🌐 Agent Browser Clawdbot.Bak 2026 01 28T18:01:09+10:30 — 浏览器自动化

v1.0.0

无头浏览器自动化工具 CLI 为 AI 智能体优化 with 无障碍树快照 and 基于引用的元素选择

1· 1.9k·1 当前·2 累计
by @nicoataiza·MIT-0
下载技能包 项目主页
License
MIT-0
最后更新
2026/4/8
0
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
安全
medium confidence
The skill's instructions, commands, and file-access expectations match a headless browser automation CLI and are internally consistent, but installing/running the referenced CLI and using saved state files carry normal risks that you should verify before use.
安全有层次,运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发,无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/1/28

- Initial release of Agent Browser skill. - Offers fast, ref-based headless browser automation for AI agents. - Uses accessibility tree snapshots for deterministic element selection. - Supports multi-step workflows, session isolation, and state persistence. - Includes detailed examples and recommended best practices.

可疑

安装命令

点击复制
官方npx clawhub@latest install agent-browser-clawdbot-bak-2026-01-28t18-01-09-10-30
🇨🇳 镜像加速npx clawhub@latest install agent-browser-clawdbot-bak-2026-01-28t18-01-09-10-30 --registry https://cn.longxiaskill.com

技能文档

Fast browser automation using accessibility tree snapshots with refs for deterministic element selection.

为什么 使用 在...上 Built-在...中 Browser Tool

使用 agent-browser 当...时:

  • Automating multi-step workflows
  • 需要 deterministic 元素 selection
  • Performance critical
  • Working 带有 complex SPAs
  • 需要 会话 isolation

使用 built-在...中 browser tool 当...时:

  • 需要 screenshots/PDFs 对于 analysis
  • Visual inspection 必填
  • Browser 扩展 integration needed

Core Workflow

# 1. Navigate and snapshot
agent-browser open https://example.com
agent-browser snapshot -i --json

# 2. Parse refs from JSON, then interact agent-browser click @e2 agent-browser fill @e3 "text"

# 3. Re-snapshot after page changes agent-browser snapshot -i --json

键 Commands

导航

agent-browser open 
agent-browser back | forward | reload | close

Snapshot (Always 使用 -i --json)

agent-browser snapshot -i --json          # Interactive elements, JSON output
agent-browser snapshot -i -c -d 5 --json  # + compact, depth limit
agent-browser snapshot -s "#main" -i      # Scope to selector

Interactions (Ref-based)

agent-browser click @e2
agent-browser fill @e3 "text"
agent-browser type @e3 "text"
agent-browser hover @e4
agent-browser check @e5 | uncheck @e5
agent-browser select @e6 "value"
agent-browser press "Enter"
agent-browser scroll down 500
agent-browser drag @e7 @e8

获取 Information

agent-browser get text @e1 --json
agent-browser get html @e2 --json
agent-browser get value @e3 --json
agent-browser get attr @e4 "href" --json
agent-browser get title --json
agent-browser get url --json
agent-browser get count ".item" --json

Check State

agent-browser is visible @e2 --json
agent-browser is enabled @e3 --json
agent-browser is checked @e4 --json

Wait

agent-browser wait @e2                    # Wait for element
agent-browser wait 1000                   # Wait ms
agent-browser wait --text "Welcome"       # Wait for text
agent-browser wait --url "/dashboard"   # Wait for URL
agent-browser wait --load networkidle     # Wait for network
agent-browser wait --fn "window.ready === true"

Sessions (Isolated Browsers)

agent-browser --session admin open site.com
agent-browser --session user open site.com
agent-browser session list
# Or via env: AGENT_BROWSER_SESSION=admin agent-browser ...

State Persistence

agent-browser state save auth.json        # Save cookies/storage
agent-browser state load auth.json        # Load (skip login)

Screenshots & PDFs

agent-browser screenshot page.png
agent-browser screenshot --full page.png
agent-browser pdf page.pdf

Network Control

agent-browser network route "/ads/" --abort           # Block
agent-browser network route "/api/" --body '{"x":1}'  # Mock
agent-browser network requests --filter api              # View

Cookies & Storage

agent-browser cookies                     # Get all
agent-browser cookies set name value
agent-browser storage local key           # Get localStorage
agent-browser storage local set key val

Tabs & Frames

agent-browser tab new https://example.com
agent-browser tab 2                       # Switch to tab
agent-browser frame @e5                   # Switch to iframe
agent-browser frame main                  # Back to main

Snapshot 输出 格式

{
  "success": true,
  "data": {
    "snapshot": "...",
    "refs": {
      "e1": {"role": "heading", "name": "Example Domain"},
      "e2": {"role": "button", "name": "Submit"},
      "e3": {"role": "textbox", "name": "Email"}
    }
  }
}

Best Practices

  • Always 使用 -i 标志 - Focus 在...上 interactive elements
  • Always 使用 --json - Easier 到 解析
  • Wait 对于 stability - agent-browser wait --加载 networkidle
  • 保存 auth state - Skip 登录 flows 带有 state 保存/加载
  • 使用 sessions - Isolate 不同 browser contexts
  • 使用 --headed 对于 debugging - See 什么's happening

示例: 搜索 和 Extract

agent-browser open https://www.google.com
agent-browser snapshot -i --json
# AI identifies search box @e1
agent-browser fill @e1 "AI agents"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i --json
# AI identifies result refs
agent-browser get text @e3 --json
agent-browser get attr @e4 "href" --json

示例: Multi-会话 Testing

# Admin session
agent-browser --session admin open app.com
agent-browser --session admin state load admin-auth.json
agent-browser --session admin snapshot -i --json

# User session (simultaneous) agent-browser --session user open app.com agent-browser --session user state load user-auth.json agent-browser --session user snapshot -i --json

Installation

npm install -g agent-browser
agent-browser install                     # Download Chromium
agent-browser install --with-deps         # Linux: + system deps

Credits

Skill created by Yossi Elkrief (@MaTriXy)

agent-browser CLI by Vercel Labs

数据来源:ClawHub ↗ · 中文优化:龙虾技能库