Browser automation with Playwright CLI

Drives a real browser from the terminal with playwright-cli: snapshots give element refs for clicks and typing, plus screenshots, console, network and traces, with no test files written. Use when a task needs a browser clicked through step by step.

TestingPack: OpenAI skills147 linesplaywright
Author
Source
openai/skills/skills/.curated/playwright @ 49f948f
License
Apache-2.0

About this skill

What it does

The skill lets the agent drive a real browser from the terminal with playwright-cli, one command at a time: open a page, take a snapshot, act on an element, look again. The snapshot gives every element a short ref such as e3, and click, fill, select or check take those refs. After navigation, a modal or a tab switch the agent snapshots again because refs go stale, and it does not bypass refs with eval or run-code without a reason. It saves screenshots and PDFs, reads the console and network log, records traces, works across tabs and keeps named sessions apart (--session or PLAYWRIGHT_CLI_SESSION). Artifacts go to output/playwright/. It writes @playwright/test specs only if you ask.

scripts/playwright_cli.sh runs npx --yes --package @playwright/cli playwright-cli, so no global install is needed, and passes the session variable on. references/cli.md lists the main commands; references/workflows.md shows common flows and a playwright-cli.json config. NOTICE.txt says the skill is adapted from Microsoft's playwright-cli skill.

When to use it, and when not

Use it to click through a flow, fill a form, pull data from a page, take screenshots, or reproduce a UI bug with the console at hand.

For tests that live in the repository and run in CI it is the wrong tool: the skill defaults to CLI commands, not test specs.

How to run it

The install command below puts the whole folder in place. It needs Node.js with npx; without it the agent stops and asks you to install Node. SKILL.md looks for the wrapper under $CODEX_HOME/skills/playwright/; in Claude Code or Cursor, point the agent at the folder where the skill was installed, or install the CLI with npm install -g @playwright/cli@latest. The agent picks the skill up by its description; to call it yourself:

  • Claude Code: /playwright, or ask for the skill by name.
  • Codex: $playwright.
  • Cursor: type / in the Agent chat and pick playwright.

Example: /playwright Open localhost:3000, sign up with a test email and take a screenshot after each step.

OpenAI has marked openai/skills deprecated; our copy is pinned to a commit there, and as of November 2026 openai/plugins has no newer version of this skill.

How it differs from similar skills

Web app testing with Playwright scripts has the agent write Python Playwright scripts, with with_server.py starting the app's servers; this skill sends CLI commands one by one and leaves no script behind. E2E tests with Playwright writes @playwright/test specs that stay in the repository. Browser testing with Chrome DevTools MCP works through an MCP server instead of a CLI and adds performance traces with LCP, CLS and INP.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/playwright/SKILL.md https://anymodel.org/en/skills/openai/playwright/SKILL.md -o ~/.claude/skills/playwright/LICENSE.txt https://anymodel.org/en/skills/openai/playwright/LICENSE.txt -o ~/.claude/skills/playwright/NOTICE.txt https://anymodel.org/en/skills/openai/playwright/NOTICE.txt -o ~/.claude/skills/playwright/agents/openai.yaml https://anymodel.org/en/skills/openai/playwright/agents/openai.yaml -o ~/.claude/skills/playwright/assets/playwright-small.svg https://anymodel.org/en/skills/openai/playwright/assets/playwright-small.svg -o ~/.claude/skills/playwright/assets/playwright.png https://anymodel.org/en/skills/openai/playwright/assets/playwright.png -o ~/.claude/skills/playwright/references/cli.md https://anymodel.org/en/skills/openai/playwright/references/cli.md -o ~/.claude/skills/playwright/references/workflows.md https://anymodel.org/en/skills/openai/playwright/references/workflows.md -o ~/.claude/skills/playwright/scripts/playwright_cli.sh https://anymodel.org/en/skills/openai/playwright/scripts/playwright_cli.sh && chmod +x ~/.claude/skills/playwright/scripts/playwright_cli.sh
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/playwright/SKILL.md https://anymodel.org/en/skills/openai/playwright/SKILL.md -o ~/.agents/skills/playwright/LICENSE.txt https://anymodel.org/en/skills/openai/playwright/LICENSE.txt -o ~/.agents/skills/playwright/NOTICE.txt https://anymodel.org/en/skills/openai/playwright/NOTICE.txt -o ~/.agents/skills/playwright/agents/openai.yaml https://anymodel.org/en/skills/openai/playwright/agents/openai.yaml -o ~/.agents/skills/playwright/assets/playwright-small.svg https://anymodel.org/en/skills/openai/playwright/assets/playwright-small.svg -o ~/.agents/skills/playwright/assets/playwright.png https://anymodel.org/en/skills/openai/playwright/assets/playwright.png -o ~/.agents/skills/playwright/references/cli.md https://anymodel.org/en/skills/openai/playwright/references/cli.md -o ~/.agents/skills/playwright/references/workflows.md https://anymodel.org/en/skills/openai/playwright/references/workflows.md -o ~/.agents/skills/playwright/scripts/playwright_cli.sh https://anymodel.org/en/skills/openai/playwright/scripts/playwright_cli.sh && chmod +x ~/.agents/skills/playwright/scripts/playwright_cli.sh
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE.txt','NOTICE.txt','agents/openai.yaml','assets/playwright-small.svg','assets/playwright.png','references/cli.md','references/workflows.md','scripts/playwright_cli.sh') { $p = Join-Path "$HOME\.claude\skills\playwright" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/openai/playwright/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE.txt','NOTICE.txt','agents/openai.yaml','assets/playwright-small.svg','assets/playwright.png','references/cli.md','references/workflows.md','scripts/playwright_cli.sh') { $p = Join-Path "$HOME\.agents\skills\playwright" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/openai/playwright/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/openai/playwright/SKILL.md

SKILL.md

Raw

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.

