Google Workspace Admin SDK: Audit logs and usage reports.
55
45%
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/gws-admin-reports/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—it identifies the domain and two broad capability areas but lacks specific actions, explicit trigger guidance, and natural keyword variations. It would be difficult for Claude to confidently select this skill over others in a large skill library without a 'Use when...' clause and more concrete action descriptions.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Google Workspace admin tasks, audit logs, login activity, or generating usage reports for their organization.'
List specific concrete actions such as 'Query user login events, retrieve email activity reports, list admin actions, export compliance audit data.'
Include natural keyword variations users might say, such as 'G Suite', 'Google admin', 'admin console', 'login activity', 'user activity reports', '.google workspace logs'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Workspace Admin SDK) and two general capabilities (audit logs and usage reports), but doesn't list specific concrete actions like 'query login events', 'generate user activity reports', or 'export compliance logs'. | 2 / 3 |
Completeness | Describes what at a high level (audit logs and usage reports) 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 weak, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Google Workspace', 'Admin SDK', 'audit logs', and 'usage reports', but misses common user variations like 'G Suite', 'admin console', 'login activity', 'user reports', or 'Google admin'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Google Workspace Admin SDK' is fairly specific and narrows the domain, but 'audit logs and usage reports' could overlap with other monitoring, logging, or reporting skills without clearer scoping. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable reference structure for the Admin Reports API with good progressive disclosure via the shared skill file and schema discovery. However, it suffers from verbose API descriptions copied from Google's documentation and lacks concrete, executable examples showing common use cases like retrieving audit logs with specific parameters.
Suggestions
Trim the verbose API resource descriptions to one short sentence each, removing the repeated 'For more information' references to external Google docs.
Add 2-3 concrete executable examples showing common tasks, e.g., `gws admin-reports activities list --params '{"applicationName":"admin","userKey":"all","startTime":"2024-01-01T00:00:00Z"}'`
Add a brief workflow for the `watch`/`stop` channel lifecycle, including how to verify the watch is active and how to clean up with `channels stop`.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The API resource descriptions are verbose and repetitive, with phrases like 'For more information, see the guides for administrator and Google Drive activity reports. For more information about the activity report's parameters, see the activity parameters reference guides.' These external doc references add little value in this context and could be trimmed significantly. | 2 / 3 |
Actionability | The skill provides the CLI syntax and the `gws schema` discovery pattern, which is somewhat actionable. However, there are no concrete examples of actual commands with real parameters (e.g., listing activities for a specific application or date range), making it incomplete for copy-paste execution. | 2 / 3 |
Workflow Clarity | There's a basic two-step discovery workflow (browse help, then inspect schema), but no concrete workflow for common tasks like pulling audit logs or usage reports. For operations like `watch` (which sets up push notifications), there's no validation or cleanup guidance. | 2 / 3 |
Progressive Disclosure | The skill appropriately references the shared skill file for auth and global flags, keeps the content focused on this specific API, and uses the `gws schema` command as a discovery mechanism rather than inlining all parameter details. This is well-structured one-level-deep referencing. | 3 / 3 |
Total | 9 / 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 | |
c7c6646
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.