The Agent Skills Directory

[SAFE]: The skill defines a read-only workflow for auditing test suites, focusing on identifying flakiness and performance issues without modifying the codebase.
[SAFE]: No evidence of data exfiltration, credential harvesting, or unauthorized network operations was found. The skill relies on local reference files for its diagnostic logic.
[SAFE]: The instructions explicitly prohibit the agent from editing, deleting, or disabling tests, which mitigates risks associated with unintended modifications during analysis.

doctor