gws-modelarmor
OfficialFilter user-generated content for safety.
Legal & Compliance#prompt engineering#safety#filtering#content moderation#response validation#model armor
Authorgoogleworkspace
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps ensure user-generated content is safe and appropriate by filtering it through Google Model Armor.
Core Features & Use Cases
- Sanitize Prompts: Clean user prompts before they are sent to a model.
- Sanitize Responses: Filter model responses to remove potentially harmful or inappropriate content.
- Create Templates: Define custom filtering rules and templates for content moderation.
- Use Case: A customer service chatbot uses this Skill to sanitize both user queries and its own responses, preventing the spread of misinformation or offensive language.
Quick Start
Use the gws-modelarmor skill to sanitize the user prompt 'Tell me about your product'.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: gws-modelarmor Download link: https://github.com/googleworkspace/cli/archive/main.zip#gws-modelarmor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.