Gws Modelarmor Create Template

Creates Google Cloud Model Armor templates for filtering AI model inputs and outputs against security threats like jailbreak attempts. You'll use this when setting up content safety guardrails for production AI applications that need to block prompt injection, harmful content, or other model abuse patterns. Ships with a jailbreak detection preset, but you can pass custom JSON configurations for specific filtering rules. The resulting templates integrate with Google's AI services to sanitize prompts before they hit your models and responses before they reach users. Essential for any customer-facing AI feature where you can't manually review every interaction.

skills.sh installs: 30.5K
GitHub stars: 32.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add googleworkspace/cli --skill gws-modelarmor-create-template --agent claude-code

Installs into .claude/skills of the current project.

Files

modelarmor +create-template

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

Create a new Model Armor template

Usage

gws modelarmor +create-template --project <PROJECT> --location <LOCATION> --template-id <ID>

Flags

Flag	Required	Default	Description
`--project`	✓	—	GCP project ID
`--location`	✓	—	GCP location (e.g. us-central1)
`--template-id`	✓	—	Template ID to create
`--preset`	—	—	Use a preset template: jailbreak
`--json`	—	—	JSON body for the template configuration (overrides --preset)

Examples

gws modelarmor +create-template --project P --location us-central1 --template-id my-tmpl --preset jailbreak
gws modelarmor +create-template --project P --location us-central1 --template-id my-tmpl --json '{...}'