The Agent Skills Directory

[SAFE]: No security vulnerabilities or malicious patterns were detected during the analysis of the skill's instructions and logic.
The skill operates locally on the project's source code to generate unit and integration tests.
It implements a mandatory "Approve first" gate in doctrine.md, ensuring the user reviews and confirms the testing strategy before any file-write operations or command executions occur.
The disable-model-invocation: true flag in SKILL.md restricts the agent's ability to trigger other model-driven skills without oversight.
No network operations, sensitive data access, or obfuscation techniques were found.

create-test