dsh-prompt-enhancer
Run the following command in DeepSeek Harness:
dsh plugin install yaoshuo530/dsh-prompt-enhancer
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, run dsh plugin install yaoshuo530/dsh-prompt-enhancer from the terminal or the plugin manager to install this plugin; the full source is available at https://github.com/yaoshuo530/dsh-prompt-enhancer .
About this plugin
In DeepSeek Harness, prompting is often a draft-and-hope exercise. You type a vague one-liner and get a generic answer back, because the model needs richer context, clearer structure, and sharper intent to deliver something genuinely useful. dsh-prompt-enhancer closes that gap by adding a ✨ Enhance button to the composer row, turning prompt improvement into a single click.
The enhancement follows a first-principles loop: return to the essence of the question, break down the structure, organize the expression, then review for coherence. The plugin automatically reads the current session system prompt (persona, memory, skill injections) and the last thirty messages of conversation, weaving that context into the rewrite. When key information appears to be missing, a clarification card pops up with option buttons and free-text fields, and generation resumes only after you answer. The enhanced prompt is always shown as a preview first; it lands in the composer only when you click Apply to input and is never sent automatically.
It is made for anyone who works in DSH daily and wants higher-quality prompts with less friction: engineers drafting technical documentation, researchers composing literature summaries, analysts producing structured reports, and anyone who feels the gap between what they know they need and what actually comes out of the keyboard.
Use Cases
- Turn a vague one-liner draft into a structured detailed prompt with one click
- Auto-fill missing context such as audience and scope before generating the enhanced version
- Leverage session memory and persona to produce prompts tightly aligned with the current conversation
Best For
- Technical engineers who craft prompts in DSH on a daily basis
- Researchers and analysts who need high-quality structured instructions
- Any DSH user who wants to reduce prompt-writing friction and improve output quality
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.