Claude Code plugin marketplace for stealth browser automation and WAF bypass skills
npx claudepluginhub esonhugh/pydoll-cf-waf-bypasser-skillsStealth browser automation skill using Pydoll, specialized in bypassing Cloudflare WAF, Turnstile CAPTCHA, and other bot detection systems.
RuFlo Marketplace: Claude Code native agents, swarms, workers, and MCP tools for continuous software engineering
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 79 focused plugins, 184 specialized agents, and 150 skills - optimized for granular installation and minimal token usage
Share bugs, ideas, or general feedback.
Claude Code Plugin for Stealth Browser Automation & WAF Bypass
Installation · Capabilities · Usage · Structure · 中文说明
A Claude Code Plugin that teaches Claude how to write stealth browser automation scripts using Pydoll — an async-native, zero-WebDriver Chromium automation library specialized in bypassing WAF protections and bot detection systems.
When you ask Claude Code to bypass Cloudflare, scrape a protected website, or automate a browser with anti-detection, this skill activates automatically.
This repository is a self-contained plugin marketplace. Add it and install:
# Step 1: Register the marketplace
/plugin marketplace add esonhugh/pydoll-cf-waf-bypasser-skills
# Step 2: Install the plugin
/plugin install pydoll-antibot-bypasser@pydoll-cf-waf-bypasser-skills
/plugin install github:Esonhugh/pydoll-cf-waf-bypasser-skills
git clone https://github.com/Esonhugh/pydoll-cf-waf-bypasser-skills.git
# Project-level (current project only)
cp -r pydoll-cf-waf-bypasser-skills/plugins/pydoll-antibot-bypasser/skills/pydoll-antibot-bypasser \
your-project/.claude/skills/
# Or global (all projects)
cp -r pydoll-cf-waf-bypasser-skills/plugins/pydoll-antibot-bypasser/skills/pydoll-antibot-bypasser \
~/.claude/skills/
Add to your project's .claude/settings.json so team members are auto-prompted to install:
{
"extraKnownMarketplaces": {
"pydoll-cf-waf-bypasser-skills": {
"source": {
"source": "github",
"repo": "Esonhugh/pydoll-cf-waf-bypasser-skills"
}
}
},
"enabledPlugins": {
"pydoll-antibot-bypasser@pydoll-cf-waf-bypasser-skills": true
}
}
| Capability | Description |
|---|---|
| Cloudflare Turnstile | Auto-detect and solve Turnstile CAPTCHA, works in headless mode |
| Cloudflare Managed Challenge | Bypass with headless=False + xvfb on servers |
| Cloudflare JS Challenge | Auto-execute JavaScript challenges |
| Human-like Interaction | Bezier curve mouse movement, typo simulation, random delays |
| Shadow DOM Access | Penetrate closed shadow roots for hidden elements |
| Browser Fingerprint Spoofing | Fake engagement time, WebRTC leak protection, language spoofing |
| Concurrent Scraping | Async-native, multi-tab parallel execution |
| Request Interception | Block images/CSS/fonts to accelerate page loading |
| WAF Provider | Status | Notes |
|---|---|---|
| Cloudflare Turnstile | ✅ Full | Works in headless mode |
| Cloudflare JS Challenge | ✅ Full | Auto JS execution |
| Cloudflare Managed Challenge | ✅ Verified | Requires headless=False + xvfb |
| DataDome | ⚠️ Partial | Needs high-quality proxy |
| PerimeterX | ⚠️ Partial | Needs randomized behavior |
| Akamai Bot Manager | ⚠️ Partial | TLS fingerprint sensitive |
Once installed, just ask Claude Code in natural language:
> Bypass Cloudflare on https://example.com and get the page title
> Scrape data from a protected website with anti-detection
> Write a stealth scraper with human-like behavior
Claude generates ready-to-run scripts using uv inline script metadata:
uv run script.py # Auto-installs dependencies and runs
# Zero WebDriver — navigator.webdriver is undefined, not false
async with Chrome(options=options) as browser:
tab = await browser.start()
# One-line Cloudflare bypass
async with tab.expect_and_bypass_cloudflare_captcha():
await tab.go_to('https://protected-site.com')
# Human-like typing with typo simulation
await input_el.type_text('Hello', humanize=True)
# Human-like mouse movement via Bezier curves
await tab.mouse.click(500, 300, humanize=True)
8 templates included in scripts/templates.py: