Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot official · Google

gws-modelarmor — Claude Code skill: what it does, how to install

Filters user prompts and model responses for safety using Google Model Armor templates. Useful for automated content sanitization via the gws CLI.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add googleworkspace/cli --skill gws-modelarmor -a claude-code
Open on GitHub

What gws-modelarmor does

This skill connects the Google Model Armor API to your coding agent via the gws CLI. It lets the agent sanitize input prompts and clean up model responses against safety policies. You can also create new filtering templates directly from the CLI. Operations run through gws modelarmor with flags configured via JSON.

The skill requires the gws binary installed on your system. It also depends on authentication rules defined in gws-shared/SKILL.md. If that prerequisite file is missing, you can create it with gws generate-skills. You can inspect available arguments and types using gws schema modelarmor.. before making calls.

Install this if you actively manage Model Armor safety checks through Google Workspace CLI tools. Without the gws binary configured, it will not function.

What it helps with

  • sanitize user prompts using a Model Armor template
  • filter model responses for safety before returning them
  • create a new safety template in Google Model Armor
  • inspect required method parameters and defaults using gws schema

Example prompts for the agent

  • Sanitize this user prompt with the default Model Armor template
  • Create a new Model Armor template using gws
  • Show me the schema and required parameters for modelarmor methods

How to install gws-modelarmor

1Skills CLI (Vercel)

npx skills add googleworkspace/cli --skill gws-modelarmor -a claude-code

2Manually: put the files in place

~/.claude/skills/gws-modelarmor/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/gws-modelarmor/

From the same set95

The whole set →
gws-gmail official googleworkspace This skill hands your agent Gmail: send mail, read the inbox, reply in a thread. Useful when email work already runs through the gws CLI. Claude Code CX Codex Cursor +1 81,900installs gws-gmail-send official googleworkspace A skill that teaches your agent to send Gmail from the terminal: recipients, subject, body, attachments and drafts. Claude Code CX Codex Cursor +1 74,700installs gws-drive official googleworkspace This skill hands your agent Google Drive through the gws CLI: files, folders, shared drives, comments and access requests. Useful when docs move through code. Claude Code CX Codex Cursor +1 74,500installs gws-shared official googleworkspace This skill gives agents shared rules for gws CLI authentication, flags, and output formats. Use it when working with gws commands. Claude Code CX Codex Cursor +1 66,000installs gws-calendar official googleworkspace Manage Google Calendar events, access rules, and schedules through the gws CLI tool. Claude Code CX Codex Cursor +1 61,100installs gws-sheets official googleworkspace This skill lets an agent read and edit Google Sheets through the CLI. Use it when a coding workflow needs spreadsheet data or table updates. Claude Code CX Codex Cursor +1 58,800installs gws-docs official googleworkspace This skill lets an agent read and update Google Docs through gws. Use it when document changes should happen from an agent chat. Claude Code CX Codex Cursor +1 58,300installs gws-sheets-read official googleworkspace Reads cell values and sheets from Google Spreadsheets via CLI. Useful when an agent needs spreadsheet data without risk of altering it. Claude Code CX Codex Cursor +1 50,600installs

Similar

doubt-driven-development addyosmani This skill sends non-trivial decisions to a fresh-context reviewer looking for flaws. Use it before changes that are hard to undo or costly to debug later. Claude Code CX Codex Cursor +1 56,100installs git-guardrails-claude-code Matt Pocock This skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes. Claude Code 499,069installs ponytail-review DietrichGebert ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. Use it for PRs and commits. Claude Code CX Codex Cursor +1 56,300installs ponytail-audit DietrichGebert It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes. Claude Code CX Codex Cursor +1 44,800installs security-audit cloudflare Reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. Claude Code CX Codex Cursor +1 52,200installs security-and-hardening addyosmani Guides threat modeling and security checks for code that handles user input, authentication, sessions, or external services. Use it when building a feature that accepts untrusted data or reviewing code before release. Claude Code CX Codex Cursor +1 69,400installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

Questions about gws-modelarmor

How to install gws-modelarmor in Claude Code?

Run npx skills add googleworkspace/cli --skill gws-modelarmor -a claude-code in your terminal. You can also place the configuration directly into ~/.claude/skills/gws-modelarmor/SKILL.md.

What does gws-modelarmor do?

It enables safety filtering for user prompts and model outputs using Google Model Armor. It provides commands to inspect schemas and sanitize text through Model Armor templates.

What prerequisites are needed to run this skill?

You must have the gws binary installed. You also need the prerequisite file gws-shared/SKILL.md, which you can generate by running gws generate-skills.

Source text

SKILL.md · Apache-2.0 
---
name: gws-modelarmor
description: "Google Model Armor: Filter user-generated content for safety."
metadata:
  version: 0.22.5
  openclaw:
    category: "productivity"
    requires:
      bins:
        - gws
    cliHelp: "gws modelarmor --help"
---

# 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.

© googleworkspace · Apache-2.0 · googleworkspace/cli

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor