Google Ads Audit
Audits your Google Ads account across Search, Shopping, Performance Max and Demand Gen, and won't suggest a negative keyword without a real search terms report behind it.
Overview
Google Ads Audit is the Google-specific worker skill in the Claude Ads suite, covering Search, Shopping, Performance Max, Demand Gen and YouTube-linked inventory in one account review.
What it covers
- Evaluates measurement, search terms/waste, account structure, keywords, creative assets, bidding/budgets, eligibility and policy.
- Never generates or illustrates specific negative keywords without a search terms report plus a business-relevance and overblocking review.
- Refuses to substitute a generic "starter" or "brand-safety" negative list as a workaround for missing evidence.
- Keeps optional, beta, premium or ineligible features unscored rather than penalizing account health.
- Returns platform health, evidence coverage, contradictions and missing inputs through the common JSON contract.
Part of Claude Ads
This skill is dispatched automatically by the main ads conductor when a Claude Ads
audit run needs Google Ads coverage. See the full
Claude Ads entry for installation and the complete platform list.
Installation
This worker skill installs automatically as part of the Claude Ads plugin, there's no separate step for it.
- Install the plugin once, from inside Claude Code:
/plugin marketplace add AgriciDaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads - This skill runs on its own whenever the
/adsconductor needs it; you don't call it directly. - See the Claude Ads entry for the full setup and platform list.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.