gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.
Install with Tessl CLI
npx tessl i github:googleworkspace/cli --skill gws-modelarmor-sanitize-prompt70
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 identifies a specific Google product and a core action but is too terse to be effective for skill selection. It lacks explicit trigger guidance ('Use when...') and doesn't explain what sanitization means or what scenarios warrant using this skill. The technical terminology may not match how users naturally request this functionality.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user needs to filter prompts for safety, check content against Google Model Armor policies, or validate inputs before sending to LLMs.'
Expand the capability description to clarify what 'sanitize' means: detecting harmful content, blocking policy violations, content moderation, etc.
Include natural user terms like 'content safety', 'prompt filtering', 'input moderation', or 'safety screening' that users might actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Model Armor) and one action (sanitize a user prompt), but lacks comprehensive detail about what sanitization entails or other capabilities. | 2 / 3 |
Completeness | Describes what it does (sanitize prompts through Model Armor) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'Google Model Armor', 'sanitize', 'prompt', and 'template' which are relevant but technical. Missing natural user terms like 'content filtering', 'safety check', 'input validation', or 'moderation'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Google Model Armor' is a specific product name which helps distinctiveness, but 'sanitize a user prompt' could overlap with other content moderation or safety-related skills. | 2 / 3 |
Total | 7 / 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 an excellent, well-crafted skill that exemplifies token efficiency and actionability. It provides everything needed to use the command without any unnecessary explanation, assumes Claude's competence, and includes helpful cross-references for context. The flag table format is clear and the examples cover common usage patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what Model Armor is or how sanitization works. Every line serves a purpose - flags, examples, and tips are all actionable. | 3 / 3 |
Actionability | Provides complete, copy-paste ready bash commands with clear flag documentation. Examples show both direct text input and stdin piping patterns. | 3 / 3 |
Workflow Clarity | This is a simple single-command skill with no multi-step process. The usage is unambiguous, and the tips section clarifies input behavior (stdin fallback) and when to use the related +sanitize-response command. | 3 / 3 |
Progressive Disclosure | Appropriately structured with clear one-level-deep references to prerequisite (gws-shared) and related commands (gws-modelarmor). Content is well-organized with distinct sections for usage, flags, examples, and tips. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Reviewed
Table of Contents
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.