Home / Plugins / UI Enhancements / dsh-vision-toolkit
dsh-vision-toolkit
★ 870Maintainer: Anionex
A DeepSeek Harness plugin that helps text-only models do visual work: paste-and-ask images, long-screenshot OCR and UI rebuilding.
What it does
- Paste an image in DSH Web and the text model switches to its vision variant automatically
- The model extracts task-relevant evidence, such as where the error or button is
- A bundled Skill explains what to inspect, which tool to use and how to verify
Install
dsh plugin add github:Anionex/dsh-vision-toolkit
- Install and start DeepSeek Harness:
npx @deepseek-ai/dsh web - Run the install command above (the CLI resolves the plugin and verifies its source)
- Confirm with dsh plugins list; restart Harness if required
For reproducible installs, append #commit to pin a specific revision.
Plugin info
| GitHub stars | 870 |
| License | MIT |
| Primary language | TypeScript |
| Last push | 2026-09-08 |
| Cataloged | 2026-08-15 |
| Repository | github.com/Anionex/dsh-vision-toolkit |
| Category | UI Enhancements |
Audit before installing
Plugins run with your dsh process permissions and may execute code during installation. Read the repository source and license first, and check for destructive commands or excessive access. This site only indexes; it does not vouch for third-party plugins.
Plugins run with your dsh process permissions and may execute code during installation. Read the repository source and license first, and check for destructive commands or excessive access. This site only indexes; it does not vouch for third-party plugins.
Related plugins
Facts (stars, license, language, last push, repository) come from a public plugin catalog snapshot: 2026-09-13。Descriptions are rewritten by us.