The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for a human-in-the-loop test design process. It does not perform any automated system actions or network communication.
[NO_CODE]: No executable code, scripts, or binary dependencies are included with the skill; it serves purely as a conceptual framework for an AI agent to assist with test planning.
[INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: The skill is designed to process behavior specifications and acceptance criteria in Step 1. 2. Boundary markers: No explicit markers are defined for untrusted content. 3. Capability inventory: The skill has no functional capabilities such as file system writing, network requests, or command execution. 4. Sanitization: No sanitization is performed, but the workflow requires human review (Step 6) as a verification baseline before scenarios are treated as verified.

tdd-tests