Form fill and submit

"$PWCLI" open https://example.com/form
"$PWCLI" snapshot
"$PWCLI" fill e1 "[email protected]"
"$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.

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack OpenAI skills

ASP.NET Core apps

Guides the agent through current ASP.NET Core practice: choosing Blazor, Razor Pages, MVC or Minimal APIs, Program.cs and middleware order, auth, EF Core, tests and upgrades to .NET 10. Use when building, reviewing or upgrading an ASP.NET Core app.

ChatGPT Apps SDK

Builds ChatGPT apps on the Apps SDK: reads current OpenAI docs first, picks an app archetype, plans MCP tools, adapts an official example or scaffolds a Node server and widget, then tests in Developer Mode. Use when building or fixing an app inside ChatGPT.

CLI creator from API docs

Builds a durable CLI from API docs, an OpenAPI spec, curls or a script: JSON output, doctor and dry-run commands, safe auth, installed on PATH and paired with a companion skill. Use when an agent keeps hitting the same service through ad hoc calls.

Define a measurable goal

Turns a fuzzy intention into one measurable goal with a validator, scope and stop condition, then registers it via get_goal and create_goal. Use before goal-backed or long-running agent work, when "done" needs a number or a check.

Address GitHub PR comments

Fetches all comments, reviews and inline threads on the current branch's GitHub PR with a gh GraphQL script, numbers them and fixes only the ones you pick. Use when a PR has review comments to work through and you want to choose which get changed.

Fix failing GitHub Actions checks

Finds failing GitHub Actions checks on a PR with gh, pulls the logs, extracts the failure snippet and drafts a fix plan, changing code only after approval. Use when a PR's CI is red and you want the cause and a plan before any edit.

Jupyter notebooks

Creates and tidies Jupyter notebooks for experiments or tutorials from bundled templates via a stdlib script, with structure patterns and a run-top-to-bottom checklist. Use when starting a notebook or turning a messy one into something others can rerun.

Linear issues and projects

Works with Linear issues, projects and cycles through Linear's MCP server in a fixed order: setup, scope, read, then write, with sample workflows for triage, sprints and releases. Use when an agent should read or update Linear as part of a task.

Deploy to Netlify

Deploys the current project to Netlify with `npx netlify`: checks the login, links the folder to a site by Git remote or creates one, builds locally and returns a preview or production URL. Use when you want to publish a site to Netlify from your machine.

Deploy to Render

Deploys an app to Render from a Git repo: writes and validates a render.yaml Blueprint with services, databases and secrets, or creates one service through the Render MCP server, then checks status and logs. Use when an app needs hosting on Render.

Security best-practice review

Checks Python, JavaScript/TypeScript and Go code against bundled security specs for ten frameworks, writes a report by severity with line numbers and fixes one finding at a time. Use when you explicitly ask for a security best-practice review.

Repository threat model

Writes a repository-grounded threat model: trust boundaries, assets, attacker capabilities and ranked abuse paths with mitigations, asking you to confirm key assumptions before the final file. Use when you explicitly ask to threat model a codebase.

Sentry issues and events

Reads Sentry issues and events through the sentry CLI without changing anything: recent production errors, issue and event details, AI root-cause summaries, with PII redacted. Use when you ask what is failing in production according to Sentry.

Deploy to Vercel

Deploys a project to Vercel, as a preview unless told otherwise, through the Vercel CLI or, without an account, a bundled script that uploads the folder and returns a preview link and a claim link. Use when you want a shareable deployment link fast.

Figma MCP design context

Reads Figma frames through the Figma MCP server in a fixed order (design context, metadata, screenshot) and rebuilds them with the project's components and tokens; also covers server setup in Codex. Use when connecting Figma MCP or coding from a frame link.

Figma use_figma prerequisite

Sets the rules an agent must load before every use_figma call that runs Plugin API JavaScript in a Figma file: return values, page resets, colours, fonts, node IDs, small validated steps. Use when creating or editing anything inside a Figma file.

Implement a Figma design in code

Implements a Figma frame or component as code in your repo with 1:1 visual parity: fetches context and a screenshot, maps the output to project tokens and components, then runs a validation checklist. Use when a Figma link must become production UI.

Generate a Figma design from an app

Builds or updates a full screen in Figma from code or a description, section by section, using the file's published components, variables and styles instead of hardcoded values. Use when a page from your app should exist as a Figma screen.

Figma design system from a codebase

Builds a Figma design system library from a codebase in five supervised phases: discovery, variables and styles, page structure, components one by one, QA. Use when a product needs a Figma library that matches its code tokens and components.

Figma Code Connect components

Links published Figma components to the code components that implement them via Code Connect: finds unmapped ones, matches them in the codebase, maps only what the user approves. Use when a Figma library and its code both exist but are not linked.

Figma design system rules

Writes project rules for turning Figma designs into code into CLAUDE.md, AGENTS.md or a Cursor rules file, based on Figma's rule template and an analysis of the codebase. Use when setting up an agent for regular Figma-to-code work in a repo.

Create a new Figma file

Creates a blank Figma design file or FigJam board in your drafts, resolving the plan through whoami, and returns the file key and URL. Use when the next Figma step needs a fresh file to write into.