The Agent Skills Directory

[SAFE]: The skill content is purely educational and instructional, providing a framework for the red-green-refactor development cycle.- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters or override core agent behavior. Guidelines to read project-specific documentation like CONTEXT.md or ADRs are standard for aligning the agent's output with a specific codebase.- [DATA_EXFILTRATION]: No network operations or unauthorized data access patterns were detected. References to environment variables (e.g., STRIPE_KEY) and database interactions in the provided files are used as illustrative examples of code to be mocked or tested, rather than active exfiltration logic.- [REMOTE_CODE_EXECUTION]: The skill does not perform any external package installations or execute code from remote sources. It contains only static markdown and configuration files.

tdd