Workflow·Web, Search & Scraping

Browser Automation with playwright-cli

Name: Browser Automation with playwright-cli
Author: microsoft

Automate browser interactions, test web pages and work with Playwright tests.

You say

Install this skill Read the source first Free Written by microsoft · unverified publisher

Context cost: 14.7k tokensestimated from the bundle, loaded when it triggers
Bundle: 10 files · 58.6 kBtext throughout, nothing executable
Licence: Apache-2.0free to use
Last change: —no release on file
Servers it uses: Noneruns standalone

What it does

Automate browser interactions, test web pages and work with Playwright tests.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

browserautomationplaywright

Filed under

Web, Search & Scraping

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md12.6 kB · 421 lines

--- name: playwright-cli description: Automate browser interactions, test web pages and work with Playwright tests. allowed-tools: Bash(playwright-cli:*) Bash(npx:*) Bash(npm:*) ---

7# Browser Automation with playwright-cli

9## Quick start

11```bash

12# open new browser

13playwright-cli open

14# navigate to a page

15playwright-cli goto https://playwright.dev

16# interact with the page using refs from the snapshot

17playwright-cli click e15

18playwright-cli type "page.click"

19playwright-cli press Enter

20# take a screenshot (rarely used, as snapshot is more common)

21playwright-cli screenshot

22# close the browser

23playwright-cli close

24```

26## Commands

28### Core

30```bash

31playwright-cli open

32# open and navigate right away

33playwright-cli open https://example.com/

34playwright-cli goto https://playwright.dev

35playwright-cli type "search query"

36playwright-cli click e3

37playwright-cli dblclick e7

38# --submit presses Enter after filling the element

39playwright-cli fill e5 "user@example.com" --submit

40playwright-cli drag e2 e8

41# drop files or data onto an element (from outside the page)

42playwright-cli drop e4 --path=./image.png

43playwright-cli drop e4 --data="text/plain=hello world"

44playwright-cli hover e4

45playwright-cli select e9 "option-value"

46playwright-cli upload ./document.pdf

47playwright-cli check e12

48playwright-cli uncheck e12

49playwright-cli snapshot

50# search the snapshot for text or a regexp, returns matching nodes with surrounding context

51playwright-cli find "Sign in"

52playwright-cli find --regex "Sign (in|up)"

53# wrap the regexp in slashes to add flags, e.g. /i for case-insensitive

54playwright-cli find --regex "/sign (in|up)/i"

55playwright-cli eval "document.title"

56playwright-cli eval "el => el.textContent" e5

57# get element id, class, or any attribute not visible in the snapshot

58playwright-cli eval "el => el.id" e5

59playwright-cli eval "el => el.getAttribute('data-testid')" e5

60playwright-cli dialog-accept

61playwright-cli dialog-accept "confirmation text"

62playwright-cli dialog-dismiss

63playwright-cli resize 1920 1080

64playwright-cli close

65```

67### Navigation

69```bash

70playwright-cli go-back

71playwright-cli go-forward

72playwright-cli reload

73```

75### Keyboard

77```bash

78playwright-cli press Enter

79playwright-cli press ArrowDown

80playwright-cli keydown Shift

81playwright-cli keyup Shift

82```

84### Mouse

86```bash

87playwright-cli mousemove 150 300

88playwright-cli mousedown

89playwright-cli mousedown right

90playwright-cli mouseup

91playwright-cli mouseup right

92playwright-cli mousewheel 0 100

93```

95### Save as

97```bash

98playwright-cli screenshot

99playwright-cli screenshot e5

100playwright-cli screenshot --filename=page.png

101playwright-cli screenshot --hires

102playwright-cli pdf --filename=page.pdf

103```

104

105### Tabs

106

107```bash

108playwright-cli tab-list

109playwright-cli tab-new

110playwright-cli tab-new https://example.com/page

111playwright-cli tab-close

112playwright-cli tab-close 2

113playwright-cli tab-select 0

114```

115

116### Storage

117

118```bash

119playwright-cli state-save

120playwright-cli state-save auth.json

121playwright-cli state-load auth.json

122

123# Cookies

124playwright-cli cookie-list

125playwright-cli cookie-list --domain=example.com

126playwright-cli cookie-get session_id

127playwright-cli cookie-set session_id abc123

128playwright-cli cookie-set session_id abc123 --domain=example.com --httpOnly --secure

