代理浏览器

数据 社区

技能解读

当前原文的自动摘译,尚未人工审校。

核心工作流程

agent-browser open <url> — 导航 agent-browser snapshot -i — 获取带有引用的交互元素(@e1、@e2、...) 使用引用进行交互 — click @e1、fill @e2 "text" 任何导航或 DOM 更改后重新快照 — 引用无效 当您不需要中间输出时,使用 && 链接命令:

内嵌框架

iframe 内容内嵌在快照中。直接与 iframe 引用交互 - 无需框架切换。

清理

完成后始终关闭会话:

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
数据
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@sipeed · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
macOS · Linux · Windows
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 命令执行
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Agent Browser

CLI browser automation via Chrome/Chromium CDP. Install: `npm i -g agent-browser && agent-browser install`.

**Before using this skill**, verify the tool is available by running `which agent-browser`. If the command is not found, tell the user that browser automation requires the `agent-browser` CLI and Chromium, which are only available in the heavy container image. Do not attempt to install it at runtime.

## Core Workflow

1. `agent-browser open <url>` — navigate
2. `agent-browser snapshot -i` — get interactive elements with refs (`@e1`, `@e2`, ...)
3. Interact using refs — `click @e1`, `fill @e2 "text"`
4. Re-snapshot after any navigation or DOM change — refs are invalidated

```bash
agent-browser open https://example.com/form
agent-browser snapshot -i
# @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "secret"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i
```

Chain commands with `&&` when you don't need intermediate output:
```bash
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i
```

## Commands

```bash
# Navigation
agent-browser open <url>
agent-browser close

# Snapshot
agent-browser snapshot -i                # Interactive elements with refs
agent-browser snapshot -s "#selector"    # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1
agent-browser fill @e2 "text"            # Clear + type
agent-browser type @e2 "text"            # Type without clearing
agent-browser select @e1 "option"
agent-browser check @e1
agent-browser press Enter
agent-browser scroll down 500

# Get info
agent-browser get text @e1
agent-browser get url
agent-browser get title

# Wait
agent-browser wait @e1                   # Wait for element
agent-browser wait --load networkidle    # Wait for network idle
agent-browser wait --url "**/dashboard"  # Wait for URL pattern
agent-browser wait --text "Welcome"      # Wait for text
agent-browser wait 2000                  # Wait ms

# Capture
agent-browser screenshot                 # Screenshot to temp dir
agent-browser screenshot --full          # Full page
agent-browser screenshot --annotate      # With numbered element labels ([N] -> @eN)
agent-browser pdf output.pdf

# Semantic locators (when refs unavailable)
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
```

## Authentication

```bash
# Option 1: Import from user's running Chrome
agent-browser --auto-connect state save ./auth.json
agent-browser --state ./auth.json open https://app.example.com

# Option 2: Persistent profile
agent-browser --profile ~/.myapp open https://app.example.com/login
# ... login once, all future runs are authenticated

# Option 3: Session name (auto-save/restore)
agent-browser --session-name myapp open https://app.example.com/login
# ... login, close, next run state is restored

# Option 4: State file
agent-browser state save auth.json
agent-browser state load auth.json
```

## Iframes

Iframe content is inlined in snapshots. Interact with iframe refs directly — no frame switch needed.

## Parallel Sessions

```bash
agent-browser --session s1 open https://site-a.com
agent-browser --session s2 open https://site-b.com
agent-browser session list
```

## JavaScript Eval

```bash
agent-browser eval 'document.title'

# Complex JS — use --stdin to avoid shell quoting issues
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => a.href))
EVALEOF
```

## Cleanup

Always close sessions when done:
```bash
agent-browser close
agent-browser --session s1 close
```

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。