# Gws Modelarmor

> Google Model Armor: Filter user-generated content for safety.

Source: https://skillsagentes.com/skills/googleworkspace/cli/gws-modelarmor
Repository: https://github.com/googleworkspace/cli
Author: googleworkspace
License: Apache-2.0
Updated: hace 4 meses
Context cost: 15 tok installed, 304 tok once triggered, 304 tok with every bundled file
Bundle: 1 file, 1 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add googleworkspace/cli --skill gws-modelarmor --agent claude-code
```

## What it does

- Ofrece acceso CLI a la API de Google Model Armor mediante `gws modelarmor <resource> <method> [flags]`
- Incluye comandos auxiliares para sanear prompts y respuestas de modelos, y crear plantillas
- Permite inspeccionar recursos y métodos con `gws modelarmor --help` y `gws schema modelarmor.<resource>.<method>`

## Use it when

- Necesitas filtrar contenido generado por usuarios por motivos de seguridad usando Model Armor
- Quieres sanear un prompt de usuario o una respuesta de modelo a través de una plantilla de Model Armor
- Necesitas crear una nueva plantilla de Model Armor

## What triggers it

- "Sanea este prompt de usuario con Model Armor antes de enviarlo al modelo"
- "Crea una plantilla de Model Armor para filtrar contenido inseguro"
- "Revisa la respuesta del modelo con gws modelarmor antes de mostrarla"

## Before you install

- Requiere el binario `gws` y haber leído ../gws-shared/SKILL.md para autenticación, flags globales y reglas de seguridad.

## Files

- SKILL.md — 1 KB

## SKILL.md

Reproduced verbatim from googleworkspace/cli under Apache-2.0. This section is the upstream document and is in English.

# modelarmor (v1)

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

```bash
gws modelarmor <resource> <method> [flags]
```

## Helper Commands

| Command | Description |
|---------|-------------|
| [`+sanitize-prompt`](../gws-modelarmor-sanitize-prompt/SKILL.md) | Sanitize a user prompt through a Model Armor template |
| [`+sanitize-response`](../gws-modelarmor-sanitize-response/SKILL.md) | Sanitize a model response through a Model Armor template |
| [`+create-template`](../gws-modelarmor-create-template/SKILL.md) | Create a new Model Armor template |

## Discovering Commands

Before calling any API method, inspect it:

```bash
# Browse resources and methods
gws modelarmor --help

# Inspect a method's required params, types, and defaults
gws schema modelarmor.<resource>.<method>
```

Use `gws schema` output to build your `--params` and `--json` flags.

---

Skills Agentes — https://skillsagentes.com/skills/googleworkspace/cli/gws-modelarmor