Skip to content
cccskills
FreePublished on GitHub

playwright

Automate a real browser from the terminal to navigate pages, fill forms, extract data, and investigate interface problems. Use page snapshots to identify controls, and capture screenshots or traces, records of browser activity, for review.

OriginalShow the original description

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` or the bundled wrapper script.

Works withPlaywright
See how to install

Good for

  • Automate form filling and submission
  • Extract information from web pages
  • Investigate UI flows with screenshots and traces
  • Work across multiple browser tabs

Files included (9)

  • SKILL.md3.7 KB
  • agents/openai.yaml313 B
  • assets/playwright-small.svg828 B
  • assets/playwright.png1.7 KB
  • LICENSE.txt11.3 KB
  • NOTICE.txt403 B
  • references/cli.md1.8 KB
  • references/workflows.md1.8 KB
  • scripts/playwright_cli.sh526 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Playwright CLI Skill

Drive a real browser from the terminal using playwright-cli. Prefer the bundled wrapper script so the CLI works even when it is not globally installed. Treat this skill as CLI-first automation. Do not pivot to @playwright/test unless the user explicitly asks for test files.

Prerequisite check (required)

Before proposing commands, check whether npx is available (the wrapper depends on it):

command -v npx >/dev/null 2>&1

If it is not available, pause and ask the user to install Node.js/npm (which provides npx). Provide these steps verbatim:

# Verify Node/npm are installed
node --version
npm --version

# If missing, install Node.js/npm, then:
npm install -g @playwright/cli@latest
playwright-cli --help

Once npx is present, proceed with the wrapper script. A global install of playwright-cli is optional.

Skill path (set once)

export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export PWCLI="$CODEX_HOME/skills/playwright/scripts/playwright_cli.sh"

User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).

Quick start

Use the wrapper script:

"$PWCLI" open https://playwright.dev --headed
"$PWCLI" snapshot
"$PWCLI" click e15
"$PWCLI" type "Playwright"
"$PWCLI" press Enter
"$PWCLI" screenshot

If the user prefers a global install, this is also valid:

npm install -g @playwright/cli@latest
playwright-cli --help

Core workflow

  1. Open the page.
  2. Snapshot to get stable element refs.
  3. Interact using refs from the latest snapshot.
  4. Re-snapshot after navigation or significant DOM changes.
  5. Capture artifacts (screenshot, pdf, traces) when useful.

Minimal loop:

"$PWCLI" open https://example.com
"$PWCLI" snapshot
"$PWCLI" click e3
"$PWCLI" snapshot

When to snapshot again

Snapshot again after:

  • navigation
  • clicking elements that change the UI substantially
  • opening/closing modals or menus
  • tab switches

Refs can go stale. When a command fails due to a missing ref, snapshot again.

Recommended patterns

Form fill and submit

"$PWCLI" open https://example.com/form
"$PWCLI" snapshot
"$PWCLI" fill e1 "user@example.com"
"$PWCLI" fill e2 "password123"
"$PWCLI" click e3
"$PWCLI" snapshot

Debug a UI flow with traces

"$PWCLI" open https://example.com --headed
"$PWCLI" tracing-start
# ...interactions...
"$PWCLI" tracing-stop

Multi-tab work

"$PWCLI" tab-new https://example.com
"$PWCLI" tab-list
"$PWCLI" tab-select 0
"$PWCLI" snapshot

Wrapper script

The wrapper script uses npx --package @playwright/cli playwright-cli so the CLI can run without a global install:

"$PWCLI" --help

Prefer the wrapper unless the repository already standardizes on a global install.

References

Open only what you need:

  • CLI command reference: references/cli.md
  • Practical workflows and troubleshooting: references/workflows.md

Guardrails

  • Always snapshot before referencing element ids like e12.
  • Re-snapshot when refs seem stale.
  • Prefer explicit commands over eval and run-code unless needed.
  • When you do not have a fresh snapshot, use placeholder refs like eX and say why; do not bypass refs with run-code.
  • Use --headed when a visual check will help.
  • When capturing artifacts in this repo, use output/playwright/ and avoid introducing new top-level artifact folders.
  • Default to CLI commands and workflows, not Playwright test specs.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

aspnet-core

FreeSummary

Build, review, and refactor ASP.NET Core web applications using official guidance. Helps choose application structure, implement pages and APIs, configure authentication and services, and plan testing, performance improvements, deployment, and version upgrades.

  • Choose an application model for a new project
  • Build pages and HTTP APIs
  • Review authentication and application configuration
openai/skills28.2KUpdated Sep 9, 2026

chatgpt-apps

FreeSummary

Build and troubleshoot ChatGPT apps with an MCP server that exposes tools and an optional interactive widget. Use current official documentation and examples to create scaffolds, configure security settings, and guide local validation and deployment when requested.

  • Create a ChatGPT app scaffold from an official example
  • Design tools and connect an MCP server to a widget
  • Refactor or troubleshoot an existing Apps SDK app
openai/skills28.2KUpdated Sep 9, 2026

cli-creator

FreeSummary

Turn API documentation or existing scripts into reusable command-line tools that Codex can run from any folder. Builds focused read and write commands, consistent JSON output, authentication handling, installation instructions, and a companion skill.

  • Turn an API into reusable commands
  • Make an internal script available from any folder
  • Build a tool for downloading and searching logs
openai/skills28.2KUpdated Sep 9, 2026

Deploy applications and infrastructure on Cloudflare by matching project needs to services such as Workers and Pages. Guides service selection and authentication checks, with references covering storage, AI, networking, security, and infrastructure configuration.

  • Publish a website or application on Cloudflare
  • Deploy serverless functions with Workers
  • Choose storage for databases and files
openai/skills28.2KUpdated Sep 9, 2026

define-goal

FreeSummary

Turn a vague intention into a concrete goal with clear scope, measurable success criteria, and evidence of completion. Check existing goals before creating one, so the agent has a specific outcome to pursue without duplicating active work.

  • Turn a vague intention into a measurable goal
  • Define completion criteria for a bug fix
  • Set performance targets and measurement methods
openai/skills28.2KUpdated Sep 9, 2026

figma

FreeSummary

Turn a linked Figma frame or layer into application code using the Figma MCP server, a connection for accessing design data. Retrieve design details, screenshots, and assets, reuse existing project components, and compare the implementation with the design.

  • Implementing a screen from a Figma frame link
  • Retrieving images and SVG assets from a design
  • Adapting a design to existing project components
openai/skills28.2KUpdated Sep 9, 2026

See all skills by openai

Report a problem with this skill