Web App Testing is an agent skill by Anthropic that tests local web apps by writing Python Playwright scripts. It includes a helper that starts your servers before the test runs.
What it does
- Chooses an approach based on whether the page is static HTML or a running app.
- Starts one or more dev servers with a bundled script and waits for them to be ready.
- Inspects the rendered page with screenshots and the DOM before choosing selectors.
- Captures console logs and screenshots while it clicks through the app.
When to use it
Use it when you want your agent to check that a local frontend actually works in a browser.
How to get it
The skill is free on GitHub under the Apache 2.0 license, in Anthropic's skills repo. Anthropic says the skills in this repo are already available on paid Claude.ai plans. In Claude Code, run /plugin marketplace add anthropics/skills, then /plugin install example-skills@anthropic-agent-skills. It needs Python with Playwright installed.
more skills
Web App Testing is an agent skill by Anthropic that tests local web apps by writing Python Playwright scripts. It includes a helper that starts your servers before the test runs.
What it does
- Chooses an approach based on whether the page is static HTML or a running app.
- Starts one or more dev servers with a bundled script and waits for them to be ready.
- Inspects the rendered page with screenshots and the DOM before choosing selectors.
- Captures console logs and screenshots while it clicks through the app.
When to use it
Use it when you want your agent to check that a local frontend actually works in a browser.
How to get it
The skill is free on GitHub under the Apache 2.0 license, in Anthropic's skills repo. Anthropic says the skills in this repo are already available on paid Claude.ai plans. In Claude Code, run /plugin marketplace add anthropics/skills, then /plugin install example-skills@anthropic-agent-skills. It needs Python with Playwright installed.
more skills
Web App Testing is an agent skill by Anthropic that tests local web apps by writing Python Playwright scripts. It includes a helper that starts your servers before the test runs.
What it does
- Chooses an approach based on whether the page is static HTML or a running app.
- Starts one or more dev servers with a bundled script and waits for them to be ready.
- Inspects the rendered page with screenshots and the DOM before choosing selectors.
- Captures console logs and screenshots while it clicks through the app.
When to use it
Use it when you want your agent to check that a local frontend actually works in a browser.
How to get it
The skill is free on GitHub under the Apache 2.0 license, in Anthropic's skills repo. Anthropic says the skills in this repo are already available on paid Claude.ai plans. In Claude Code, run /plugin marketplace add anthropics/skills, then /plugin install example-skills@anthropic-agent-skills. It needs Python with Playwright installed.

