The Agent Skills Directory

[SAFE]: The skill is a purely analytical framework designed to guide an AI agent through the process of reviewing test code quality. It identifies common pitfalls such as test brittleness, mock abuse, and code duplication without performing any system-level changes or external network calls.
[NO_CODE]: The skill consists only of markdown documentation (SKILL.md and test-guide.md). It does not contain or execute any scripts, binaries, or shell commands. All instructions are aimed at natural language analysis of code provided by the user.
[INDIRECT_PROMPT_INJECTION]: The skill has a defined attack surface as it is intended to process external test files provided by a user. However, there are no findings of actionable risk because the skill lacks high-privilege capabilities such as file writing, system command execution, or network exfiltration. The skill further includes limitations that explicitly instruct the agent to verify all generated code and recommendations before use, providing a layer of protection against accidental obedience to instructions embedded in analyzed data.

brooks-test