Sanitize user prompts and model responses using gws modelarmor templates.
npx skills add https://github.com/cellarwood/figurio --skill gws-modelarmor-cellarwood
Please help me install this Agent Skill. Skill: gws-modelarmor Source: https://github.com/cellarwood/figurio/tree/main/skills/gws-modelarmor Command: npx skills add https://github.com/cellarwood/figurio --skill gws-modelarmor-cellarwood
This Skill automates detection and removal of unsafe or policy-violating content from user inputs and model outputs to prevent harmful or disallowed material from reaching downstream systems.
Sanitize the user message "Please remove insults and disallowed content from this input" using the modelarmor sanitize-prompt template.
High-intent search queries and answers about installing and using this skill.
To sanitize user prompts, you apply a Model Armor template that automatically detects and removes unsafe or policy-violating content from the input before it reaches the model. This prevents disallowed material from entering your workflow.
Filtering unsafe model responses involves post-processing outputs through Model Armor to redact, normalize, or remove harmful content. This ensures model responses comply with safety policies before reaching downstream systems.
You create Model Armor templates to define consistent safety rules, then apply them to sanitize prompts and responses. This template-driven approach enforces uniform policy compliance across your content workflows.
Yes, you can inspect resources and method schemas via the gws CLI. This allows you to build correct parameters and construct safe calls when configuring CLI moderation pipelines.
Yes, Model Armor sanitizes user prompts and model responses specifically within Google Workspace integrations. It filters user-generated content to enforce safety rules and ensure policy compliance across these environments.
mirExport Google Docs and Sheets content as Markdown.
jongwonyRun Gemini prompts via CLI with model selection and approval modes.
hmj1026Validate code changes against OpenSpec delta specs and tasks.
temple-slopeSanitize prompts and responses using Google Model Armor templates.
