Playwright Cli logo

Playwright Cli

Community
lexler
playwright-cli

Drive a browser from the terminal with playwright-cli: snapshot the page, then act on elements by ref. Use when automating browser interactions, filling web forms, testing UIs, or driving logged-in web apps from the command line.

Overview

Publisherlexler
Repositoryskill-factory
Skill nameplaywright-cli
Stars
239
Forks
63
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lexler on GitHub. Read the source before you install it.

Installation

Install the Playwright Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/lexler/skill-factory/tree/main/output_skills/developer-tools/playwright-cli
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/lexler/skill-factory.git /tmp/skill-factory
mkdir -p .claude/skills
cp -r /tmp/skill-factory/output_skills/developer-tools/playwright-cli .claude/skills/playwright-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Playwright Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Playwright Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Playwright Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

STARTER_CHARACTER = 🎭

playwright-cli

Driving a browser from the shell. Each command prints the executed Playwright code, the page state, and a fresh snapshot.

The loop

Snapshot to see the page, act on an element by its ref, snapshot again.

bash
playwright-cli snapshot          # accessibility tree with [ref=e8] handles
playwright-cli click e8          # act on a ref
playwright-cli snapshot          # confirm the result

Refs are not stable. Any DOM change renumbers them — re-snapshot before acting on a page that just changed. Acting on a stale ref hits the wrong element or none.

For a large page, snapshot a region instead of the whole tree: snapshot e34 or snapshot --depth=4.

Targeting elements

A target is one of three things — a ref, a CSS selector, or a Playwright locator:

bash
playwright-cli click e8
playwright-cli click ".todo-list .toggle"
playwright-cli click "getByRole('button', { name: 'Submit' })"
playwright-cli click "getByText('buy milk')"

A bare descriptive phrase is not a target. click "the submit button" is parsed as a CSS selector and fails with "does not match any elements". Prefer refs; reach for getByRole/getByText when a ref won't survive a re-render.

Key commands

bash
playwright-cli goto https://example.com
playwright-cli fill e5 "user@example.com" --submit   # clear, type, then Enter — one step
playwright-cli type "free text into the focused element"
playwright-cli press Enter                            # also: Tab, Escape, ArrowDown
playwright-cli select e9 "option-value"
playwright-cli check e12        # uncheck / hover / dblclick likewise
playwright-cli screenshot       # saves to .playwright-cli/

fill works on React/controlled inputs where raw DOM events don't. After filling, the field must blur before dependent values (totals, validation) update — --submit or a following press Tab does that.

Inspecting and verifying

bash
playwright-cli eval "el => el.getAttribute('data-testid')" e5   # attributes the snapshot hides
playwright-cli console                                          # page console messages
playwright-cli requests                                         # network log, then `request <n>`

--raw strips the wrapper so output pipes, and proves what an action changed:

bash
playwright-cli --raw snapshot > before.yml
playwright-cli click e8
playwright-cli --raw snapshot > after.yml
diff before.yml after.yml

Sessions

open launches a fresh browser; --persistent keeps cookies across runs. To drive an already-running, logged-in browser instead, attach over CDP. See references/attaching-to-chrome.md.

Name parallel browsers with -s=<name> (omit it for the implicit default session). playwright-cli list, close, close-all.

Full command set

The above is the working subset. The CLI ships its own exhaustive reference — tabs, storage, mocking, tracing, video, codegen. See references/full-command-reference.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Playwright Cli AI skill do?

Drive a browser from the terminal with playwright-cli: snapshot the page, then act on elements by ref. Use when automating browser interactions, filling web forms, testing UIs, or driving logged-in web apps from the command line.

Why use Playwright Cli on TypingMind?

Because you install it once and use it with any model. Playwright Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Playwright Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lexler/skill-factory/tree/main/output_skills/developer-tools/playwright-cli. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Playwright Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Playwright Cli?

As many as you like. As long as a model supports skills, you can use Playwright Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Playwright Cli AI skill free?

Yes. It is published on GitHub by lexler under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