The Agent Skills Directory

[COMMAND_EXECUTION]: The skill generates and instructs the user to execute bash scripts. These scripts leverage standard system tools (e.g., xdg-open, gh CLI) to perform actions like opening URLs and managing repository configuration. The instructions recommend static verification and the use of ShellCheck before execution.
[DATA_EXPOSURE]: The generated scripts are designed to process credentials such as API keys. The template.sh library implements security-conscious helpers like ask_secret, which suppresses terminal echo during input, and directs persisted secrets to local .env files or authenticated GitHub Secret storage.
[SAFE]: The skill references Stripe as a legitimate example of a third-party service setup. The behavior is consistent with the stated purpose of infrastructure provisioning and environment setup, with no detection of obfuscation or unauthorized network exfiltration.

wizard