# heravision

> heravision — djfarhad368-heravision. Use this tool when you need to extract UI structure from screenshots for text-only Large Language Models (LLMs), enabling them to better understand visual interfaces. Heravision solves the problem of LLMs being unable to interpret visual data, providing a pure Go, offline solution with a native binary. It takes screenshots as input and outputs the extracted UI structure, making it ideal for use cases where visual data needs to be converted into a text-based format.

Canonical page: https://skillsregistry.net/skills/djfarhad368-heravision  
JSON: https://api.skillsregistry.net/v1/skills/djfarhad368-heravision

## Description

Extract UI structure from screenshots for text-only LLMs with a pure Go, offline, MCP-native binary.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **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/djfarhad368/heravision)

## 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": "djfarhad368-heravision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/djfarhad368-heravision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/djfarhad368-heravision/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