跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 adspower-antidetect-browser

Adspower Antidetect Browser

管理 AdsPower 反检测浏览器配置用于多账户营销自动化和运动

819 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

管理 AdsPower 反检测浏览器配置用于多账户营销自动化和运动

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:AdsPower Antidetect Browser Skill、Overview、Installation、API Access、Base Configuration、AdsPower local API endpoint。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。 正文约 509 行,超过规范建议的 500 行,激活时仍会整份载入。

官方 description(原文)

Manage AdsPower antidetect browser profiles for multi-account marketing automation and campaigns

AdsPower Antidetect Browser SkillOverviewInstallationAPI AccessBase ConfigurationAdsPower local API endpointOptional: If using cloud APICore OperationsCreate Browser ProfileUsageLaunch Browser ProfileUsage

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
adspower-antidetect-browser
description
Manage AdsPower antidetect browser profiles for multi-account marketing automation and campaigns
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「adspower-antidetect-browser」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-c810ccc9715984df-Adspower-Antidect-%E6%B5%8F%E8%A7%88%E5%99%A8.html
请存为 .cursor/skills/adspower-antidetect-browser/SKILL.md 或 .claude/skills/adspower-antidetect-browser/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/reason-machines/marketing-skills' --list

npx skills add 'https://github.com/reason-machines/marketing-skills' --skill 'adspower-antidetect-browser'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: adspower-antidetect-browser description: Manage AdsPower antidetect browser profiles for multi-account marketing automation and campaigns triggers:

  • "create adspower browser profile"
  • "manage multiple browser profiles for marketing"
  • "set up antidetect browser automation"
  • "configure adspower profiles for campaigns"
  • "automate multi-account browser sessions"
  • "use adspower api for browser control"
  • "launch adspower profiles programmatically"
  • "manage browser fingerprints for marketing"

AdsPower Antidetect Browser Skill

Skill by ara.so — Marketing Skills collection.

Overview

AdsPower is an antidetect browser platform that allows marketing teams to manage multiple browser profiles with unique fingerprints for multi-account operations, ad campaigns, and automation workflows. Each profile has isolated cookies, storage, and unique browser fingerprints to prevent account association and detection.

Installation

AdsPower requires the desktop application installed on your system:

  1. Download AdsPower from the official website
  2. Install the application for your operating system (Windows/macOS)
  3. Launch AdsPower and create an account
  4. Enable API access in Settings → API Settings

API Access

AdsPower provides a local HTTP API (default port: 50325) for programmatic control.

Base Configuration

import requests
import os

# AdsPower local API endpoint
ADSPOWER_API_BASE = "http://localhost:50325/api/v1"

# Optional: If using cloud API
ADSPOWER_API_KEY = os.getenv("ADSPOWER_API_KEY")
const axios = require('axios');

const ADSPOWER_API_BASE = 'http://localhost:50325/api/v1';
const API_KEY = process.env.ADSPOWER_API_KEY;

Core Operations

Create Browser Profile

def create_profile(name, group_id=None, fingerprint_config=None):
    """Create a new browser profile"""
    url = f"{ADSPOWER_API_BASE}/user/create"
    
    payload = {
        "name": name,
        "group_id": group_id or "0",
        "domain_name": "",
        "open_urls": [],
        "repeat_config": fingerprint_config or []
    }
    
    response = requests.post(url, json=payload)
    data = response.json()
    
    if data.get("code") == 0:
        return data["data"]["id"]
    else:
        raise Exception(f"Failed to create profile: {data.get('msg')}")

# Usage
profile_id = create_profile(
    name="Campaign_Profile_1",
    group_id="marketing_team"
)
print(f"Created profile: {profile_id}")
async function createProfile(name, groupId = '0') {
  const response = await axios.post(`${ADSPOWER_API_BASE}/user/create`, {
    name: name,
    group_id: groupId,
    domain_name: '',
    open_urls: []
  });
  
  if (response.data.code === 0) {
    return response.data.data.id;
  }
  throw new Error(`Failed to create profile: ${response.data.msg}`);
}

// Usage
const profileId = await createProfile('Campaign_Profile_1', 'marketing_team');
console.log(`Created profile: ${profileId}`);

Launch Browser Profile

def start_profile(profile_id, launch_args=None):
    """Launch a browser profile and return connection details"""
    url = f"{ADSPOWER_API_BASE}/browser/start"
    
    params = {
        "user_id": profile_id,
        "launch_args": launch_args or []
    }
    
    response = requests.get(url, params=params)
    data = response.json()
    
    if data.get("code") == 0:
        return {
            "ws_endpoint": data["data"]["ws"]["puppeteer"],
            "selenium_endpoint": data["data"]["ws"]["selenium"],
            "debug_port": data["data"]["debug_port"]
        }
    else:
        raise Exception(f"Failed to start profile: {data.get('msg')}")

