points from teacher-supplied textbooks and curriculum standards, produces a structured lesson-blueprint.json, then renders the PPTX from that single source of truth. After the deck is finalized, slide IDs are mapped into eleven content-control tags in the Word lesson plan, and both files are re-opened for an integrity audit. Everything runs locally—no uploads, no second model call—and all intermediates stay in the current DSH workspace for easy rollback.
It is built for middle-school English teachers on Windows 10/11 who use desktop Word and PowerPoint and already work from a district or school template. It explicitly does not support macOS, Linux, WPS, or web-based Office, and it contains no OCR—scanned-image PDFs must be converted to selectable-text formats first.
Use Cases
- Generate synchronized PPT and Word lesson plans from teacher-provided textbook and curriculum standards
- Produce multi-period teaching materials in bulk from existing templates at the start of a term
- Apply a unified school PPT and Word template to a new teaching unit quickly
Best For
- Middle-school English teachers
- Educators using desktop Microsoft Office on Windows
- DeepSeek Harness plugin users
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.