The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection (the !command syntax) to execute shell commands during the loading phase. These commands (find and git remote -v) are used neutrally to detect the repository's stack, configuration files, and remote origins without performing unauthorized modifications or exfiltration.
[EXTERNAL_DOWNLOADS]: The skill facilitates enrollment in the laurigates/claude-plugins marketplace. This configuration step allows the repository to interact with external plugins provided by the vendor to extend agent capabilities.

configure-repo