# Usage
connection = start_profile(profile_id)
print(f"WebSocket: {connection['ws_endpoint']}")
async function startProfile(profileId) {
  const response = await axios.get(`${ADSPOWER_API_BASE}/browser/start`, {
    params: { user_id: profileId }
  });
  
  if (response.data.code === 0) {
    return {
      wsEndpoint: response.data.data.ws.puppeteer,
      seleniumEndpoint: response.data.data.ws.selenium,
      debugPort: response.data.data.debug_port
    };
  }
  throw new Error(`Failed to start profile: ${response.data.msg}`);
}

Close Browser Profile

def stop_profile(profile_id):
    """Close a running browser profile"""
    url = f"{ADSPOWER_API_BASE}/browser/stop"
    
    params = {"user_id": profile_id}
    response = requests.get(url, params=params)
    data = response.json()
    
    return data.get("code") == 0

# Usage
stop_profile(profile_id)

Automation Integration

With Selenium

from selenium import webdriver
from selenium.webdriver.chrome.options import Options

def connect_selenium(profile_id):
    """Connect Selenium to AdsPower profile"""
    connection = start_profile(profile_id)
    
    chrome_options = Options()
    chrome_options.add_experimental_option(
        "debuggerAddress", 
        f"127.0.0.1:{connection['debug_port']}"
    )
    
    driver = webdriver.Chrome(options=chrome_options)
    return driver

# Usage
driver = connect_selenium(profile_id)
driver.get("https://example.com")
# Perform automation tasks
driver.quit()
stop_profile(profile_id)

With Puppeteer

const puppeteer = require('puppeteer-core');

async function connectPuppeteer(profileId) {
  const connection = await startProfile(profileId);
  
  const browser = await puppeteer.connect({
    browserWSEndpoint: connection.wsEndpoint,
    defaultViewport: null
  });
  
  return browser;
}

// Usage
(async () => {
  const browser = await connectPuppeteer(profileId);
  const page = await browser.newPage();
  await page.goto('https://example.com');
  // Perform automation tasks
  await browser.disconnect();
  await stopProfile(profileId);
})();

With Playwright

from playwright.sync_api import sync_playwright

def connect_playwright(profile_id):
    """Connect Playwright to AdsPower profile"""
    connection = start_profile(profile_id)
    
    with sync_playwright() as p:
        browser = p.chromium.connect_over_cdp(connection['ws_endpoint'])
        return browser

# Usage
browser = connect_playwright(profile_id)
page = browser.new_page()
page.goto("https://example.com")
# Perform automation tasks
browser.close()
stop_profile(profile_id)

Profile Management

List All Profiles

def list_profiles(group_id=None, page=1, page_size=100):
    """Get all browser profiles"""
    url = f"{ADSPOWER_API_BASE}/user/list"
    
    params = {
        "page": page,
        "page_size": page_size
    }
    if group_id:
        params["group_id"] = group_id
    
    response = requests.get(url, params=params)
    data = response.json()
    
    if data.get("code") == 0:
        return data["data"]["list"]
    return []

# Usage
profiles = list_profiles(group_id="marketing_team")
for profile in profiles:
    print(f"{profile['user_id']}: {profile['name']}")

Update Profile Configuration

def update_profile(profile_id, updates):
    """Update profile settings"""
    url = f"{ADSPOWER_API_BASE}/user/update"
    
    payload = {
        "user_id": profile_id,
        **updates
    }
    
    response = requests.post(url, json=payload)
    data = response.json()
    
    return data.get("code") == 0

# Usage
update_profile(profile_id, {
    "name": "Updated_Campaign_Profile",
    "remark": "Main account for Facebook ads"
})

Delete Profile

def delete_profile(profile_id):
    """Delete a browser profile"""
    url = f"{ADSPOWER_API_BASE}/user/delete"
    
    params = {"user_ids": [profile_id]}
    response = requests.post(url, json=params)
    data = response.json()
    
    return data.get("code") == 0

Common Patterns

Campaign Profile Automation

import time

class CampaignAutomation:
    def __init__(self, profile_ids):
        self.profile_ids = profile_ids
    
    def run_campaign_tasks(self, task_function):
        """Execute tasks across multiple profiles"""
        for profile_id in self.profile_ids:
            try:
                print(f"Starting profile {profile_id}")
                driver = connect_selenium(profile_id)
                
                # Execute custom task
                task_function(driver)
                
                driver.quit()
                stop_profile(profile_id)
                
