Administer IT — monitor security and configure Workspace.
47
35%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/persona-it-admin/SKILL.mdQuality
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 too terse and lacks explicit trigger guidance ('Use when...'), making it difficult for Claude to reliably select this skill from a large pool. While it names a domain and two high-level actions, it doesn't specify the platform clearly or enumerate concrete capabilities, reducing both specificity and distinctiveness.
Suggestions
Add a 'Use when...' clause with explicit trigger terms, e.g., 'Use when the user asks about Google Workspace administration, security monitoring, user management, or domain configuration.'
Specify the platform explicitly (e.g., 'Google Workspace' instead of just 'Workspace') and list more concrete actions like 'manage user accounts, set security policies, configure SSO, review audit logs, manage groups and OUs.'
Include natural keyword variations users might say, such as 'admin console', 'G Suite', 'domain settings', 'two-factor authentication', 'user provisioning'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (IT administration) and mentions two actions ('monitor security' and 'configure Workspace'), but these are fairly high-level and not comprehensive — no specific concrete sub-actions like 'manage user accounts', 'set security policies', 'audit logs', etc. | 2 / 3 |
Completeness | Provides a brief 'what' (monitor security, configure Workspace) but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is weak enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'IT', 'security', and 'Workspace', but misses many natural user terms such as 'admin console', 'Google Workspace', 'user management', 'permissions', 'SSO', 'audit', etc. | 2 / 3 |
Distinctiveness Conflict Risk | 'Workspace' provides some specificity but is ambiguous (could be Google Workspace, Slack workspace, etc.), and 'monitor security' is broad enough to overlap with other security-focused skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is concise but lacks substance. The instructions read as high-level aspirational goals rather than actionable guidance — 'monitor suspicious login activity' and 'configure Drive sharing policies' give no concrete commands, API calls, or specific procedures. For security-sensitive IT administration tasks, the absence of validation steps and concrete workflows is a significant gap.
Suggestions
Add concrete, executable commands for each instruction (e.g., specific `gws` CLI commands to review audit logs, check login activity, or configure sharing policies).
Provide a step-by-step workflow for common IT admin tasks like investigating suspicious logins, including validation checkpoints (e.g., verify findings before taking action).
Include at least one concrete example showing input and expected output for a typical IT admin operation like reviewing audit logs or modifying sharing policies.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient at under 20 lines. Every line serves a purpose with no unnecessary explanation of concepts Claude already knows. | 3 / 3 |
Actionability | The instructions are vague and abstract — 'monitor suspicious login activity,' 'configure Drive sharing policies,' and 'review audit logs' provide no concrete commands, code, or specific steps to execute these tasks. | 1 / 3 |
Workflow Clarity | The instructions are a loose collection of general directives with no clear sequencing, no validation checkpoints, and no feedback loops. For an IT admin role involving security-sensitive operations, this lacks the necessary rigor. | 1 / 3 |
Progressive Disclosure | References to utility skills and a workflow are present and clearly signaled, but the skill itself provides almost no substantive content to serve as an overview. The references to prerequisite skills are helpful but the body content is too thin to effectively guide navigation. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%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 | |
a3768d0
Table of Contents
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.