The Agent Skills Directory

[SAFE]: The skill is entirely documentation-based and does not contain any executable code, scripts, or automated triggers. Its primary purpose is to provide methodological guidance to an AI agent or user.
[COMMAND_EXECUTION]: The reference file references/use-method.md lists standard Linux system administration tools such as vmstat, mpstat, sar, free, iostat, ss, netstat, ip, and pidstat. These are used as informational examples for manual performance analysis and do not represent malicious or unauthorized command execution.
[PROMPT_INJECTION]: The instructions focus on engineering discipline and technical methodology. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.

performance-tuning