129playwright-cli cookie-delete session_id

130playwright-cli cookie-clear

131

132# LocalStorage

133playwright-cli localstorage-list

134playwright-cli localstorage-get theme

135playwright-cli localstorage-set theme dark

136playwright-cli localstorage-delete theme

137playwright-cli localstorage-clear

138

139# SessionStorage

140playwright-cli sessionstorage-list

141playwright-cli sessionstorage-get step

142playwright-cli sessionstorage-set step 3

143playwright-cli sessionstorage-delete step

144playwright-cli sessionstorage-clear

145```

146

147### Network

148

149```bash

150playwright-cli route "**/*.jpg" --status=404

151playwright-cli route "https://api.example.com/**" --body='{"mock": true}'

152playwright-cli route-list

153playwright-cli unroute "**/*.jpg"

154playwright-cli unroute

155```

156

157### DevTools

158

159```bash

160playwright-cli console

161playwright-cli console warning

162playwright-cli requests

163playwright-cli request 5

164playwright-cli run-code "async page => await page.context().grantPermissions(['geolocation'])"

165playwright-cli run-code --filename=script.js

166playwright-cli tracing-start

167playwright-cli tracing-stop

168playwright-cli video-start video.webm

169playwright-cli video-chapter "Chapter Title" --description="Details" --duration=2000

170playwright-cli video-stop

171

172# annotate each subsequent action (click, type, ...) with a callout naming the action and highlighting the target

173playwright-cli video-show-actions --duration=600 --position=top-right

174playwright-cli video-hide-actions

175

176# launch the dashboard for UI review / design feedback — user annotates the page, you receive the annotated screenshot, snapshot, and notes

177playwright-cli show --annotate

178

179# generate a Playwright locator for an element from its ref or selector

180playwright-cli generate-locator e5 --raw

181

182# show a persistent highlight overlay for an element, optionally with a custom style

183playwright-cli highlight e5

184playwright-cli highlight e5 --style="outline: 3px dashed red"

185# hide a single element highlight, or all page highlights when no target is given

186playwright-cli highlight e5 --hide

187playwright-cli highlight --hide

188```

189

190## Raw output

191

192The global --raw option strips page status, generated code, and snapshot sections from the output, returning only the result value. Use it to pipe command output into other tools. Commands that don't produce output return nothing.

193

194```bash

195playwright-cli --raw eval "JSON.stringify(performance.timing)" | jq '.loadEventEnd - .navigationStart'

196playwright-cli --raw eval "JSON.stringify([...document.querySelectorAll('a')].map(a => a.href))" > links.json

197playwright-cli --raw snapshot > before.yml

198playwright-cli click e5

199playwright-cli --raw snapshot > after.yml

200diff before.yml after.yml

201TOKEN=$(playwright-cli --raw cookie-get session_id)

202playwright-cli --raw localstorage-get theme

203```

204

205For structured output wrapping every reply as JSON, pass --json

206```bash

207playwright-cli list --json

208```

209

210## Open parameters

211```bash

212# Use specific browser when creating session

213playwright-cli open --browser=chrome

214playwright-cli open --browser=firefox

215playwright-cli open --browser=webkit

216playwright-cli open --browser=msedge

217

218# Emulate a generic mobile device (Pixel 10 for Chromium, iPhone 17 for WebKit).

219# Prefer this when a mobile layout is acceptable: mobile pages are usually

220# lighter, so snapshots are smaller and cheaper.

