How do I install the Playwright CLI skill?

Run npx skillmds@latest add dynamods/playwright-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Playwright CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Playwright CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Playwright CLI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Playwright CLI?

dynamods (@dynamods) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Playwright CLI by dynamods — Agent Skill

Name: Playwright CLI
Author: dynamods

Playwright CLI

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

dynamods 40496da 2.4 KB Updated Sep 17, 2026

File contents

Browser Automation with playwright-cli

Used in DynamoHome for exploratory testing — navigating the live dev server, discovering data-testid gaps, and validating interactions before writing formal Playwright tests.

Typical DynamoHome workflow

# 1. Start the dev server first
npm run start

# 2. Open the app
playwright-cli open http://localhost:8080

# 3. Take a snapshot to see the current state and element refs
playwright-cli snapshot

# 4. Interact with elements using refs from the snapshot
playwright-cli click e5
playwright-cli snapshot

# 5. Close when done
playwright-cli close

Core commands

playwright-cli open http://localhost:8080   # open the app
playwright-cli goto http://localhost:8080   # navigate to a URL
playwright-cli snapshot                     # capture page state + element refs
playwright-cli click e3                     # click element by ref
playwright-cli hover e4                     # hover over element
playwright-cli press Enter                  # keyboard press
playwright-cli eval "document.title"        # run JS on the page
playwright-cli screenshot                   # take a screenshot
playwright-cli console                      # view console output
playwright-cli network                      # view network requests
playwright-cli close                        # close the browser

Snapshots

After each command, playwright-cli returns a snapshot of the current page with element refs (e.g. e5, e12). Use these refs to interact with specific elements. Snapshots are saved under .playwright-cli/ — this folder is git-ignored.

What to do with findings

Once you have identified the interactions and selectors needed:

Add any missing data-testid attributes to the source components (via the frontend-agent)
Create Page Object classes in tests/e2e/pages/ or tests/e2e/components/
Write formal test cases in the appropriate tests/e2e/*.spec.ts file

Do not leave raw playwright-cli findings as permanent tests — convert them into the POM structure defined in the end-to-end-testing skill.

---name: playwright-clidescription: Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.---# Browser Automation with playwright-cliUsed in DynamoHome for **exploratory testing** — navigating the live dev server, discovering `data-testid` gaps, and validating interactions before writing formal Playwright tests.## Typical DynamoHome workflow```bash# 1. Start the dev server firstnpm run start# 2. Open the appplaywright-cli open http://localhost:8080# 3. Take a snapshot to see the current state and element refsplaywright-cli snapshot# 4. Interact with elements using refs from the snapshotplaywright-cli click e5playwright-cli snapshot# 5. Close when doneplaywright-cli close```## Core commands```bashplaywright-cli open http://localhost:8080 # open the appplaywright-cli goto http://localhost:8080 # navigate to a URLplaywright-cli snapshot # capture page state + element refsplaywright-cli click e3 # click element by refplaywright-cli hover e4 # hover over elementplaywright-cli press Enter # keyboard pressplaywright-cli eval "document.title" # run JS on the pageplaywright-cli screenshot # take a screenshotplaywright-cli console # view console outputplaywright-cli network # view network requestsplaywright-cli close # close the browser```## SnapshotsAfter each command, playwright-cli returns a snapshot of the current page with element refs (e.g. `e5`, `e12`). Use these refs to interact with specific elements. Snapshots are saved under `.playwright-cli/` — this folder is git-ignored.## What to do with findingsOnce you have identified the interactions and selectors needed:1. Add any missing `data-testid` attributes to the source components (via the `frontend-agent`)2. Create Page Object classes in `tests/e2e/pages/` or `tests/e2e/components/`3. Write formal test cases in the appropriate `tests/e2e/*.spec.ts` fileDo not leave raw `playwright-cli` findings as permanent tests — convert them into the POM structure defined in the `end-to-end-testing` skill.

Frequently asked questions