# Perfect

> Perfect — gtarafdar-perfect. Use this tool when you need to automate browser interactions or provide hands-on capabilities to Cursor agents. It solves problems related to browser automation, navigation, and data extraction by enabling actions like clicking, filling forms, and taking screenshots. With permission modes, it allows for controlled and secure execution of browser actions through an unofficial MCP bridge in Chrome.

Canonical page: https://skillsregistry.net/skills/gtarafdar-perfect  
JSON: https://api.skillsregistry.net/v1/skills/gtarafdar-perfect

## Description

Unofficial open-source MCP bridge that gives Cursor agents hands in your real Chrome browser. Enables navigation, clicking, filling, screenshots, and other browser actions with permission modes.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/b18n98wk2z)
- **Repository:** <https://github.com/Gtarafdar/perfect>

## 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": "gtarafdar-perfect"
    }
  }
}
```

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