# dsh

> Vision translation for DSH: image → structured <vision-context> primitives via an auxiliary VLM bridge. DeepSeek Harness plugin (视觉翻译，图→视觉基元文本)

## Metadata

- Author: [@BingL-Li](https://github.com/BingL-Li)
- Repo: <https://github.com/BingL-Li/vision-translation>
- GitHub: [BingL-Li/vision-translation](https://github.com/BingL-Li/vision-translation)
- Stars: 0
- Language: Python
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `cordis-plugin`, `deepseek-harness-plugin`, `dsh-plugin`
- Forks: 0
- Open Issues: 1
- Last push: 2026-08-19T23:16:41.000Z
- Added: 2026-08-18T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add vision-translation-dsh
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh](https://deepseek-plugin.org/plugins/BingL-Li/vision-translation/adapters/dsh)
