# screencye

> screencye — veloce-ai-idm-deepsee. Use this tool when you need to decode visual information from screenshots into structured text for text-only LLMs to analyze and reason about UI layouts. It solves the problem of limited vision capabilities in text-only models by providing exact text data, including words, coordinates, sizes, and colors. This tool is ideal for use cases where vision models or VRAM usage are not feasible, and pure-code CV and OCR are preferred.

Canonical page: https://skillsregistry.net/skills/veloce-ai-idm-deepsee  
JSON: https://api.skillsregistry.net/v1/skills/veloce-ai-idm-deepsee

## Description

Eyes for text-only LLMs: decodes screenshots into exact structured text (words, coordinates, sizes, colors) using pure-code CV and OCR. Enables text-only models to reason about UI layouts without vision models or VRAM usage.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ilj95pv4xj)
- **Repository:** <https://github.com/veloce-ai-idm/deepsee>

## 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": "veloce-ai-idm-deepsee"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/veloce-ai-idm-deepsee` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/veloce-ai-idm-deepsee/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