# picturereader

> DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.

## Metadata

- Author: [@jing-hy](https://github.com/jing-hy)
- Repo: <https://github.com/jing-hy/picturereader>
- GitHub: [jing-hy/picturereader](https://github.com/jing-hy/picturereader)
- Stars: 28
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh-plugin`, `image-reading`, `ocr`, `pixel-art`, `vision`
- Forks: 3
- Open Issues: 0
- Last push: 2026-08-20T09:39:29.000Z
- Added: 2026-08-20T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add picturereader
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [picturereader](https://deepseek-plugin.org/plugins/jing-hy/picturereader)