# shadow-vision

> shadow-vision — wardlu-shadow-vision. Use this tool when you need to enable text-only LLMs and AI agents to understand images and perform tasks like OCR, visual analysis, and UI inspection. It provides multimodal capabilities, allowing agents to process and analyze visual data, and outputs text-based representations of images. Ideal for applications requiring image understanding and analysis, such as data extraction, content moderation, and accessibility services.

Canonical page: https://skillsregistry.net/skills/wardlu-shadow-vision  
JSON: https://api.skillsregistry.net/v1/skills/wardlu-shadow-vision

## Description

Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.

## Trust

- **Trust score (0–1):** 0.79
- **Verification tier:** scanned
- **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/WardLu/shadow-vision)

## 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": "wardlu-shadow-vision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wardlu-shadow-vision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wardlu-shadow-vision/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