# midscene-computer-browser

> midscene-computer-browser — quanru-midscene-computer-browser. Use this tool when you need to automate browser interactions using visual inputs, such as clicking on images or buttons, to solve problems like data extraction or automated testing. It takes in visual elements and outputs automated browser actions, streamlining tasks that require human-like interaction with web pages. Ideal for use cases where traditional automation methods fall short, like navigating complex web applications or handling non-standard user interfaces.

Canonical page: https://skillsregistry.net/skills/quanru-midscene-computer-browser  
JSON: https://api.skillsregistry.net/v1/skills/quanru-midscene-computer-browser

## Description

Vision-driven browser automation using Midscene.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/quanru-midscene-computer-browser)

## 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": "quanru-midscene-computer-browser"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/quanru-midscene-computer-browser` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/quanru-midscene-computer-browser/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