# deepseek-eyes

> deepseek-eyes — shaohan-he-deepseek-eyes. Use this tool when you need to analyze images and generate text descriptions, as it enables visual recognition by processing clipboard images through a visual model, providing a textual output. It solves problems related to image understanding and description, such as object identification and scene explanation. Ideal for use cases where visual data needs to be translated into readable text, like content creation or data analysis.

Canonical page: https://skillsregistry.net/skills/shaohan-he-deepseek-eyes  
JSON: https://api.skillsregistry.net/v1/skills/shaohan-he-deepseek-eyes

## Description

给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Shaohan-He/deepseek-eyes)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shaohan-he-deepseek-eyes"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shaohan-he-deepseek-eyes` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shaohan-he-deepseek-eyes/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt