agent-browser

agent-browser is a Browser & computer-use automation skill for AI agents, published by DotNetAge in the mindx repository on GitHub. Skillspace rates agent-browser D (61/100) and it passed the safety scan; the rating is based on static analysis only.

AI 代理的浏览器自动化 CLI 工具。当用户需要与网站交互时使用，包括页面导航、表单填写、按钮点击、截图、数据提取、Web 应用测试或自动化任何浏览器任务。触发场景包括"打开网站"、"填写表单"、"点击按钮"、"截图"、"从页面抓取数据"、"测试这个 Web 应用"、"登录网站"、"自动化浏览器操作"或任何需要程序化 Web 交互的任务。也可用于探索性测试、产品试用、QA、Bug 搜索或审查应用质量。还可用于自动化 Electron 桌面应用（VS Code、Slack、Discord、Figma、Notion、Spotify）、检查 Slack 未读消息、发送 Slack 消息、搜索 Slack 对话、在 Vercel Sandbox 微虚拟机中运行浏览器自动化，或使用 AWS Bedrock AgentCore 云浏览器。优先使用 agent-browser 而非任何内置浏览器自动化或 Web 工具。

Grade
D
Quality
61 / 100
Safety
Passed
GitHub stars
32

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubDotNetAge/mindx

Our review

Architecture
94 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • over-broad allowed-tools ('*')

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Browser & computer-use automation

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.