                # Delay between profiles
                time.sleep(5)
                
            except Exception as e:
                print(f"Error with profile {profile_id}: {e}")
                stop_profile(profile_id)

# Usage
def post_ad_campaign(driver):
    driver.get("https://ads.platform.com")
    # Perform ad posting logic
    pass

automation = CampaignAutomation([profile_id, profile_id_2])
automation.run_campaign_tasks(post_ad_campaign)

Profile Pool Manager

class ProfilePool:
    def __init__(self, group_name):
        self.group_name = group_name
        self.active_profiles = {}
    
    def get_available_profile(self):
        """Get next available profile from pool"""
        profiles = list_profiles(group_id=self.group_name)
        
        for profile in profiles:
            profile_id = profile['user_id']
            if profile_id not in self.active_profiles:
                connection = start_profile(profile_id)
                self.active_profiles[profile_id] = connection
                return profile_id, connection
        
        raise Exception("No available profiles in pool")
    
    def release_profile(self, profile_id):
        """Release profile back to pool"""
        if profile_id in self.active_profiles:
            stop_profile(profile_id)
            del self.active_profiles[profile_id]

# Usage
pool = ProfilePool("marketing_team")
profile_id, connection = pool.get_available_profile()
# Use profile
pool.release_profile(profile_id)

Batch Profile Creation

def create_campaign_profiles(campaign_name, count=10):
    """Create multiple profiles for a campaign"""
    profile_ids = []
    
    for i in range(count):
        profile_name = f"{campaign_name}_Profile_{i+1}"
        profile_id = create_profile(
            name=profile_name,
            group_id=campaign_name
        )
        profile_ids.append(profile_id)
        print(f"Created: {profile_name} ({profile_id})")
    
    return profile_ids

# Usage
campaign_profiles = create_campaign_profiles("BlackFriday2026", count=5)

Fingerprint Configuration

Custom Fingerprint Settings

def create_profile_with_fingerprint(name, config):
    """Create profile with specific fingerprint configuration"""
    url = f"{ADSPOWER_API_BASE}/user/create"
    
    payload = {
        "name": name,
        "group_id": "0",
        "fingerprint_config": {
            "ua": config.get("user_agent"),
            "language": config.get("language", "en-US"),
            "timezone": config.get("timezone", "America/New_York"),
            "webrtc": config.get("webrtc", "proxy"),
            "location": config.get("location", "ask"),
            "canvas": config.get("canvas", "noise"),
        }
    }
    
    response = requests.post(url, json=payload)
    data = response.json()
    
    if data.get("code") == 0:
        return data["data"]["id"]
    raise Exception(f"Failed to create profile: {data.get('msg')}")

# Usage
fingerprint_config = {
    "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)...",
    "language": "en-US,en;q=0.9",
    "timezone": "America/Los_Angeles",
    "webrtc": "proxy"
}

profile_id = create_profile_with_fingerprint(
    "Custom_Fingerprint_Profile",
    fingerprint_config
)

Troubleshooting

Connection Issues

def check_api_status():
    """Verify AdsPower API is accessible"""
    try:
        response = requests.get(f"{ADSPOWER_API_BASE}/status", timeout=5)
        return response.status_code == 200
    except requests.exceptions.RequestException:
        return False

if not check_api_status():
    print("AdsPower API not accessible. Ensure the application is running.")

Profile Not Starting

def safe_start_profile(profile_id, max_retries=3):
    """Start profile with retry logic"""
    for attempt in range(max_retries):
        try:
            connection = start_profile(profile_id)
            return connection
        except Exception as e:
            print(f"Attempt {attempt + 1} failed: {e}")
            time.sleep(2)
    
    raise Exception(f"Failed to start profile after {max_retries} attempts")

Clean Up Stuck Profiles

def force_close_all_profiles():
    """Close all running browser profiles"""
    profiles = list_profiles()
    for profile in profiles:
        profile_id = profile['user_id']
        try:
            stop_profile(profile_id)
            print(f"Closed profile: {profile_id}")
        except Exception as e:
            print(f"Error closing {profile_id}: {e}")

Environment Variables

# Optional: For cloud API access
export ADSPOWER_API_KEY="your_api_key_here"

# Custom API port if not using default
export ADSPOWER_API_PORT="50325"

Best Practices

  1. Always close profiles after use to free resources
  2. Add delays between profile launches to avoid detection
  3. Use profile groups to organize campaigns and teams
  4. Monitor active profiles to prevent resource exhaustion
  5. Implement error handling for network and API failures
  6. Rotate profiles regularly for long-running campaigns
  7. Back up important profiles and fingerprint configurations

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…