The Agent Skills Directory

[SAFE]: The skill consists of instructional documentation and coding guidelines that promote best practices in software design and testing.
[COMMAND_EXECUTION]: The skill defines a workflow for writing and executing code tests. This is the intended purpose of the skill and is secured by explicit manual checkpoints ('Pause') where the agent must stop and wait for user confirmation before proceeding with any implementation or next steps.
[PROMPT_INJECTION]: The agent processes external data such as project requirement documents (PRDs) and agent briefs. Although these inputs serve as a surface for indirect prompt injection, the skill mitigates this risk by requiring the agent to present its generated tests and implementation summaries to the user for validation at every stage of the TDD cycle.

tdd