gws-modelarmor-sanitize-prompt

Google Model Armor: Sanitize a user prompt through a Model Armor template.

Quality

70%

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-sanitize-prompt/SKILL.md

Quality

Discovery

40%

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 identifies a clear niche product (Google Model Armor) and a specific action (sanitizing prompts), which gives it good distinctiveness. However, it lacks a 'Use when...' clause, provides only a single action without elaboration, and misses natural trigger term variations that users might employ when needing this skill.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to sanitize, filter, or validate prompts using Google Model Armor or GCP content safety features.'

Expand the capability description with additional concrete actions, e.g., 'Sanitize user prompts, evaluate prompt safety, apply Model Armor templates, and inspect sanitization results.'

Include natural trigger term variations such as 'GCP Model Armor', 'prompt filtering', 'content safety', 'input sanitization', or 'prompt moderation'.

Dimension	Reasoning	Score
Specificity	Names the domain (Google Model Armor) and one action (sanitize a user prompt through a template), but doesn't list multiple concrete actions or elaborate on what sanitization entails or what outcomes are produced.	2 / 3
Completeness	Describes what it does (sanitize a user prompt through a Model Armor template) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also quite thin, bringing it to 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Google Model Armor', 'sanitize', 'user prompt', and 'Model Armor template', but misses common variations users might say such as 'content filtering', 'prompt safety', 'input validation', or 'GCP Model Armor'.	2 / 3
Distinctiveness Conflict Risk	The description is clearly scoped to a specific Google product (Model Armor) with a distinct use case (prompt sanitization via templates), making it unlikely to conflict with other skills.	3 / 3
	Total	8 / 12 Passed

Implementation

100%

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-crafted, concise skill for a single CLI command. It provides all necessary information (flags, examples, input methods, related commands) without any bloat. The structure is clean with appropriate cross-references to shared and parent skills.

Dimension	Reasoning	Score
Conciseness	Every token earns its place. No unnecessary explanations of what Model Armor is or how sanitization works conceptually. The content is lean, assumes Claude's competence, and focuses purely on usage specifics.	3 / 3
Actionability	Provides concrete, copy-paste-ready CLI commands with clear flag descriptions, examples including piped input, and a well-structured flags table with required/default information.	3 / 3
Workflow Clarity	This is a simple single-command skill with no multi-step process or destructive operations. The single action is unambiguous, input sources are clearly specified (--text, --json, or stdin), and the distinction between sanitize-prompt and sanitize-response is noted.	3 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to the shared skill for auth/global flags and the parent modelarmor skill. Content is appropriately scoped to this single command without inlining unrelated material.	3 / 3
	Total	12 / 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 8 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.