gws-modelarmor-create-template

Google Model Armor: Create a new Model Armor template.

Quality

60%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/gws-modelarmor-create-template/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is very terse—it identifies the product (Google Model Armor) and a single action (create a template) but lacks a 'Use when' clause, detailed capabilities, and natural trigger terms. It would be difficult for Claude to reliably select this skill from a large pool, and it provides minimal guidance on when it should be chosen over similar skills.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create a new Model Armor template in Google Cloud, or mentions content safety policies, prompt filtering, or AI guardrails.'

Expand the capability description with more concrete actions, e.g., 'Creates a new Google Cloud Model Armor template with configurable safety filters, prompt/response inspection rules, and content moderation policies.'

Include natural trigger term variations such as 'GCP', 'content moderation', 'AI safety', 'guardrails', 'prompt filtering', and 'Model Armor template' to improve matching.

Dimension	Reasoning	Score
Specificity	Names the domain (Google Model Armor) and one action (create a new template), but does not list multiple concrete actions or elaborate on what creating a template involves.	2 / 3
Completeness	Describes what it does (create a Model Armor template) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also minimal, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Google Model Armor' and 'template', but misses common variations or related terms users might say (e.g., 'content safety', 'guardrails', 'AI safety filter', 'GCP Model Armor').	2 / 3
Distinctiveness Conflict Risk	The mention of 'Google Model Armor' is fairly specific and niche, reducing conflict risk with most other skills. However, it could overlap with other Google Cloud or Model Armor-related skills (e.g., editing or deleting templates) since it only specifies 'create' without strong distinguishing triggers.	2 / 3
	Total	7 / 12 Passed

Implementation

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, concise CLI skill that provides actionable guidance with clear flag documentation and examples. Its main weakness is the lack of explicit validation/verification steps after the write operation (e.g., confirming template creation succeeded or handling errors), which is important for a destructive/write command.

Suggestions

Add a validation step after template creation, e.g., 'Verify the template was created: `gws modelarmor +get-template --project P --location us-central1 --template-id my-tmpl`' or check the command's exit code/output for errors.

Include brief error handling guidance (e.g., what to do if the template ID already exists or if the JSON body is malformed).

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. Every section serves a purpose — usage, flags table, examples, tips, and cross-references. No unnecessary explanations of what Model Armor is or how GCP works.	3 / 3
Actionability	Provides concrete, copy-paste-ready CLI commands with clear flag descriptions. The examples show both preset and JSON usage patterns, and the flags table specifies required vs optional with defaults.	3 / 3
Workflow Clarity	This is a write/destructive command and includes a caution to confirm with the user, but lacks explicit validation steps (e.g., verify the template was created successfully, check for errors, retry logic). For a write command, missing feedback loops cap this at 2.	2 / 3
Progressive Disclosure	Clear structure with a prerequisite reference to shared skills, well-organized sections, and one-level-deep 'See Also' links to related skills. Content is appropriately scoped for this single-purpose skill.	3 / 3
	Total	11 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Repository: googleworkspace/cli
Commit: c7c6646

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.