browser-automation-expert
Expert guide for autonomous web agents (Browser-Use, Stagehand v0.4+), hardcore anti-bot evasion (Playwright Stealth, WebGL masking), and Vision LLM visual QA / Panduan ahli agen web otonom, penghindaran deteksi bot, dan QA visual berbasis Vision LLM.
roedyrustam · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add roedyrustam/vibes-plug --skill browser-automation-expert技能说明
name: browser-automation-expert description: "Expert guide for autonomous web agents (Browser-Use, Stagehand v0.4+), hardcore anti-bot evasion (Playwright Stealth, WebGL masking), and Vision LLM visual QA / Panduan ahli agen web otonom, penghindaran deteksi bot, dan QA visual berbasis Vision LLM." author: "Roedy Rustam"
version: "4.2.1"
Autonomous Web Agent & Automation Expert (2026 Edition)
English
Purpose & Overview
Deploy ultra-powerful autonomous web agents that perceive, navigate, and execute complex workflows without human intervention. Combine modern agentic web automation frameworks (Browser-Use, Stagehand v0.4+) with hardcore anti-detection evasion techniques (Playwright Stealth, fingerprint spoofing, residential proxy rotation) and frontier Vision LLMs (Gemini 4 Pro / Flash, Project Astra, Claude 5.1 Fable / 5.0 Computer Use, OpenAI GPT-5.6 / o3 / GPT-4.5) for pixel-accurate visual QA.
Core Capabilities
-
Autonomous Execution Frameworks (2026 Standard)
- Stagehand v0.4+: Natural language DOM perception with semantic actions (
page.act(),page.extract(),page.observe()). Avoid fragile CSS/XPath selectors. - Browser-Use: Autonomous multi-turn web browsing driven by LLMs with accessibility-tree parsing, visual bounding boxes, and goal-oriented execution loops.
- Stagehand v0.4+: Natural language DOM perception with semantic actions (
-
Hardcore Evasion & Anti-Bot Bypassing
- Playwright Stealth: Mask
navigator.webdriver, automate runtime evasion plugins, and neutralize detection scripts (Datadome, Cloudflare Turnstile, Kasada). - Fingerprint Masking: Spoof Canvas, WebGL, AudioContext, hardware concurrency, and WebRTC leak vectors.
- Human Behavior Mimicry: Inject natural Bezier-curve mouse movements, randomized typing cadences, and realistic scroll viewport dynamics.
- Playwright Stealth: Mask
-
Visual QA & Layout Diffing via Vision LLMs
- Feed high-resolution viewport screenshots into Gemini 3.8 Flash or Claude 3.7 Sonnet.
- Perform automatic visual regression audits, layout drift detection, contrast validation, and modal overlay checks.
Production Implementation Recipes
Recipe 1: Stagehand v0.4+ with Playwright Stealth (TypeScript)
import { Stagehand } from '@browserbase/stagehand';
import { z } from 'zod';
export async function runAutonomousShoppingAgent(targetProduct: string) {
const stagehand = new Stagehand({
env: 'LOCAL',
modelName: 'claude-3-7-sonnet-20250219',
browserbaseSessionCreateParams: {
projectId: process.env.BROWSERBASE_PROJECT_ID,
},
});
await stagehand.init();
const page = stagehand.page;
try {
await page.goto('https://example-store.com');
// Semantic action without hardcoded selectors
await page.act({ action: `Search for "${targetProduct}" in the search input and press Enter` });
// Extract structured data validated by Zod schema
const productData = await page.extract({
instruction: 'Extract the top 3 product names, prices, and availability status',
schema: z.object({
products: z.array(
z.object({
title: z.string(),
price: z.string(),
inStock: z.boolean(),
})
),
}),
});
console.log('Extracted Products:', productData.products);
return productData.products;
} finally {
await stagehand.close();
}
}
Recipe 2: Browser-Use with Anti-Bot Evasion (Python)
import asyncio
from browser_use import Agent
from langchain_google_genai import ChatGoogleGenerativeAI
from playwright.async_api import async_playwright
async def run_autonomous_browser_agent(goal: str):
llm = ChatGoogleGenerativeAI(
model="gemini-3.8-flash",
temperature=0.1
)
# Initialize agent with human-like viewport and natural interactions
agent = Agent(
task=goal,
llm=llm,
use_vision=True,
max_actions_per_step=3
)
result = await agent.run(max_steps=25)
print(f"Goal Completed: {result.is_done()}")
return result.final_result()
if __name__ == "__main__":
asyncio.run(run_autonomous_browser_agent("Search flights from CGK to HND for next month and return cheapest option"))
Execution Protocol & Guardrails
- Pre-flight: Always inject evasion headers and randomize screen dimensions before navigating.
- Fail-safe: Set maximum navigation step thresholds (
max_steps <= 30) to prevent infinite looping. - Visual Validation: Capture viewport screenshots at critical check-in steps and pass to Vision LLMs to verify state transitions.
Visual Regression & Vision QA
Description
This skill transforms the agent from a blind code generator into a visual designer. Instead of hoping the CSS looks correct, the agent is instructed to write a script that takes a screenshot of the newly created component, analyzes the screenshot using its own Vision AI capabilities, and iteratively tweaks the CSS until it matches the design intent perfectly.
Trigger Conditions
Activate this skill when the user says:
- "Fix the CSS, the button is misaligned."
- "Make it look exactly like this mockup."
- "Ensure the UI is responsive on mobile screens."
The Visual QA Loop
- Code: The agent writes the HTML/CSS/React component.
- Serve: The agent starts a local dev server in the background.
- Capture: The agent runs a quick Playwright/Puppeteer script to take screenshots at various viewports (Mobile, Tablet, Desktop).
- Analyze: The agent receives the screenshot (via the
view_filetool on the image) and analyzes the visual hierarchy, contrast, and alignment. - Correct: The agent fixes margin, padding, or flexbox issues based on what it saw, not