The Agent Skills Directory

[SAFE]: The skill functions as a coordinator for local markdown files used as agent prompts. It reads files from ./agents/ and ~/.claude/agents/ to populate a selection menu.
[SAFE]: The skill uses the standard Agent tool to execute sub-agents. It constructs prompts by combining the content of the markdown files with a user-provided task description.
[SAFE]: No hardcoded credentials, sensitive file exfiltration, or unauthorized network operations were identified.
[SAFE]: There are no signs of obfuscation, dynamic code execution, or persistence mechanisms within the provided instructions.

team-builder