The Agent Skills Directory

[SAFE]: The skill utilizes the standard pulumi CLI for infrastructure management tasks, which is the intended purpose of the skill.
[SAFE]: Strong emphasis on security best practices, such as explicitly instructing the agent to use --show-secrets=false to prevent accidental exposure of sensitive configuration values.
[SAFE]: Incorporates operational safety rules that mandate using --preview-only for updates and requiring explicit human confirmation before executing destructive actions like pulumi destroy.
[SAFE]: The 'Discovery-First Pattern' reduces the risk of errors or unintended actions by ensuring the agent verifies the current state of the environment before proposing or making changes.

managing-pulumi-cloud