The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and configuration metadata. It does not include any executable scripts, binary files, or commands that would perform automated actions.
[SAFE]: The instructions explicitly include security best practices, directing the agent to keep secrets, credentials, and private data out of commands and evidence logs.
[SAFE]: The skill mandates environment cleanup, requiring the removal of any temporary instrumentation or diagnostic artifacts before the task is considered complete.

diagnosing-bugs