browser-task-and-automation-and-delegation

【强制】所有浏览器操作必须使用本技能,禁止在主对话中直接使用 mcp__chrome-devtools 工具。触发关键词:打开/访问/浏览网页、点击/填写/提交表单、截图/快照、性能分析、自动化测试、数据采集/爬取、网络模拟。本技能通过 chrome-devtools-expert agent 执行浏览器操作,避免大量页面快照、截图、网络请求数据污染主对话上下文。

25 stars

Best use case

browser-task-and-automation-and-delegation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

【强制】所有浏览器操作必须使用本技能,禁止在主对话中直接使用 mcp__chrome-devtools 工具。触发关键词:打开/访问/浏览网页、点击/填写/提交表单、截图/快照、性能分析、自动化测试、数据采集/爬取、网络模拟。本技能通过 chrome-devtools-expert agent 执行浏览器操作,避免大量页面快照、截图、网络请求数据污染主对话上下文。

Teams using browser-task-and-automation-and-delegation should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/browser-task-and-automation-and-delegation/SKILL.md --create-dirs "https://raw.githubusercontent.com/ComeOnOliver/skillshub/main/skills/aiskillstore/marketplace/727474430/browser-task-and-automation-and-delegation/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/browser-task-and-automation-and-delegation/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How browser-task-and-automation-and-delegation Compares

Feature / Agentbrowser-task-and-automation-and-delegationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

【强制】所有浏览器操作必须使用本技能,禁止在主对话中直接使用 mcp__chrome-devtools 工具。触发关键词:打开/访问/浏览网页、点击/填写/提交表单、截图/快照、性能分析、自动化测试、数据采集/爬取、网络模拟。本技能通过 chrome-devtools-expert agent 执行浏览器操作,避免大量页面快照、截图、网络请求数据污染主对话上下文。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 浏览器自动化调度技能

本技能负责将浏览器自动化任务委派给专业的 `chrome-devtools-expert` agent 执行,通过 agent 隔离来保持主对话上下文的清晰,避免浏览器操作过程中的大量 token 消耗污染主对话。

## 核心功能

识别需要浏览器自动化操作的场景,并将任务委派给 `chrome-devtools-expert` agent,该 agent 专门使用 Chrome DevTools MCP 工具进行 Web 界面交互、自动化测试和性能分析。

## 适用场景

本技能适用于以下场景:

1. **页面导航与浏览**
   - 打开指定 URL 的网页
   - 在页面间导航(前进、后退)
   - 管理多个浏览器标签页

2. **元素交互操作**
   - 点击按钮、链接等元素
   - 悬停在元素上触发效果
   - 拖拽元素到指定位置

3. **表单填写与提交**
   - 填写输入框、文本域
   - 选择下拉菜单选项
   - 提交表单并等待响应

4. **页面截图与快照**
   - 截取整个页面或特定元素
   - 获取页面的文本快照
   - 保存截图到文件

5. **性能分析与测试**
   - 启动性能跟踪
   - 分析页面加载性能
   - 获取核心 Web 指标(CWV)

6. **自动化测试**
   - 执行功能测试流程
   - 验证页面元素状态
   - 检查控制台错误

7. **数据采集**
   - 从网页提取信息
   - 执行 JavaScript 获取数据
   - 监控网络请求

8. **网络与设备模拟**
   - 模拟不同网络条件
   - 模拟 CPU 性能限制
   - 调整页面尺寸

## 调用规则

### 1. 委派方式

使用 Task tool 调用 `chrome-devtools-expert` agent:

```
Task tool 参数:
- subagent_type: "chrome-devtools-expert"
- description: 简短描述任务(3-5个字)
- prompt: 详细的操作需求和目标
```

## 场景示例

### 示例 1:打开页面并截图

**用户需求**: "打开 example.com 并截图"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "打开页面并截图"
- prompt: "打开 https://example.com,等待页面加载完成后截图,将截图保存到桌面"
```

### 示例 2:表单自动化

**用户需求**: "帮我填写这个登录表单并提交"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "填写登录表单"
- prompt: "在当前页面找到登录表单,填写用户名'test@example.com',密码'password123',然后点击登录按钮,等待响应并告诉我是否成功"
```

### 示例 3:性能分析

**用户需求**: "分析这个页面的加载性能"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "页面性能分析"
- prompt: "对 https://example.com 进行性能分析,启动性能跟踪,刷新页面,停止跟踪,提供核心 Web 指标和性能洞察"
```

### 示例 4:自动化测试

**用户需求**: "测试购物车添加商品的功能"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "测试购物车功能"
- prompt: "打开商城页面,找到商品列表中的第一个商品,点击'加入购物车'按钮,然后检查购物车图标的数量是否增加,验证功能是否正常"
```

