#3030th of 324 in Skills, plugins and prompts
playwright-cli
Command-line browser control for coding agents, built on Playwright
- Stars
- 14.8k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
7,193 on 10 Apr 202614,846 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
playwright-cli exposes Playwright browser automation as shell commands (open, click, fill, snapshot, screenshot, route, tracing, video) that coding agents call instead of loading MCP tool schemas. Page snapshots are written to files with element refs, so page data stays out of the model context unless requested. It ships installable skills for Claude Code and GitHub Copilot, named sessions, and a dashboard to watch or take over running browsers.
Who it is for: Developers giving Claude Code or Copilot browser testing and automation
Strengths
- Snapshots saved to files with refs, plus find and depth limits, keep context small
- Covers cookies, storage, network mocking, tracing, video and device emulation
- Named sessions and a show dashboard let you monitor or take over agent browsers
- Can attach to an existing Chrome via CDP or the Playwright extension
Weaknesses
- No persistent page state for iterative reasoning; README points to Playwright MCP for that
- Requires Node.js 18 or newer and a global npm install
- Headless sessions shut down after an hour idle by default
- Skills install targets Claude Code and Copilot; other agents must read --help
What it needs
- no GPU
- Needs Node.js 18+
Quick answers
Is playwright-cli open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |