跳到正文
TakoAPI
返回技能列表

agent-browser

由 matrixy 提供

Clawdbot Tools
26.2k下载量由 clawskills.sh 提供
66星标
18浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Headless browser automation CLI optimized for AI agents.

描述

该技能的功能

Headless browser automation CLI built for AI agent workflows. Takes accessibility tree snapshots of web pages and exposes interactive elements as stable refs (like @e2, @e3) for deterministic targeting. Supports isolated sessions, saved auth state, and network interception.

Ref-based element selection from accessibility tree snapshots avoids the fragility of CSS selectors and XPath that break when layouts change.

何时使用

  • Automating multi-step web form submissions without brittle selectors
  • Running simultaneous admin and user browser sessions for testing
  • Scraping dynamic single-page apps that require JavaScript execution
  • Reusing saved login state to skip authentication on repeat runs
  • Mocking API responses during automated browser workflows

示例工作流

输入

User asks: search Google for 'AI agents' and return the first result link

智能体
  1. 1

    Run agent-browser open https://www.google.com

  2. 2

    Run agent-browser snapshot -i --json to get interactive element refs

  3. 3

    Identify search box ref from snapshot, run agent-browser fill @e1 "AI agents" then agent-browser press Enter

  4. 4

    Run agent-browser wait --load networkidle, then agent-browser snapshot -i --json again

  5. 5

    Run agent-browser get attr @e4 "href" --json to extract the first result URL

输出

Returns the href value of the first search result as JSON

前置要求

  • agent-browser CLI installed globally via npm install -g agent-browser

安装

clawhub install matrixy/agent-browser-clawdbot

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接