The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown documentation and instructional guidelines focused on improving the stability and safety of the execution environment.
[SAFE]: It enforces security best practices by explicitly advising against dangerous command patterns, such as piping remote scripts to shells (curl | bash), using rm -rf without variable guards, and running commands without explicit timeouts.
[SAFE]: No executable code, hidden payloads, obfuscation, or unauthorized data access mechanisms were found within the skill files.
[SAFE]: The instructions provided are intended to protect the agent's operating environment (e.g., preventing terminal FD corruption) and do not attempt to bypass safety filters or exfiltrate sensitive information.

global-rules