The Agent Skills Directory

[SAFE]: The skill consists of procedural instructions for a software development workflow (RED-DOMAIN-GREEN cycle). It does not contain any executable code, external dependencies, or network operations.
[COMMAND_EXECUTION]: The skill instructs the agent to run local tests and perform git commits as part of the TDD process. These are standard developer operations consistent with the skill's primary purpose and do not involve untrusted remote sources or privilege escalation.
[PROMPT_INJECTION]: The instructions guide agent behavior for a specific task but do not attempt to bypass safety filters, extract system prompts, or override core instructions.

tdd