# humanjs

> humanjs — totigm-humanjs. Use this tool when you need to automate browser interactions in a human-like way for AI agents, QA tests, or demos. Humanjs records sessions to video or runnable tests, and allows control over the browser via MCP from your AI, streamlining testing and automation processes. It integrates with git for seamless version control and collaboration.

Canonical page: https://skillsregistry.net/skills/totigm-humanjs  
JSON: https://api.skillsregistry.net/v1/skills/totigm-humanjs

## Description

Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it over MCP from your favorite AI.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/totigm/humanjs)

## 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": "totigm-humanjs"
    }
  }
}
```

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