### 示例 5:数据采集

**用户需求**: "从这个页面提取所有产品标题"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "提取产品标题"
- prompt: "从当前页面使用 JavaScript 提取所有产品标题,返回一个标题列表"
```

### 示例 6:网络条件测试

**用户需求**: "在慢速 3G 网络下测试页面加载"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "慢速网络测试"
- prompt: "设置网络模拟为 Slow 3G,打开 https://example.com,记录页面加载时间和用户体验,然后恢复正常网络"
```

### 示例 7:多步骤操作

**用户需求**: "打开网站,登录,然后导航到设置页面并截图"

**执行方式**:
```
调用 Task tool:
- subagent_type: "chrome-devtools-expert"
- description: "登录并截图设置页"
- prompt: "1) 打开 https://example.com
2) 填写登录表单(用户名:test@example.com,密码:password123)并提交
3) 等待登录成功
4) 点击导航栏的'设置'链接
5) 等待设置页面加载完成
6) 截取设置页面的完整截图并保存"
```

## 执行原则

1. **自动识别**: 当判断需要浏览器操作时,自动激活本技能
2. **快速委派**: 不在主对话中尝试浏览器操作,直接委派给专业 agent
3. **上下文隔离**: 将大量的浏览器输出数据隔离在 agent 上下文中
4. **结果精简**: agent 只返回关键操作结果,过滤冗余信息
5. **效率优先**: agent 会采用最优策略执行浏览器操作,最小化 token 消耗

通过本技能,主 agent 可以高效地将浏览器自动化任务委派给专业 agent,保持对话流程清晰,优化 token 使用。

Related Skills

processing-computer-vision-tasks

25
from ComeOnOliver/skillshub

Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.

luigi-task-generator

25
from ComeOnOliver/skillshub

Luigi Task Generator - Auto-activating skill for Data Pipelines. Triggers on: luigi task generator, luigi task generator Part of the Data Pipelines skill category.

google-sheets-automation

25
from ComeOnOliver/skillshub

Google Sheets Automation - Auto-activating skill for Business Automation. Triggers on: google sheets automation, google sheets automation Part of the Business Automation skill category.

ecs-task-definition-creator

25
from ComeOnOliver/skillshub

Ecs Task Definition Creator - Auto-activating skill for AWS Skills. Triggers on: ecs task definition creator, ecs task definition creator Part of the AWS Skills skill category.

cloud-tasks-queue-setup

25
from ComeOnOliver/skillshub

Cloud Tasks Queue Setup - Auto-activating skill for GCP Skills. Triggers on: cloud tasks queue setup, cloud tasks queue setup Part of the GCP Skills skill category.

conducting-browser-compatibility-tests

25
from ComeOnOliver/skillshub

This skill enables cross-browser compatibility testing for web applications using BrowserStack, Selenium Grid, or Playwright. It tests across Chrome, Firefox, Safari, and Edge, identifying browser-specific bugs and ensuring consistent functionality. It is used when a user requests to "test browser compatibility", "run cross-browser tests", or uses the `/browser-test` or `/bt` command to assess web application behavior across different browsers and devices. The skill generates a report detailing compatibility issues and screenshots for visual verification. Activates when you request "conducting browser compatibility tests" functionality.

asana-task-creator

25
from ComeOnOliver/skillshub

Asana Task Creator - Auto-activating skill for Enterprise Workflows. Triggers on: asana task creator, asana task creator Part of the Enterprise Workflows skill category.

001-jeremy-taskwarrior-integration

25
from ComeOnOliver/skillshub

Enforces complete Taskwarrior integration protocol for ALL coding tasks. Activates automatically when user mentions "taskwarrior", "task warrior", "tw", or discusses task management. Decomposes all coding work into properly tracked Taskwarrior tasks with full lifecycle: task add → task start → implementation → task done. Integrates with Timewarrior for automatic time tracking.

recipe-review-overdue-tasks

25
from ComeOnOliver/skillshub

Find Google Tasks that are past due and need attention.

recipe-create-task-list

25
from ComeOnOliver/skillshub

Set up a new Google Tasks list with initial tasks.

gws-workflow-email-to-task

25
from ComeOnOliver/skillshub

Google Workflow: Convert a Gmail message into a Google Tasks entry.

gws-tasks

25
from ComeOnOliver/skillshub

Google Tasks: Manage task lists and tasks.