The Agent Skills Directory

[COMMAND_EXECUTION]: The skill guides the agent to perform shell operations such as npm test and npm run test:coverage to validate the implementation against defined test cases.
[REMOTE_CODE_EXECUTION]: The core TDD workflow involves the dynamic creation of test files (unit, integration, and E2E) which are subsequently executed to ensure code quality and coverage.
[EXTERNAL_DOWNLOADS]: The skill references standard industry tools and libraries including Jest, Vitest, and Playwright, and includes integration patterns for external services like Supabase and OpenAI.
[PROMPT_INJECTION]: An indirect prompt injection surface is present in the TDD workflow.
Ingestion points: User-provided descriptions (User Journeys) in Step 1 serve as the basis for generated test code.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat user-provided journey text as untrusted content.
Capability inventory: The agent possesses the capability to write files and execute shell commands (npm test) which could be exploited if malicious code is generated from a poisoned journey.
Sanitization: The skill lacks instructions for sanitizing or validating user input before incorporating it into executable test scripts.

tdd-workflow