agentsclimarketplace

Playwright cli

Skill appautomaton/webmaton/skills/playwright-cli

Portable web-research and browser-automation SKILLs for Claude Code, Codex, and OpenCode — Playwright, Chrome DevTools, nodriver, and HTML-to-Markdown.

Install
npx -y skills add appautomaton/webmaton --skill playwright-cli

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 18 stars18 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when a task needs Playwright-backed browser automation from the shell: open or attach to browser sessions, inspect snapshots and element refs, click/type/fill forms, debug Playwright tests, inspect console/network/storage, run Playwright snippets, capture screenshots/traces/videos, or generate reliable test code. Prefer for repeatable browser workflows and Playwright test work; not for static HTTP fetches, JSON APIs, or simple web search.

SKILL.md

3.5 KB, as published. Nobody here has run it

playwright-cli

playwright-cli is a token-efficient shell interface to Playwright. It keeps browser state across commands, exposes page snapshots with stable element refs such as e15, and prints the Playwright code it ran so the interaction can be converted into tests.

Core Workflow

playwright-cli open https://example.com
playwright-cli snapshot
playwright-cli click e15
playwright-cli fill e5 "[email protected]"
playwright-cli press Enter
playwright-cli close

Use refs from the latest snapshot by default. Re-run snapshot after navigation, major DOM changes, or a failed ref action. Use CSS selectors or Playwright locators only when refs are unavailable or unstable.

Operating Rules

  • Discover exact syntax with playwright-cli --help and playwright-cli <command> --help; the CLI changes quickly.
  • Use --raw when piping values into other tools. Use --json only if the installed CLI advertises it.
  • Use named sessions with -s=<name> for concurrent or long-lived work.
  • Use open --persistent only when disk-persisted cookies/storage are needed.
  • Prefer attach --cdp=chrome, attach --cdp=msedge, or attach --cdp=http://127.0.0.1:9222 when the task needs an existing browser/session.
  • Close sessions when finished. Reserve close-all and kill-all for cleanup of stale sessions.

Common Tasks

playwright-cli open https://example.com --browser=chrome
playwright-cli snapshot --depth=4
playwright-cli screenshot --filename=page.png
playwright-cli console warning
playwright-cli network --filter="/api/.*" --request-headers
playwright-cli run-code "async page => await page.context().grantPermissions(['geolocation'])"
playwright-cli tracing-start
playwright-cli tracing-stop

For a broader command map, read references/cli-reference.md.

Playwright Test Debugging

When a Playwright test fails, prefer the CLI debug workflow:

PLAYWRIGHT_HTML_OPEN=never npx playwright test --debug=cli
# wait for "Debugging Instructions", then attach to the printed session
playwright-cli attach tw-abcdef

Keep the test process running while inspecting the paused page. Use snapshots, console/network inspection, and generated Playwright code to identify the fix.

References

Load only what the task needs:

  • references/cli-reference.md — command groups, output modes, and version-sensitive features
  • references/playwright-tests.md — running and debugging Playwright tests
  • references/request-mocking.md — route mocking and request interception
  • references/running-code.md — custom Playwright snippets with run-code
  • references/session-management.md — named sessions and cleanup
  • references/storage-state.md — cookies, localStorage, sessionStorage, auth state
  • references/test-generation.md — turning CLI output into tests
  • references/tracing.md — trace capture and inspection
  • references/video-recording.md — WebM recording and chapter markers
  • references/element-attributes.md — inspect IDs/classes/data attributes not shown in snapshots

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.