The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs local shell operations to run linting, type-checking, and Playwright/Cypress test suites. These commands are necessary for the skill's stated purpose and are scoped to the project's repository context.\n- [EXTERNAL_DOWNLOADS]: Downloads and initializes well-known automation frameworks from official package registries (e.g., npm init playwright@latest). These downloads target trusted services and represent standard development workflows.\n- [REMOTE_CODE_EXECUTION]: Includes capabilities for remote repository actions like pushing or merging code. Security is maintained through a strictly enforced promotion policy that requires explicit human approval and documented verification before any remote action can be executed.\n- [DATA_EXFILTRATION]: Synchronizes automation status with Notion and Plane.so platforms via their respective MCP tools. The instructions include specific mandates for redacting secrets, tokens, and personally identifiable information (PII) before transmission to these external services.

qa-automation