agent-browser
Navigate pages, inspect snapshots and repeat common browser actions using a CLI.
npx skills add vercel-labs/agent-browser --skill agent-browserTest browser workflows you own and turn authorized page interactions into repeatable checks.
Choose a CLI for quick reproducible interactions, a test skill for assertions, or testing guidance for a flaky suite.
Navigate pages, inspect snapshots and repeat common browser actions using a CLI.
npx skills add vercel-labs/agent-browser --skill agent-browserRecord browser actions and inspect results with Playwright CLI tooling.
npx skills add microsoft/playwright-cli --skill playwright-cliTest a running web application with Playwright and capture screenshots or logs.
npx skills add anthropics/skills --skill webapp-testingImprove the reliability of Playwright test suites, selectors and assertions.
npx skills add currents-dev/playwright-best-practices-skill --skill playwright-best-practicesAutomate repeatable form and navigation tasks on websites you are authorized to use.
npx skills add browser-act/skills --skill browser-actGuide a browser agent through browsing and data entry on permitted sites.
npx skills add browser-use/browser-use --skill browser-useNo skill in this category has a full write-up yet.
A browser skill lets Claude drive a real browser instead of guessing what a page looks like. That distinction matters: a model reading HTML can tell you a button exists, but not that a cookie banner covers it, that its label only appears on hover, or that the form resets when you tab away. A browser skill closes the loop — act, then look at what actually happened.
Three jobs cover almost every use: filling a form that has no API, reading a dashboard that only renders client-side, and proving that a change you shipped still works after login.
The six skills on this page split into three kinds, and picking the wrong kind is the usual reason someone concludes “browser automation doesn't work”.
For a repeatable test of your own app, use webapp-testing from anthropics. It writes Playwright assertions you can run in CI, and it expects a running web application — not a production site you do not own. Pair it with playwright-best-practices from currents-dev when your suite is already flaky: that one is about selectors and waiting strategy, not about driving a browser for you.
For one-off inspection of a live page, use a CLI. Agent Browser from Vercel Labs navigates and prints a snapshot of the page; playwright-cli (microsoft) records the actions you take by hand so you can replay them. Record the flow manually once, then let the agent turn the recording into a script — that order matters, because a script written from a description is a guess.
For form and navigation tasks you are authorised to run, browser-act and browser-use sit at that level: multi-step flows on permitted sites, with the agent deciding the next action. They are the most useful and the least predictable of the six, so give them a stopping condition.
Use a test account and record the page state, locator and assertion for each step.
Record the page state, locator and assertion for every step, and re-run the check before calling it stable.
Use the command beside the skill, select a supported agent, then reload the agent and confirm it can see the skill in your project.
For your own application, webapp-testing writes assertions you can run in CI. agent-browser and browser-act drive a live page for inspection. If the goal is a repeatable test, use the testing skill, not the CLI.
No. Driving a site you do not own or have written permission to use runs into terms of service, rate limits and legal exposure that no skill removes. Test your own staging environment instead.
Install playwright-cli when you want a script built from actions you have already done by hand, and record the flow manually once first. The recorded script and the manual flow should match before you trust it.
Use a test account with no real customer records. Deleting a row or sending an email during a test run is not recoverable, and production data is the most common cause of an automation incident.
Use the API for operations it supports. Use browser automation when you need to verify what a user sees or interacts with on the page.
A browser skill needs an authorized test session to work behind a login. Use a dedicated test account with sample records.
Stop the run at the CAPTCHA and review the step manually. In a test environment you own, use the CAPTCHA provider's test configuration.
Check the resulting record in the application, such as the saved row or created ticket. A screenshot shows the page rendered, and the record confirms that the action persisted.