dsh-screenshot-to-code
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-screenshot-to-code
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install satan9394/dsh-screenshot-to-code in DeepSeek Harness to install this plugin; the full source repository is at https://github.com/satan9394/dsh-screenshot-to-code.
About this plugin
Staring at a UI screenshot or design reference and manually translating it into working code is slow and prone to subtle misalignment. dsh-screenshot-to-code tackles that pain point by feeding the visual input straight into a model-inference pipeline, cutting out the back-and-forth pixel-perfect tweaking.
The workflow is straightforward: supply a screenshot, and during inference the model parses the layout, palette, typography, and component structure, then emits the corresponding code snippet. The entire process runs on top of DeepSeek Harness model-inference capabilities, so there is no separate conversion service to stand up.
It is well suited for front-end developers who want to jump from a visual reference into coding quickly, product folks validating rapid prototypes, and solo builders who just need a working interactive version fast before iterating on the details.
Use Cases
- Turn Figma-exported screenshots into front-end component code instantly
- Build a quick interactive prototype right after seeing a competitor UI screenshot
- Photograph a paper design sketch and generate matching HTML/CSS code
Best For
- Front-end developers who want to jump from a visual reference into coding quickly
- Product managers and designers who need to validate UI concepts fast
- Solo builders who want a working interactive version first, then iterate on the details
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.