The Agent Skills Directory

[SAFE]: The skill establishes a multi-phase orchestration pipeline (Design, Architecture, Implementation, Integration, Validation, and Sign-off) to coordinate subagents. No malicious intent, obfuscation, or data exfiltration patterns were identified.
[COMMAND_EXECUTION]: The skill configuration allows for the Bash and Task tools. These are utilized within the defined scope of game development tasks (e.g., code implementation and testing). The instructions explicitly require the agent to use AskUserQuestion for user approval at each phase transition, ensuring that any actions or code generated by subagents are reviewed by a human before proceeding.

team-combat