google-ads

Query, audit, and optimize Google Ads campaigns. Supports two modes: (1) API mode for bulk operations with the google-ads Python SDK, (2) attached-browser mode for users without API access. Use when asked to check ad performance, pause campaigns or keywords, find wasted spend, audit conversion tracking, or optimize Google Ads accounts.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-structured with clear workflows and genuine progressive disclosure to real reference files. The main weakness is duplicated safety/troubleshooting content that could be consolidated to tighten token use.

Suggestions

Consolidate the overlapping safety material from "Safety Boundaries", "Troubleshooting", and the "Security & Change-Control Addendum" into a single section to reduce redundancy.

Trim the audit checklist's browser paths since the same navigation is already detailed in the Browser Mode workflows.

Consider moving the full troubleshooting matrix into a reference file, keeping only the top failure modes inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with code blocks and tables, but safety guidance is repeated across "Safety Boundaries", "Troubleshooting", and the "Security & Change-Control Addendum", and the audit checklist restates browser workflow paths already covered.	2 / 3
Actionability	Provides executable GAQL queries, copy-paste Python snippets for queries and mutations, concrete browser navigation URLs, and specific filter instructions — all directly usable.	3 / 3
Workflow Clarity	Sequenced mode selection, numbered browser/API workflows, and explicit validation/confirmation checkpoints for mutating operations ("requires explicit confirmation listing impacted entities first").	3 / 3
Progressive Disclosure	Body is an overview with two clearly signaled one-level-deep references (browser-workflows.md, api-setup.md) that exist in the references folder; detail is appropriately split out.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong, third-person description that concretely enumerates capabilities, modes, and natural trigger phrases. It cleanly answers both what the skill does and when Claude should invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Query, audit, and optimize", "check ad performance, pause campaigns or keywords, find wasted spend, audit conversion tracking, or optimize" — and names both operating modes with the underlying SDK.	3 / 3
Completeness	Explicitly answers what it does (query/audit/optimize across two modes) and when to use it via an explicit "Use when asked to..." clause with multiple triggers.	3 / 3
Trigger Term Quality	The "Use when" clause surfaces natural phrasing a user would say ("check ad performance", "pause campaigns or keywords", "find wasted spend", "audit conversion tracking", "optimize Google Ads accounts").	3 / 3
Distinctiveness Conflict Risk	The Google Ads niche plus mode-specific triggers make it unlikely to fire for unrelated skills; no overlap risk with generic analytics skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 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	13 / 16 Passed

Repository: jdrhyne/agent-skills
Commit: 292843f

Reviewed: about 18 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.