Analyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.
- GitHub stars
- 1
- License
- MIT
- Added
- 2026-08-27
GitHub info
- GitHub stars
- 1
- License
- MIT
- Primary language
- JavaScript
- Last push
- Aug 22, 2026, 10:55 AM
- Maintainer
- InkshadeWoods
- Added
- 2026-08-27
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
对截图进行 UI 复刻的对话
https://raw.githubusercontent.com/InkshadeWoods/dsh-tool-visual-primitives/master/test/test-2-Replicate_Image_UI.png
对话视觉入口成功读取图片
https://raw.githubusercontent.com/InkshadeWoods/dsh-tool-visual-primitives/master/test/test-1-Read_Image_Information.png
根据视觉证据生成的 HTML 页面
https://raw.githubusercontent.com/InkshadeWoods/dsh-tool-visual-primitives/master/test/test-2-Replicate_UI_Display.png
Install
dsh plugin --profile web add dsh-tool-visual-primitivesREADME badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/InkshadeWoods/dsh-tool-visual-primitives)Related plugins
Vision & Multimodalmodlens
★ 3768Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-router
★ 1030Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
★ 842Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.