playwright

Automate real browser interactions from the terminal using playwright-cli commands.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/JFeimster/moonshine-capital-portal --skill playwright-jfeimster
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: playwright
Source: https://github.com/JFeimster/moonshine-capital-portal/tree/main/skills/playwright
Command: npx skills add https://github.com/JFeimster/moonshine-capital-portal --skill playwright-jfeimster

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @playwright/cli, and includes scripts (resource) and references (resource) components.

What problem does it solve? Manually testing web pages, filling forms, and debugging UI flows in a browser is repetitive and hard to reproduce. This Skill lets you drive a real browser from the terminal with deterministic commands, capturing snapshots, screenshots, and traces along the way. ## Core Features & Use Cases - CLI-first browser automation: Open pages, snapshot the DOM to get stable element refs, then click, type, fill, and navigate using those refs via playwright-cli or the bundled wrapper script. - Artifact capture: Take screenshots, generate PDFs, record traces, and inspect console and network activity for debugging UI flows. - Session isolation: Run named sessions to keep separate automation contexts for different projects or flows. - Use Case: You need to verify a checkout flow on a staging site. Open the page headed, snapshot to get element refs, fill the form fields, submit, re-snapshot, and capture a screenshot and trace for the bug report. ## Quick Start Ask the assistant to open a website with the Playwright CLI, snapshot the page, and click or fill elements using the refs from the snapshot.

Frequently Asked Questions about playwright

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser actions from the command line with Playwright?▼

Use playwright-cli through the wrapper script: open a URL, run snapshot to get stable element refs, then issue commands like click, fill, type, and press against those refs. Re-snapshot after navigation or major DOM changes because refs can go stale.

How do I fill and submit a web form using playwright-cli?▼

Open the form page, run snapshot to list element refs, then use fill with each field's ref and value, and click the submit button's ref. Finish with another snapshot or a screenshot to confirm the submission result.

Do I need to install Playwright globally to use playwright-cli?▼

No. The bundled wrapper script runs the CLI via npx --package @playwright/cli, so only Node.js with npx is required. A global install of @playwright/cli is optional if you prefer a persistent setup.

Why do playwright-cli element refs stop working?▼

Element refs come from the most recent snapshot and go stale after navigation, modal changes, tab switches, or significant DOM updates. Run snapshot again to get fresh refs and retry the failed command.

Can I run multiple isolated browser sessions with playwright-cli?▼

Yes. Pass --session with a name on each command, or set the PLAYWRIGHT_CLI_SESSION environment variable once. Each named session maintains its own isolated browser context for separate projects or flows.

When should I use playwright-cli instead of Playwright test files?▼

Use playwright-cli for interactive, terminal-driven automation like exploratory debugging, one-off form fills, and data extraction. This Skill is CLI-first and only pivots to @playwright/test spec files when the user explicitly asks for tests.