# 🎨 dsh-media-skills ### *Give DeepSeek Harness eyes — 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 — 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**: - 📎 **Paste to read** — 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 — see [docs/HARNESS_PATCH_EN.md](docs/HARNESS_PATCH_EN.md); this bundle contributes the vision model route and the skill it relies on.)* - 👁️ **`vision-review`** — analyze images and screenshots, catch UI visual bugs, detect watermarks, turn images into text. - 🎨 **`media-tools`** — generate illustrations, avatars, backgrounds and banners with a free, watermark-free model. - 🔀 **Engine failover** — GLM-4V-Flash → SiliconFlow Qwen3-VL → Google Gemini ([AI Studio](https://aistudio.google.com)) → any OpenAI-compatible endpoint, with ModLens-style structured evidence output. No hardcoded keys, no paid API, no file saving, no session switching. [Why](#-why) · [Quick start](#-quick-start) · [See it in action](#-see-it-in-action) · [Usage](#-usage) · [Keys & privacy](#-keys--privacy) · [FAQ](#-faq) · [Examples](#-examples) [**English**](README.md) · [**简体中文**](docs/lang/README_ZH.md) · [**繁體中文**](docs/lang/README_ZH_TW.md) · [**日本語**](docs/lang/README_JA.md) · [**한국어**](docs/lang/README_KO.md) · [**Español**](docs/lang/README_ES.md) · [**Deutsch**](docs/lang/README_DE.md) · [**Português**](docs/lang/README_PT.md) · [**Русский**](docs/lang/README_RU.md)
*How it works in one picture:*
## 🚀 Usage
Three ways to read images:
| Way | How | When |
|---|---|---|
| **A. Paste directly (recommended)** | In any session, click the 📎 button / drag / paste an image and send | Everyday image questions — no file saving, no model switching |
| **B. Vision model session** | New conversation, pick 智谱 GLM-4V-Flash（视觉）, paste images and chat | Multi-turn image conversations, native `read_image` |
| **C. Files + skill** | Put the image in the workspace and say “read this image with vision-review” | Batch review, scripted workflows |
Descriptions follow your message language (Chinese message → Chinese description; English message → English description; no text → Chinese).
Also just say:
- “Look at this image / check this screenshot for visual bugs” → `vision-review`
- “Generate an image of …” → `media-tools`
## 🔑 Keys & privacy
Keys are **never stored in this repo**. Skill scripts read, in order: environment variables → `~/.dsh/secrets/media-tools.env` → `~/.codex/secrets/media-tools.env` (legacy fallback). The vision model route reads `GLM_API_KEY` from DSH's credential store.
Where to get the keys (all free): Zhipu — [open.bigmodel.cn](https://open.bigmodel.cn) → API Keys (glm-4v-flash). SiliconFlow — [siliconflow.cn](https://siliconflow.cn) → API Keys (Kolors). Google (optional, joins the vision failover chain automatically) — [aistudio.google.com](https://aistudio.google.com) → Get API key.
```sh
# ~/.dsh/secrets/media-tools.env (chmod 600, one KEY=value per line)
GLM_API_KEY=...
SILICONFLOW_API_KEY=...
GEMINI_API_KEY=... # optional
```
Your images are sent only to the provider you configure — never to this repo, never to a shared anonymous endpoint.
> Privacy note on Gemini: Google's free-tier key comes with data-use terms — requests may be used to improve Google products. For sensitive images (IDs, internal docs, customer data), prefer the direct domestic engines (Zhipu / SiliconFlow).
## ❓ FAQ
**Does paste-image reading require a DeepSeek Harness core patch?**
The auto-describe pipeline lives in the Harness **core** (`api-proxy` image-admission logic; see [docs/HARNESS_PATCH_EN.md](docs/HARNESS_PATCH_EN.md)). This bundle ships the **model route + skills**: the vision model works on any DSH build, but paste-image reading requires a Harness build with that core support — see FAQ Q1 in [docs/SETUP_VISION_EN.md](docs/SETUP_VISION_EN.md).
**Why not just use a built-in free endpoint with no key at all?**
We prefer to let you own the route: your images go to the provider you pick, under your rate limits, with no shared middleman. The keys are free and take about two minutes to create.
**Is `media-tools` really free?**
Yes — SiliconFlow Kolors is free and watermark-free. If a model is temporarily disabled, the skill lists available models and you can switch.
## 🎁 Examples
Sample material to try instantly — 6 AI-generated images with their prompts, plus a purpose-built vision test card (title, buttons, bar-chart values) for checking reading accuracy:
→ [examples/README.md](examples/README.md)
## 🗺️ Layout
```
dsh-media-skills/
├── package.json # dsh.bundle manifest
├── cordis.patch.yml # plugin layer
├── index.js # registers skills + seeds the zhipu-vision model route
├── skills/
│ ├── vision-review/ # image reading
│ └── media-tools/ # image generation
├── examples/ # sample images + vision test card
├── docs/
│ ├── screenshots/ # demo mockup & how-it-works diagram
│ ├── SETUP_VISION_EN.md # detailed setup guide (English)
│ ├── SETUP_VISION.md # 详细配置指南（中文）
│ ├── HARNESS_PATCH_EN.md# core patch notes (English)
│ ├── HARNESS_PATCH.md # 本体补丁说明（中文）
│ ├── COMPARE_MODLENS.md # 与 ModLens 的对比/共存（中文）
│ └── lang/ # READMEs in 9 languages
├── scripts/make-banner.py # regenerates docs/social-preview.png
└── docs/social-preview.png
```
## 🧩 Using ModLens alongside?
Both this bundle and [ModLens](https://github.com/liustack/modlens) give text-only models vision. Installed together they do not conflict: ModLens intercepts pastes first (path → `modlens_read_image` tool), and this bundle's api-proxy fallback handles anything it doesn't take over. See [docs/COMPARE_MODLENS.md](docs/COMPARE_MODLENS.md) (中文) for the full comparison, the paste routing order, and how to point ModLens at the same free Zhipu endpoint.
## 🤝 Join the DSH plugin ecosystem
DeepSeek Harness developer preview is still in its testing phase for Harness developers; core plugins and base APIs will keep iterating. We look forward to exploring the upper limits of intelligence together with developers worldwide, on top of open-source, open, reusable, and composable infrastructure.
- [dsh-plugin topic](https://github.com/topics/dsh-plugin)
- [Quickstart](https://deepseek-harness.github.io/deepseek-harness/guide/quickstart)
- [DeepSeek Harness repo](https://github.com/deepseek-ai/deepseek-harness)
- [dsh-agent-conductor](https://github.com/MJorgin/dsh-agent-conductor) — 同作者的指挥家：在 DSH 里派活给 11 种外部 agent CLI（Codex / Claude Code / TraeCode…）
> This repo is tagged [`dsh-plugin`](https://github.com/topics/dsh-plugin) and listed in the [awesome-dsh-plugin](https://github.com/awesome-dsh-plugin/awesome-dsh-plugin) curated list. PRs, issues and translations are welcome.
## 📄 License
[MIT](LICENSE)