patchright-skill

Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

242 stars

Best use case

patchright-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "patchright-skill" skill to help with this workflow task. Context: Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

Example output

A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

  • Use this skill when you want a reusable workflow rather than writing the same prompt again and again.

When not to use this skill

  • Do not use this when you only need a one-off answer and do not need a reusable workflow.
  • Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/patchright-skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/smallnest/patchright-skill/SKILL.md"

Manual Installation

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

How patchright-skill Compares

Feature / Agentpatchright-skillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

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

# Patchright - Browser Automation Skill

Patchright-based browser automation with bot detection bypass. Use for localhost, dev servers, web app testing, screenshots, and UI interactions.

## Triggers

**URL/Network:**
- localhost (http://localhost:*, http://127.0.0.1:*)
- Local IPs (192.168.x.x, 10.x.x.x, 172.16-31.x.x)
- Dev server ports (3000, 5173, 8080, 4200, 5000, etc.)

**Web App Testing:**
- "test the app", "check the site"
- "open localhost", "view in browser"
- "take screenshot", "capture screen"
- "check UI", "view page"
- QA, E2E testing, dev build verification

**Browser Interaction:**
- "click", "press button"
- "type", "fill form"
- "login", "sign up"
- "open menu", "click tab"
- "scroll", "navigate"

**Visual Verification:**
- "how does it look?", "is it working?"
- "check design", "verify layout"
- "responsive test", "screen size"
- "check rendering", "verify component"

**Development Workflow:**
- Verify changes after code edits
- Frontend debugging
- Real-time dev feedback
- Pre-deployment checks

## Core: Server Mode (Session Persistence!)

**Problem**: scripts/executor.py terminates process on each call -> browser session lost
**Solution**: scripts/server.py runs background server -> session persists

### Start Server (Required!)

```bash
cd ~/.claude/skills/patchright-skill
python scripts/server.py start &
```

### Server Commands

```bash
# Check status
python scripts/server.py status

# Stop server
python scripts/server.py stop

# Call tool
python scripts/server.py call '{"tool": "...", "args": {...}}'
```

## Usage

### 1. Navigate + Screenshot (Most Common Pattern)

```bash
cd ~/.claude/skills/patchright-skill

# Start server (if not running)
python scripts/server.py start &
sleep 2

# Navigate to page
python scripts/server.py call '{"tool": "navigate", "args": {"url": "http://localhost:3000"}}'

# Take screenshot
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "screenshot.png", "full_page": true}}'
```

### 2. Click + Interaction

```bash
# Click element
python scripts/server.py call '{"tool": "click", "args": {"selector": "button.submit"}}'
python scripts/server.py call '{"tool": "click", "args": {"selector": "#menu-btn"}}'
python scripts/server.py call '{"tool": "click", "args": {"selector": "body"}}'  # Click anywhere

# Type text
python scripts/server.py call '{"tool": "type", "args": {"selector": "#email", "text": "test@test.com"}}'
python scripts/server.py call '{"tool": "type", "args": {"selector": "input[name=password]", "text": "password123"}}'
```

### 3. Get Information

```bash
# Current URL
python scripts/server.py call '{"tool": "get_url"}'

# Page title
python scripts/server.py call '{"tool": "get_title"}'

# Element text
python scripts/server.py call '{"tool": "get_text", "args": {"selector": ".error-message"}}'
```

### 4. Wait

```bash
# Wait for element to appear
python scripts/server.py call '{"tool": "wait_for", "args": {"selector": ".loading-complete", "timeout": 10000}}'
```

## Tool Reference

| Tool | Description | Args |
|------|-------------|------|
| launch | Start browser | headless: bool (default: false) |
| close | Close browser | - |
| navigate | Go to URL | url: string (required) |
| screenshot | Save to file | path: string, full_page: bool |
| click | Click element | selector: string (required) |
| type | Type text | selector: string, text: string |
| get_text | Get element text | selector: string |
| wait_for | Wait for element | selector: string, timeout: int |
| get_url | Get current URL | - |
| get_title | Get page title | - |

## Examples

### Login Test

```bash
cd ~/.claude/skills/patchright-skill
python scripts/server.py start &
sleep 2

# Navigate to login page
python scripts/server.py call '{"tool": "navigate", "args": {"url": "http://localhost:3000/login"}}'
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "login_page.png"}}'

# Fill form
python scripts/server.py call '{"tool": "type", "args": {"selector": "#email", "text": "admin@test.com"}}'
python scripts/server.py call '{"tool": "type", "args": {"selector": "#password", "text": "admin123"}}'
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "login_filled.png"}}'

# Submit
python scripts/server.py call '{"tool": "click", "args": {"selector": "button[type=submit]"}}'
sleep 2
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "login_result.png"}}'
```

### App Navigation

```bash
# Enter app
python scripts/server.py call '{"tool": "navigate", "args": {"url": "http://localhost:3000"}}'
python scripts/server.py call '{"tool": "click", "args": {"selector": "body"}}'  # Click to enter
sleep 2
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "app_main.png", "full_page": true}}'

# Explore features
python scripts/server.py call '{"tool": "click", "args": {"selector": ".create-btn"}}'
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "after_action.png"}}'
```

## Selector Tips

```css
/* ID */
#submit-btn

/* Class */
.nav-menu
button.primary

/* Attribute */
input[type=email]
button[data-testid="login"]
a[href="/about"]

/* Text content */
text=Login
text=Submit

/* Combined */
form#login button[type=submit]
.sidebar .menu-item:first-child
```

## Technical Specs

- **Engine**: patchright (undetected playwright fork)
- **Browser**: Google Chrome (channel: 'chrome')
- **Bot Detection Bypass**: YES (Cloudflare, reCAPTCHA, etc.)
- **Localhost Support**: YES
- **Private IP Support**: YES
- **Server Port**: 9222

## Troubleshooting

**"Server not running" error:**
```bash
python scripts/server.py start &
sleep 2
```

**Browser not visible:**
- headless=False is default, browser window should appear
- In server mode, browser persists in background

**Session disconnected:**
- Use scripts/server.py instead of scripts/executor.py
- Server keeps session alive once started

**Element not found:**
- Use wait_for to wait first
- Verify selector in DevTools

Related Skills

azure-quotas

242
from aiskillstore/marketplace

Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".

DevOps & Infrastructure

raindrop-io

242
from aiskillstore/marketplace

Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.

Data & Research

zlibrary-to-notebooklm

242
from aiskillstore/marketplace

自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。

discover-skills

242
from aiskillstore/marketplace

当你发现当前可用的技能都不够合适(或用户明确要求你寻找技能)时使用。本技能会基于任务目标和约束,给出一份精简的候选技能清单,帮助你选出最适配当前任务的技能。

web-performance-seo

242
from aiskillstore/marketplace

Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.

project-to-obsidian

242
from aiskillstore/marketplace

将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则(默认到 00_Inbox/AI/、追加式、统一 Schema) 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】: - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建(先到 00_Inbox/AI/) - 禁止自作主张决定输出位置

obsidian-helper

242
from aiskillstore/marketplace

Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩(00_Inbox/AI/、追加式、白名单字段) 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤,不要自作主张 【禁止行为】: - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记(除非用户明确指定)

internationalizing-websites

242
from aiskillstore/marketplace

Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.

google-official-seo-guide

242
from aiskillstore/marketplace

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

github-release-assistant

242
from aiskillstore/marketplace

Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.

doc-sync-tool

242
from aiskillstore/marketplace

自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件,保持内容一致性。支持自动监听和手动触发。

deploying-to-production

242
from aiskillstore/marketplace

Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.