# graea

> graea — estejosh-graea. Use this tool when you need to integrate a large language model (LLM) with a Telegram bot, enabling it to capture and interpret visual data through screenshots and a vision reader. It solves problems related to LLMs interacting with visual interfaces, providing a user client and database functionality through DuckDB. The tool accepts inputs via MCP, CLI, or HTTP and outputs interpreted visual data, making it suitable for applications requiring LLMs to interact with graphical user interfaces.

Canonical page: https://skillsregistry.net/skills/estejosh-graea  
JSON: https://api.skillsregistry.net/v1/skills/estejosh-graea

## Description

Give any LLM eyes on a Telegram bot it built: MTProto user client + real screenshots + vision reader + DuckDB run memory. MCP / CLI / HTTP. Source-available (UFL-2.0) — UFL-H-1a

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/estejosh/graea)

## 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": "estejosh-graea"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/estejosh-graea` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/estejosh-graea/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