
Playwright Cli
This is a comprehensive CLI wrapper around Playwright that lets Claude drive browsers directly from bash commands. You get the full automation toolkit: clicking elements by reference IDs from snapshots, filling forms, managing tabs, mocking network requests, and even recording videos with annotated actions. The state management commands are especially practical for debugging auth flows, since you can save and restore cookies, localStorage, and full browser state. The snapshot system is clever, it generates YAML representations of the page after each action so Claude can see what changed and pick the right element references. If you're doing any browser testing or scraping work with Claude, the raw output mode makes it easy to pipe results into jq or other tools.
- GitHub stars
- 298
- last updated
- Jun 11, 2026
Install
$ npx -y skills add syahiidkamil/software-engineer-ai-agent-atlas --skill playwright-cli --agent claude-codeInstalls into .claude/skills of the current project.
Files
Browser Automation with playwright-cli
Quick start
# open new browser
playwright-cli open
# navigate to a page
playwright-cli goto https://playwright.dev
# interact with the page using refs from the snapshot
playwright-cli click e15
playwright-cli type "page.click"
playwright-cli press Enter
# take a screenshot (rarely used, as snapshot is more common)
playwright-cli screenshot
# close the browser
playwright-cli close
Commands
Core
Sponsors
Details
- Repository
- github.com/syahiidkamil/software-engineer-ai-agent-atlas
- Categories
- Testing & QA, AI & Agent Building, Automation & Workflows, CLI & Terminal
- First seen
- Jun 11, 2026