This handles browser automation through CDP, WebDriver, and modern frameworks like Playwright, with built-in security controls that actually matter. You get domain allowlists, credential protection, and audit logging baked in rather than bolted on later. The TDD workflow pushes you to write pytest-playwright tests first, which is the right way to do automation anyway. Performance patterns cover context reuse, parallel execution, and resource blocking to keep things fast. It's marked high-risk because you're touching web access and data extraction, so the security guardrails around blocking banking domains and password fields aren't optional. Good for scraping, testing, and automation where you need controls from day one.

skills.sh installs
232
GitHub stars
48
last updated
Aug 21, 2026

Install

$ npx -y skills add martinholovsky/claude-skills-generator --skill browser-automation --agent claude-code

Installs into .claude/skills of the current project.

Files

1. Overview

Risk Level: HIGH - Web access, credential handling, data extraction, network requests

You are an expert in browser automation with deep expertise in:

  • Chrome DevTools Protocol: Direct Chrome/Chromium control
  • WebDriver/Selenium: Cross-browser automation standard
  • Playwright/Puppeteer: Modern automation frameworks
  • Security Controls: Domain restrictions, credential protection

Core Principles

  1. TDD First - Write tests before implementation using pytest-playwright
  2. Performance Aware - Reuse contexts, parallelize, block unnecessary resources
  3. Security First - Domain allowlists, credential protection, audit logging
  4. Reliable Automation - Timeout enforcement, proper waits, error handling

Core Expertise Areas

  1. CDP Protocol: Network interception, DOM manipulation, JavaScript execution
  2. WebDriver API: Element interaction, navigation, waits
  3. Security: Domain allowlists, credential handling, audit logging
  4. Performance: Resource management, parallel execution

2. Implementation Workflow (TDD)

Step 1: Write Failing Test First

Sponsors

Details

Repository
github.com/martinholovsky/claude-skills-generator
Categories
Testing & QA, DevOps & CI/CD, Automation & Workflows
First seen
Jun 3, 2026

More from martinholovsky/claude-skills-generator

All 50
1guia-matthieu avatarbrand-strategyguia-matthieu/clawfu-skillsCreate distinctive brands that customers choose because they believe there's no substitute, using Marty Neumeier's Brand Gap and Zag frameworks Use when: **Buil228skills.sh installs
2leeguooooo avatarzentaoleeguooooo/zentao-mcpDEPRECATED — prefer the official zentao-cli (https://github.com/easysoft/zentao-cli) and its skills (https://github.com/easysoft/zentao-skills) for new setups. 217skills.sh installs
3pluginagentmarketplace avatarsolidity-developmentpluginagentmarketplace/custom-plugin-blockchainMaster Solidity smart contract development with patterns, testing, and best practices208skills.sh installs
4levnikolaevich avatarln-513-regression-checkerlevnikolaevich/claude-code-skillsRuns existing test suite to catch regressions after implementation changes. Use when Story needs regression verification. No status changes.206skills.sh installs
5yonatangross avatarimplementyonatangross/orchestkitFull-power feature implementation using parallel subagents for backend, frontend, testing, and security, with worktree isolation and quality verification in one206skills.sh installs
6feiskyer avatargithub-fix-issuefeiskyer/claude-code-settingsFix GitHub issues end-to-end — from analysis through branch creation, implementation, testing, and PR submission. Use this skill whenever the user mentions fixi202skills.sh installs