The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not include executable scripts (Python, Node.js, or shell). It focuses on static analysis and documentation of test designs.
[SAFE]: The instructions explicitly prohibit the agent from executing tests, editing target systems, or inventing data, which serves as a safety constraint against unauthorized system modifications.
[SAFE]: No sensitive file paths, hardcoded credentials, or network operations were detected in the skill files.
[SAFE]: The YAML frontmatter in SKILL.md correctly scopes the skill's purpose without requesting elevated permissions or unsafe tool access.
[SAFE]: The evals/ directory contains standard configuration for testing the agent's adherence to the property-based testing design rules and does not contain malicious payloads.

property-based-testing