The Agent Skills Directory

[SAFE]: The skill serves as a development guide and documentation suite for creating slash commands. The content is educational and adheres to platform best practices, such as recommending the principle of least privilege for tool access.
[COMMAND_EXECUTION]: The skill documents and provides examples of bash execution using the platform's native syntax (e.g., !\git status`). These examples are contextualized within development workflows and typically use restricted tool sets (e.g., allowed-tools: Bash(git:*)`). There are no instances of arbitrary or unvalidated command execution from untrusted sources.
[SAFE]: Heuristic flags for destructive system commands in references/testing-strategies.md and references/marketplace-considerations.md are false positives. The identified commands, such as dd to create large test files and rm to clean up temporary test artifacts, are used appropriately within the context of testing and atomic operations. No commands target sensitive system directories or pose a risk of system instability.
[SAFE]: The skill teaches input validation techniques (e.g., using regex to validate environment names) and error handling, which improves the security posture of the commands developed using this guidance.

Command Development