221playwright-cli open --mobile

222playwright-cli open --device="iPhone 15"

223

224# Use persistent profile (by default profile is in-memory)

225playwright-cli open --persistent

226# Use persistent profile with custom directory

227playwright-cli open --profile=/path/to/profile

228

229# Connect to browser via Playwright Extension

230playwright-cli attach --extension=chrome

231

232# Connect to a running Chrome or Edge by channel name

233playwright-cli attach --cdp=chrome

234playwright-cli attach --cdp=msedge

235

236# Connect to a running browser via CDP endpoint

237playwright-cli attach --cdp=http://localhost:9222

238

239# Start with config file

240playwright-cli open --config=my-config.json

241

242# Close the browser

243playwright-cli close

244# Detach from an attached browser (leaves the external browser running)

245playwright-cli -s=msedge detach

246# Delete user data for the default session

247playwright-cli delete-data

248```

249

250## URLs with & on Windows

251

252On Windows, cmd.exe and PowerShell treat & as a command separator, so URLs with multiple query parameters get truncated before playwright-cli runs. Escape & with ^& in cmd.exe, or use --% in PowerShell:

253

254```batch

255playwright-cli goto "https://example.com/?a=1^&b=2"

256```

257

258```powershell

259playwright-cli --% goto "https://example.com/?a=1&b=2"

260```

261

262## Snapshots

263

264After each command, playwright-cli provides a snapshot of the current browser state.

265

266```bash

267> playwright-cli goto https://example.com

268### Page

269- Page URL: https://example.com/

270- Page Title: Example Domain

271### Snapshot

272[Snapshot](.playwright-cli/page-2026-02-14T19-22-42-679Z.yml)

273```

274

275You can also take a snapshot on demand using playwright-cli snapshot command. All the options below can be combined as needed.

276

277```bash

278# default - save to a file with timestamp-based name

279playwright-cli snapshot

280

281# save to file, use when snapshot is a part of the workflow result

282playwright-cli snapshot --filename=after-click.yaml

283

284# snapshot an element instead of the whole page

285playwright-cli snapshot "#main"

286

287# limit snapshot depth for efficiency, take a partial snapshot afterwards

288playwright-cli snapshot --depth=4

289playwright-cli snapshot e34

290

291# include each element's bounding box as [box=x,y,width,height]

292playwright-cli snapshot --boxes

293

294# search a large snapshot instead of capturing it all — returns matching nodes

295# with 3 lines of context around each match (like grep -C)

296playwright-cli find "Add to cart"

297playwright-cli find --regex "\\$[0-9]+\\.[0-9]{2}"

298```

299

300## Targeting elements

301

302By default, use refs from the snapshot to interact with page elements.

303

304```bash

305# get snapshot with refs

306playwright-cli snapshot

307

308# interact using a ref

309playwright-cli click e15

310```

311

312You can also use css selectors or Playwright locators.

313

314```bash

315# css selector

316playwright-cli click "#main > button.submit"

317

318# role locator

319playwright-cli click "getByRole('button', { name: 'Submit' })"

320

321# test id

322playwright-cli click "getByTestId('submit-button')"

323```

324

325## Browser Sessions

326

327```bash

328# create new browser session named "mysession" with persistent profile

329playwright-cli -s=mysession open example.com --persistent

330# same with manually specified profile directory (use when requested explicitly)

331playwright-cli -s=mysession open example.com --profile=/path/to/profile

332playwright-cli -s=mysession click e6

333playwright-cli -s=mysession close # stop a named browser

334playwright-cli -s=mysession delete-data # delete user data for persistent session

335

336playwright-cli list

337# Close all browsers

338playwright-cli close-all

339# Forcefully kill all browser processes

340playwright-cli kill-all

341```

342

343## Installation

344

345If global playwright-cli command is not available, try a local version via npx playwright cli:

346

347```bash

348npx --no-install playwright --version

349```

350

351When local version is available, use npx playwright cli in all commands. Otherwise, install playwright-cli as a global command:

