webapp-testing
Interact with and test local web apps using Playwright — screenshots, logs, UI debugging.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for webapp-testing, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official web-app testing skill. Writes native Python Playwright scripts to verify frontend functionality, debug UI behavior, capture screenshots, and read browser logs, with a bundled with_server.py helper that manages one or more server lifecycles. Launches a real browser and runs arbitrary Playwright automation against local servers.
Key features and capabilities
- Native Playwright script generation
- with_server.py multi-server lifecycle manager
- Screenshot capture and browser-log inspection
Use cases
- Test a local React app's login flow
- Debug a failing UI interaction with screenshots