playwright-cli
/playwright-cli
Browser automation via Playwright CLI — UI testing, form filling, screenshots, scraping. Token-efficient alternative to MCP. Use when user asks to test UI, automate browser, take screenshots, fill forms, or scrape web pages.
- Author
- keiseilab ↗
- Repository
- keiseikit ↗
- Licence
- Apache-2.0
- Last repository change
- 19.07.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 19.07.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Browser automation via Playwright CLI — UI testing, form filling, screenshots, scraping. Token-efficient alternative to MCP. Use when user asks to test UI, automate browser, take screenshots, fill forms, or scrape web pages.
Original author description
Browser automation via Playwright CLI — UI testing, form filling, screenshots, scraping. Token-efficient alternative to MCP. Use when user asks to test UI, automate browser, take screenshots, fill forms, or scrape web pages.
How it works
- When to use
- Overview
- Key Workflow Pattern
- Essential Commands
- Parallel UI Testing Pattern
- Tips
SKILL.md preview
--- name: playwright-cli description: Browser automation via Playwright CLI — UI testing, form filling, screenshots, scraping. Token-efficient alternative to MCP. Use when user asks to test UI, automate browser, take screenshots, fill forms, or scrape web pages. --- # Browser Automation with playwright-cli ## When to use - Automating browser tasks: UI testing, form filling, taking screenshots, or scraping web pages. - Token-efficient alternative to the Playwright MCP — saves ~90K tokens per task by passing only an accessibility-tree summary. - Any task asking to "test UI", "automate browser", "take a screenshot", "fill a form", or "scrape a page". ## Overview `playwright-cli` is a token-efficient CLI tool for browser automation. It saves the accessibility tree to disk and only passes a summary to the agent — ~90K tokens cheaper than MCP per task. **Run via:** `npx @playwright/cli <command>` (installed globally would be just `playwright-cli <command>`) ## Key Workflow Pattern ``` 1. npx @playwright/cli open [url] — launch browser (headless by default) 2. npx @playwright/cli snapshot — get accessibility tree, identify element refs 3. npx @playwright/cli click <ref> — interact using refs from snapshot 4. npx @playwright/cli screenshot — capture result 5. npx @playwright/cli close — cleanup ``` **For headed (visible) browser:** `npx @playwright/cli open --headed [url]` ## Essential Commands ### Opening & Navigation - `open [url]` — launch browser (add `--headed` to see it) - `goto <url>` — navigate to URL - `go-back` / `go-forward` — browser history - `close` — close browser session ### Page Interaction (use refs from `snapshot`) - `click <ref>` — click element - `dblclick <ref>` — double click - `fill <ref> <text>` — fill input field - `type <text>` — type text into focused element - `select <ref> <value>` — select dropdown option - `check <ref>` / `uncheck <ref>` — checkboxes - `hover <ref>` — hover over element - `drag <startRef> <endRef>` — drag and drop - `upload <file>` — file upload ### Inspection - `snapshot` — capture page accessibility tree, get element refs - `screenshot` — take screenshot (saved to disk) - `pdf` — export page as PDF ### Keyboard & Mouse - `press <key>` — press key (Enter, Tab, etc.) - `keydown <key>` / `keyup <key>` — key press/release - `mousemove <x> <y>` / `mousedown` / `mouseup` / `mousewheel` ### Storage & Cookies - `cookie-list` / `cookie-get <name>` / `cookie-set` / `cookie-delete` - `localstorage-list` / `localstorage-get` / `localstorage-set` / `localstorage-delete` - `sessionstorage-list` / `sessionstorage-get` / `sessionstorage-set` ### Network - `route <pattern>` — mock network requests - `route-list` — list active mocks - `unroute [pattern]` — remove mocks - `network` — list all network requests ### DevTools & Recording - `console [min-level]` — list console messages - `eval <func> [ref]` — evaluate JS on page or element - `run-code <code>` — run Playwright code snippet - `tracing-start` / `tracing-stop` — trace recording - `video-start` / `video-stop` — video recording ### Session Management - `list` — list browser sessions - `close-all` — close all sessions - `kill-all` — force kill stale sessions - Use `-s=<session>` flag to work with named sessions (parallel testing) ### Browser Options - Chrome (default), Firefox, WebKit, Edge - `--browser=firefox` to use different browser - Persistent profiles supported ## Parallel UI Testing Pattern For parallel sub-agent testing (recommended for form/UI validation): ``` Prompt to Claude Code: "Use playwright-cli to test [feature]. Run 3 parallel sub-agents: 1. Happy path — valid inputs, expected flow 2. Edge cases — empty fields, special characters, very long input 3. Validation — invalid email, missing required fields, XSS attempts Use headed browsers so I can see. Take screenshots of results." ``` Each sub-agent gets its own session via `-s=<name>` flag. ## Tips - **Default is headless** — add `--headed` to `open` command to see the browser - **Always `snapshot` first** — to get element refs before interacting - **Sessions for parallelism** — use `-s=agent1`, `-s=agent2` etc. for parallel agents - **Screenshots for evidence** — always take screenshots of test results - **Close sessions** — always `close` or `close-all` when done - **Token efficiency** — CLI saves accessibility tree to disk, only passes summary to agent
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · keiseilab/keiseikit | 100 | Apache-2.0 |
| atc-net/atc-agentic-toolkit | 100 | MIT |
| thefrederiksen/devthrottle | 100 | MIT |
| zebbern/claude-code-guide | 100 | MIT |
| sanity-io/sanity | 100 | MIT |
| fugazi/test-automation-skills-agents | 100 | MIT |
| laurigates/claude-plugins | 100 | MIT |
| ulises-jeremias/agent-toolkit | 100 | MIT |
| testdino-hq/playwright-skill | 100 | MIT |
Database snapshot: 13.11.2026 · package version 244b2add3edc (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click… - 100ac-qa-playwright-cli
Browser automation via playwright-cli. Token-efficient alternative to Playwright MCP - uses CLI commands through Bash instead of MCP tool schemas. Supports navigation, interaction, screenshots, video recording, and session management. Triggers on keywords: browser, e2e,… - 100playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli`. - 100playwright-automation
Browser automation via Playwright for web testing, screenshots, form filling, scraping, and verification. Use when tasks require navigating websites, interacting with web pages, or testing web applications. - 100playwright-testing
UI/E2E test automation with Playwright MCP. Use when the user asks to "test the UI", "automate browser tests", "check the page", "take a screenshot", "run Playwright", "write E2E tests", or anything about browser-based testing. - 100playwright
Provides Playwright-based browser automation and E2E testing. Supports screenshots, web scraping, and form automation. Use for "브라우저", "스크린샷", "E2E 테스트", "웹 스크래핑" requests.