# clawdcursor

> clawdcursor — amrdab-clawdcursor. Use this tool when you need to automate desktop interactions across different operating systems, providing AI agents with the ability to interact with and verify desktop environments on Windows, macOS, and Linux. It solves problems of OS compatibility and ground-truth verification, allowing for seamless automation of tasks. With clawdcursor, AI agents can receive inputs from and send outputs to desktop applications, enabling automated testing, data entry, and other tasks.

Canonical page: https://skillsregistry.net/skills/amrdab-clawdcursor  
JSON: https://api.skillsregistry.net/v1/skills/amrdab-clawdcursor

## Description

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/AmrDab/clawdcursor)

## 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": "amrdab-clawdcursor"
    }
  }
}
```

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