Claude Code plugins for browser automation, Playwright E2E testing, and developer tooling
Semantic browser interface for LLM agents — token-efficient page snapshots via Puppeteer/CDP, with a skill for live page interaction
Skills for building Playwright E2E tests — analyze codebase, plan coverage, generate test cases, write test code, review, and fix flaky tests
Site-specific automation patterns and knowledge for popular websites (Airbnb, Amazon, Apple Store)
WebBench benchmark runner — executes real-world browser tasks from the Halluminate/WebBench dataset, scores via LLM-as-judge, and produces evaluation reports