Claude Agent Skill · by Googleworkspace

Gws Modelarmor

Google's Model Armor wrapped as a Claude skill for content safety filtering. You get sanitization commands for both user prompts and model responses, plus templ

Install
Terminal · npx
$npx skills add https://github.com/googleworkspace/cli --skill gws-modelarmor
Works with Paperclip

How Gws Modelarmor fits into a Paperclip company.

Gws Modelarmor drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md42 lines
Expand
---name: gws-modelarmordescription: "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. ```bashgws 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 methodsgws modelarmor --help # Inspect a method's required params, types, and defaultsgws schema modelarmor.<resource>.<method>``` Use `gws schema` output to build your `--params` and `--json` flags.