google-ads
Query, audit, and optimize Google Ads campaigns. Supports two modes: (1) API mode for bulk operations with google-ads Python SDK, (2) Browser automation mode for users without API access - just attach a browser tab to ads.google.com. Use when asked to check ad performance, pause campaigns/keywords, find wasted spend, audit conversion tracking, or optimize Google Ads accounts.
93
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, includes natural trigger terms users would actually say, explicitly states when to use it, and is clearly distinguishable from other skills through its Google Ads focus and dual-mode operation details.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query, audit, and optimize', 'bulk operations', 'check ad performance', 'pause campaigns/keywords', 'find wasted spend', 'audit conversion tracking'. Also specifies two distinct operational modes with technical details. | 3 / 3 |
Completeness | Clearly answers both what (query, audit, optimize with two modes) AND when with explicit 'Use when asked to...' clause listing specific trigger scenarios like checking performance, pausing campaigns, finding wasted spend. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Google Ads', 'ad performance', 'pause campaigns', 'keywords', 'wasted spend', 'conversion tracking', 'optimize', 'ads.google.com'. These are terms users naturally use when discussing advertising tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around Google Ads specifically. The mention of 'google-ads Python SDK', 'ads.google.com', and Google Ads-specific terminology makes it unlikely to conflict with other marketing or analytics skills. | 3 / 3 |
Total | 12 / 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 strong, well-organized skill that efficiently covers two distinct operational modes with concrete, executable guidance. The content respects token budget while providing actionable code and clear workflows. The main weakness is the lack of explicit validation steps for destructive operations like pausing campaigns/keywords.
Suggestions
Add validation/confirmation steps for pause operations (e.g., 'Verify the items selected before confirming' or 'After pausing, refresh and confirm status changed to Paused')
Include a feedback loop for API mutations: check operation response for errors, verify changes took effect with a follow-up query
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, assuming Claude's competence with Google Ads concepts. No unnecessary explanations of what Google Ads is or how APIs work—jumps straight to actionable content. | 3 / 3 |
Actionability | Provides fully executable Python code for API mode, specific navigation paths for browser mode, and concrete GAQL queries. Copy-paste ready with real field names and methods. | 3 / 3 |
Workflow Clarity | Steps are clearly listed for both modes, but lacks explicit validation checkpoints. For destructive operations like pausing keywords, there's no confirmation/verification step before or after the action. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections for each mode, references to external files for detailed content (browser-workflows.md, api-setup.md), and appropriate use of tables for quick reference. Navigation is clear and one-level deep. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 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.