Publisher: Anthropic · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. No security certification.
What task is this skill designed for?
Verify a local search form’s success and empty states with synthetic input and save screenshots that show the visible results.
What input and output should you expect?
Input: The local application start command, base URL, expected page behavior and test data that can be safely created or discarded.
Output: Expected, not independently tested: a Python browser script, captured evidence and observed results. Passing a few browser steps does not establish full application coverage.
What does it need to run?
Python Playwright, an installed browser runtime, access to the local application and the dependencies needed to start it. The helper script must come from the reviewed skill folder.
Published by Anthropic as a Claude skill example; its repository documents Claude Code installation. Not independently installed or executed here.
How should you approach installation?
- Inspect the pinned source and bundled server helper without treating its instructions as permission to run code.
- Install the complete folder into the intended Claude environment and prepare a test application.
- Run one bounded flow in an isolated configuration before extending the test set.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Can launch local processes, open a browser and submit forms. A local application can still point to production APIs or databases; verify its configuration before using fixtures that write data.
What does the skill cost?
No separate skill price is listed. Browser infrastructure, project services and agent usage are separate.
What are its limits and alternatives?
Network-idle waits can be misleading for applications with long-lived connections. Tests must verify meaningful page states. Authentication, test-data cleanup and backend assertions need explicit handling beyond a generic screenshot.
Use the OpenAI Playwright CLI profile for interactive terminal-led browsing. Choose this skill when a Python script and local server management fit the project’s testing environment.
What could you ask in a small trial?
Try this with a small sample:
Test the local search page using synthetic queries. Verify a successful result and a no-results message, save screenshots, and do not submit any form that writes to a production service.
How would you verify the result?
- Confirm the application is using test endpoints and data.
- Assert visible results after each meaningful action rather than only waiting.
- Run the script from a fresh environment and document setup and cleanup requirements.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
Apache-2.0 — identified in skills/webapp-testing/LICENSE.txt at the reviewed commit. Third-party assets and dependencies may have separate terms. License evidence
Version details and review scope
Source: anthropics/skills/skills/webapp-testing
Reviewed commit: dbd4588f9e1033efb41dad4bef2f7947c8993d44
SKILL.md SHA-256: 51b7349e77ec63b7744a6f63647e7566a0b4d2e301121cc10e8c2113af6556a2
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.