352

353```bash

354npm install -g @playwright/cli@latest

355```

356

357## Example: Form submission

358

359```bash

360playwright-cli open https://example.com/form

361playwright-cli snapshot

362

363playwright-cli fill e1 "user@example.com"

364playwright-cli fill e2 "password123"

365playwright-cli click e3

366playwright-cli snapshot

367playwright-cli close

368```

369

370## Example: Multi-tab workflow

371

372```bash

373playwright-cli open https://example.com

374playwright-cli tab-new https://example.com/other

375playwright-cli tab-list

376playwright-cli tab-select 0

377playwright-cli snapshot

378playwright-cli close

379```

380

381## Example: Debugging with DevTools

382

383```bash

384playwright-cli open https://example.com

385playwright-cli click e4

386playwright-cli fill e7 "test"

387playwright-cli console

388playwright-cli requests

389playwright-cli close

390```

391

392```bash

393playwright-cli open https://example.com

394playwright-cli tracing-start

395playwright-cli click e4

396playwright-cli fill e7 "test"

397playwright-cli tracing-stop

398playwright-cli close

399```

400

401## Example: Interactive session

402

403Ask the user for UI review or design feedback. The user draws boxes on the live page and types comments; you receive the annotated screenshot, the snapshot of the marked region, and the user's notes. Use this whenever the user asks for "UI review", "design feedback", or to "ask the user what they think / want / mean":

404

405```bash

406playwright-cli open https://example.com

407playwright-cli show --annotate

408```

409

410## Specific tasks

411

412* **Running and Debugging Playwright tests** [references/playwright-tests.md](references/playwright-tests.md)

413* **Request mocking** [references/request-mocking.md](references/request-mocking.md)

414* **Running Playwright code** [references/running-code.md](references/running-code.md)

415* **Browser session management** [references/session-management.md](references/session-management.md)

416* **Storage state (cookies, localStorage)** [references/storage-state.md](references/storage-state.md)

417* **Test generation (plan / generate / heal)** [references/test-generation.md](references/test-generation.md)

418* **Tracing** [references/tracing.md](references/tracing.md)

419* **Video recording** [references/video-recording.md](references/video-recording.md)

420* **Inspecting element attributes** [references/element-attributes.md](references/element-attributes.md)

421

In the file

SKILL.md1,457 words

Files10

LicenceApache-2.0

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈50

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

14,600

on trigger

The instruction body and 9 supporting files, read only when the skill fires.

7.3%

of a 200k window

Ten skills this size would take about 73% of the window before you open a file.

050k100k150k200k context window

14.7k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption

Installsnone yet

Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for

Writes filesno

Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

32 other skills in Web, Search & Scraping

What is in the bundle

10 files, 58.6 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

SKILL.md12.6 kB
references/element-attributes.md0.7 kB
references/playwright-tests.md1.7 kB
references/request-mocking.md2.2 kB
references/running-code.md5.6 kB
references/session-management.md5.7 kB
references/storage-state.md5.2 kB
references/test-generation.md16.1 kB
references/tracing.md3.4 kB
references/video-recording.md5.4 kB

What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 10 files you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Browser Automation with playwright-cli · 14.7k tokens when loaded
npx mcprush@latest skill add microsoft/browser-automation-with-playwright-cli

Writes to .claude/skills/browser-automation-with-playwright-cli/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/

Claude Desktop

ChatGPT

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok.grok/skills/

Zed.agents/skills/

Windsurf.windsurf/skills/

Agent SDK.claude/skills/

HTTP / API

This release

Versionnot versioned

Publishedno release date on file

PriceFree

Referencemicrosoft/browser-automation-with-playwright-cli

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

No earlier releases have been published to the marketplace.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

microsoft

Publishes on mcprush.

0 servers listed2 skills listednot claimed

Profile

Publisher

Servers0

Claim this skill