此内容尚未提供您的语言版本,正在以英文显示。

Gws Modelarmor

技能已验证活跃

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

目的

To provide a reliable and safe way to filter user-generated content within Google Workspace applications by leveraging Google Model Armor's capabilities through a command-line interface.

功能

Filter user-generated content for safety
Sanitize prompts through Model Armor templates
Sanitize model responses through Model Armor templates
Create new Model Armor templates
Integrates with Google Workspace CLI

使用场景

Ensuring user-generated comments or posts are safe before display
Validating LLM-generated responses for harmful content
Defining custom content safety policies via templates
Automating content moderation workflows within Google Workspace

非目标

Performing moderation actions beyond content sanitization
Replacing the core functionality of Google Workspace applications
Providing AI model training or fine-tuning capabilities

Documentation

info:Configuration & parameter referenceWhile commands are documented, specific parameters and their defaults are not explicitly listed in the SKILL.md, requiring users to consult `gws schema`.

Code Execution

info:ValidationThe `gws` CLI likely handles input validation internally, but explicit validation schemas within the extension's direct code are not visible from the provided SKILL.md.

Compliance

info:GDPRThe extension filters user-generated content, which may include personal data. While Model Armor aims to sanitize, the skill itself doesn't implement additional GDPR-specific sanitization beyond what the underlying service provides.

安装

npx skills add googleworkspace/cli

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证

98 /100

1 day ago 分析

信任信号

最近提交2 days ago

GitHub 所有者 googleworkspace

星标26.2k

许可证Apache-2.0

网站developers.google.com

状态

查看源代码

类似扩展

Azure Ai Contentsafety Java

Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.

技能

microsoft