Gws Modelarmor Sanitize Response
Google Model Armor: Sanitize a model response through a Model Armor template.
Install
npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-responsegit clone --depth 1 https://github.com/googleworkspace/cli.git /tmp/cli
mkdir -p ~/.claude/skills
cp -r /tmp/cli/skills/gws-modelarmor-sanitize-response ~/.claude/skills/gws-modelarmor-sanitize-responsePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# modelarmor +sanitize-response > **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it. Sanitize a model response through a Model Armor template ## Usage ```bash gws modelarmor +sanitize-response --template <NAME> ``` ## Flags | Flag | Required | Default | Description | |------|----------|---------|-------------| | `--template` | ✓ | — | Full template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE) | | `--text` | — | — | Text content to sanitize | | `--json` | — | — | Full JSON request body (overrides --text) | ## Examples ```bash gws modelarmor +sanitize-response --template projects/P/locations/L/templates/T --text 'model output' model_cmd | gws modelarmor +sanitize-response --template ... ``` ## Tips - Use for outbound safety (model -> user). - For inbound safety (user -> model), use +sanitize-prompt. ## See Also - [gws-shared](../gws-shared/SKILL.md) — Global flags and auth - [gws-modelarmor](../gws-modelarmor/SKILL.md) — All filter user-generated content for safety commands
Details
- Skill name
gws-modelarmor-sanitize-response- Repository
- googleworkspace/cli
- Path
skills/gws-modelarmor-sanitize-response/SKILL.md- License
- Apache-2.0
- Repo updated
- 3 November 2026
FAQ
What does the Gws Modelarmor Sanitize Response skill do?
Google Model Armor: Sanitize a model response through a Model Armor template.
How do I install the Gws Modelarmor Sanitize Response skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-response. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Gws Modelarmor Sanitize Response popular?
It lives in googleworkspace/cli, which has 32,385 GitHub stars and 1,999 forks, and is included in 2 curated skill lists.
Related skills
Gws Admin Reports
32kgoogleworkspace/cli
Google Workspace Admin SDK: Audit logs and usage reports.
Gws Classroom
32kgoogleworkspace/cli
Google Classroom: Manage classes, rosters, and coursework.
Gws Drive
32kgoogleworkspace/cli
Google Drive: Manage files, folders, and shared drives.
Screenpipe Chats
22kscreenpipe/screenpipe
Search what was said in existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats, then continue or steer one exact chat when the user explicitly asks. Use for requests about finding another agent conversation, recalling what an agent said, or sending work to one.
Gws Modelarmor Sanitize Prompt
32kgoogleworkspace/cli
Google Model Armor: Sanitize a user prompt through a Model Armor template.
Plannotator Annotate
13kbacknotprop/plannotator
Open Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.