dsh-ppt-pages
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-ppt-pages
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness by running dsh plugin install uckkk/dsh-ppt-pages; the source repository is https://github.com/uckkk/dsh-ppt-pages .
About this plugin
One of the most nagging questions when building a slide deck is how many pages to actually include. Too many and the audience drifts; too few and the content feels thin. dsh-ppt-pages solves this by registering a ppt_pages tool that precisely calculates a recommended page count from the parameters you supply and returns a detailed breakdown, giving you a concrete, data-driven starting point before you design a single slide.
The plugin is implemented entirely in Node with zero network dependencies. Once installed you invoke the tool straight from a session with no extra setup or external services required. It is lightweight and plug-and-play, turning a gut-feel guess into a parameterized, justifiable decision.
It is a great fit for developers, educators, and content creators who regularly prepare lectures, project reviews, or public talks. If you have ever spent an unreasonable amount of time debating slide count, this plugin helps you lock in a framework quickly so you can focus on what actually matters: the content itself.
Use Cases
- Deciding total slide count before a public talk
- Allocating page budgets per section while preparing course material
- Planning the overall length of a project review deck
Best For
- Developers and engineers who build decks regularly
- Educators preparing lectures or internal training sessions
- Content creators who deliver periodic project reviews or public talks
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.