# ๐จ dsh-media-skills
### *Give DeepSeek Harness eyes โ and a brush. Read images in any chat, generate new ones, all with free models.*
[](LICENSE)
[](https://python.org)
[](https://github.com/topics/dsh-plugin)
[](docs/SETUP_VISION_EN.md)
[](docs/FREE_VISION_PROVIDERS_EN.md)
[](README.md#-keys--privacy)
[](docs/lang/README_ZH.md)
DeepSeek Harness is brilliant at reasoning โ but a text-only model can't see the image you just dragged into the chat. This bundle fixes that with **two free skills**, a **free vision model route**, and a **vision engine failover chain**:
- ๐ **Paste to read** โ paste, drag, or pick an image in any session; the free vision model turns it into text your current model understands. *(Powered by the DeepSeek Harness core auto-description path โ see [docs/HARNESS_PATCH_EN.md](docs/HARNESS_PATCH_EN.md); this bundle contributes the vision model route and the skill it relies on.)*
- ๐๏ธ **`vision-review`** โ analyze images and screenshots, catch UI visual bugs, detect watermarks, turn images into text.
- ๐จ **`media-tools`** โ generate illustrations, avatars, backgrounds and banners with a free, watermark-free model.
- ๐ **Engine failover** โ GLM-4V-Flash โ SiliconFlow Qwen3-VL โ Google Gemini ([AI Studio](https://aistudio.google.com)) โ any OpenAI-compatible endpoint, with ModLens-style structured evidence output.
No hardcoded keys, no paid API, no file saving, no session switching.
[Why](#-why) ยท [Quick start](#-quick-start) ยท [See it in action](#-see-it-in-action) ยท [Usage](#-usage) ยท [Keys & privacy](#-keys--privacy) ยท [FAQ](#-faq) ยท [Examples](#-examples)
[**English**](README.md) ยท [**็ฎไฝไธญๆ**](docs/lang/README_ZH.md) ยท [**็น้ซไธญๆ**](docs/lang/README_ZH_TW.md) ยท [**ๆฅๆฌ่ช**](docs/lang/README_JA.md) ยท [**ํ๊ตญ์ด**](docs/lang/README_KO.md) ยท [**Espaรฑol**](docs/lang/README_ES.md) ยท [**Deutsch**](docs/lang/README_DE.md) ยท [**Portuguรชs**](docs/lang/README_PT.md) ยท [**ะ ัััะบะธะน**](docs/lang/README_RU.md)
---
## ๐ค Why
Most DSH vision plugins only **read** images โ and many push you through a shared third-party endpoint. `dsh-media-skills` takes a different stance:
| | This bundle | Typical vision-only plugin |
|---|---|---|
| Read images for free | โ
Zhipu GLM-4V-Flash | โ
|
| **Generate** images for free | โ
SiliconFlow Kolors | โ usually absent |
| Auto model route in the picker | โ
installed automatically | sometimes |
| Keys committed to the repo | โ never โ keys stay local | โ ๏ธ often required |
| Docs in multiple languages | โ
9 languages | โ usually English only |
| Privacy | โ
you choose the provider; images only go to your provider | shared free endpoints can see your images |
**Why bring your own free key instead of a built-in anonymous endpoint?** Privacy and reliability. Your images go only to the provider you choose, under your account and your rate limits โ no shared third-party service in the middle.
## โจ What you get
| Capability | What it does | Model | Cost |
|---|---|---|---|
| ๐ Paste-image reading | In a **text-only** session, the input bar gains an โAdd imageโ button (paperclip); pasted images are auto-described by the vision model and handed to the current model as text. *(Harness-core feature: requires the core api-proxy admission patch; this bundle supplies the vision route + skill it depends on)* | Zhipu GLM-4V-Flash | Free |
| ๐ง Vision model route | ใๆบ่ฐฑ GLM-4V-Flash๏ผ่ง่ง๏ผใ appears in the model selector automatically โ pick it for a new conversation and talk about images directly | Zhipu GLM-4V-Flash | Free |
| ๐๏ธ `vision-review` | Analyze / recognize / describe images & screenshots; catch UI visual bugs (overlap, overflow, misalignment); detect watermarks/logos; turn images into text. Optional `--structured` mode returns ModLens-style evidence JSON (summary, full OCR, reading-order layout, entities/relations, uncertainty). Engine failover chain: GLM-4V-Flash โ SiliconFlow Qwen3-VL / Google Gemini (auto-join with free keys) โ any OpenAI-compatible endpoint | GLM-4V-Flash + Qwen3-VL + Gemini | Free |
| ๐จ `media-tools` | Generate images, illustrations, avatars, backgrounds, banners | SiliconFlow Kolors | Free, no watermark |
## โก Quick start
```sh
dsh plugin --profile