skills.rest
vikingokft
vikingokftOFFICIAL
Explore all skills by this author →
GitHub

gws-modelarmor

Filter user-generated text and media against configurable safety policies.

Updated Jun 7, 2026
Search Tags:#integration#safety#real-time#moderation#policy#multilingual#content-filtering
One-click install
npx skills add https://github.com/vikingokft/vikingo-studio-skills --skill gws-modelarmor-vikingokft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gws-modelarmor
Source: https://github.com/vikingokft/vikingo-studio-skills/tree/main/google/gws-modelarmor
Command: npx skills add https://github.com/vikingokft/vikingo-studio-skills --skill gws-modelarmor-vikingokft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Filters user-generated content to prevent unsafe, harmful, or non-compliant posts from being published.

Core Features & Use Cases

  • Real-time moderation: Filter user-generated content across text and media using configurable safety policies.
  • Multilingual support: Enforce policies across languages and regions to maintain safe communities.
  • Audit trails: Record moderation decisions and provide integration hooks for workflows.
  • Use Case: A community forum uses Model Armor to automatically screen posts before publishing to prevent offensive content.

Quick Start

Run the gws modelarmor tool on your content resource to start filtering posts in real time.

Frequently Asked Questions about gws-modelarmor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I filter user-generated content for safety and compliance in real time?▼

Filter user-generated content by applying configurable safety policies to screen text and media before publishing. This real-time moderation prevents unsafe or non-compliant posts from appearing in forums, chat apps, and social feeds.

Can I enforce moderation policies across multiple languages for my community forum?▼

Yes, you can enforce moderation policies across multiple languages and regions. Multilingual content filtering ensures diverse community interactions remain safe and compliant with your configured rules.

What is the best way to integrate content moderation into existing workflows?▼

Integrate content moderation into existing workflows by using audit trails and integration hooks. The system records moderation decisions, providing logs that connect seamlessly with your current review processes.

Does real-time content filtering support both text and media types?▼

Yes, real-time content filtering supports both text and media types. Configurable safety policies evaluate all user-generated content formats to maintain safe community standards across platforms.

How do I record moderation decisions for audit logging?▼

Record moderation decisions for audit logging by running the content filtering tool on your resources. The system automatically generates audit trails of moderation actions for compliance tracking.

When do I need automated content moderation for social feeds?▼

You need automated content moderation for social feeds when preventing offensive or harmful posts before publishing. Real-time filtering with configurable policies ensures community safety without manual review delays.

Related Skills

Explore More Content & Communication Skills→
BjornMelinBjornMelin
5

streamdown

Render streaming Markdown with incomplete syntax handling and code highlighting.

Community
Advanced
CleanExpoCleanExpo
1

Content Moderation

Automate content filtering and safety checks for NodeJS applications.

Community
Advanced
skywatch-bskyskywatch-bsky
6

skywatch-labeling-standards

Enforce evidence-based comment structures for Ozone label moderation actions.

Official
Advanced
davidrrowleydavidrrowley

azure-ai-contentsafety-py

Detect harmful content in text and images using Azure Content Safety APIs.

Community
Intermediate