The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands for environment preparation and test execution.\n
Uses netstat and curl to identify active development server ports on localhost (SKILL.md).\n
Executes npm run dev and npm run test:e2e for server lifecycle management and test suites (SKILL.md).\n
Includes instructions for manual process management and cleanup using TaskStop (SKILL.md).\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection during testing.\n
Ingestion points: Data from the game environment enters the agent context via page.evaluate() (to access window properties like playerState) and through DOM interrogation using page.locator() (SKILL.md).\n
Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the game state.\n
Capability inventory: The skill possesses capabilities including shell command execution, background task management, and automated browser control (SKILL.md).\n
Sanitization: No validation or sanitization of data retrieved from the browser context is specified before it is processed by the agent.

qa-gameplay-testing