# underpixel

> underpixel — leluth-underpixel. Use this tool when you need to record, replay, and analyze visual interactions with web applications, correlating user interface events with underlying API calls. It solves problems of understanding and debugging complex user interfaces, providing timestamped visual-API correlation for tools like Claude Code. Input includes user interactions, outputting correlated visual and API data for analysis and debugging.

Canonical page: https://skillsregistry.net/skills/leluth-underpixel  
JSON: https://api.skillsregistry.net/v1/skills/leluth-underpixel

## Description

Chrome extension + MCP server — record, replay, and understand what's behind the pixels. Timestamped visual-API correlation for Claude Code and any MCP client.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/Leluth/underpixel)

## 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": "leluth-underpixel"
    }
  }
}
```

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