The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx playwright test to run automated browser tests.
[DYNAMIC_EXECUTION]: The skill utilizes the Playwright framework to dynamically execute JavaScript within a browser context for verifying DOM structure, computed styles, and interactive behaviors.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it interacts with web content and browser DOM which may originate from untrusted sources.
Ingestion points: Web pages and DOM elements accessed via page.goto() and page.locator() in SKILL.md.
Boundary markers: Not explicitly defined in the provided test templates, though the skill context is constrained to developer testing.
Capability inventory: Command-line execution via npx and file system writes for screenshots (page.screenshot).
Sanitization: The skill explicitly mandates 'Test Payload Sanitization' to prevent the inclusion of real PII or sensitive tokens in test fixtures.

browser-tdd