Skip to content
SkillCheatSheet Sign in

gws-modelarmor

An AI agent skill from googleworkspace/cli, scored 52 out of 100 by code.

52/ 100D

Code score by group

  • Spec20/20
  • Description2/20
  • Procedure3/15
  • Done criteria0/15
  • Resources10/10
  • Scripts5/8
  • Safety7/7
  • Upkeep5/5

It loses the most points in Description (18), the group that checks whether the description says what the skill does and when to use it.

What the author says it does

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

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
googleworkspace/cli
Folder
skills/gws-modelarmor
License
Apache-2.0
GitHub stars
32,267
SKILL.md lines
44
Other files
0

Add gws-modelarmor to your agent

npx skills add googleworkspace/cli --skill gws-modelarmor

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

More skills from googleworkspace/cli

  1. recipe-create-gmail-filter

    Create a Gmail filter to automatically label, star, or categorize incoming messages.

    62C
  2. recipe-organize-drive-folder

    Create a Google Drive folder structure and move files into the right locations.

    62C
  3. recipe-compare-sheet-tabs

    Read data from two tabs in a Google Sheet to compare and identify differences.

    61C
  4. recipe-block-focus-time

    Create recurring focus time blocks on Google Calendar to protect deep work hours.

    59C
  5. recipe-schedule-recurring-event

    Create a recurring Google Calendar event with attendees.

    59C
  6. gws-docs

    Read and write Google Docs.

    58C
  7. recipe-backup-sheet-as-csv

    Export a Google Sheets spreadsheet as a CSV file for local backup or processing.

    58C
  8. recipe-batch-invite-to-event

    Add a list of attendees to an existing Google Calendar event and send notifications.

    58C

All skills in googleworkspace/cli

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.