Skip to content
SkillModel-led658 tokens in use

Google Ads Audit

Read-only audit of Google Ads accounts covering measurement, Search, Shopping, Performance Max, Demand Gen, search terms, bidding and policy.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-google
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Google Ads Audit costs

94tokens idle
658tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure22/25
  • Examples0/15
  • Output15/15
  • Size11/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

The Google Ads audit skill reviews an account from the exports, screenshots, API results or MCP data you supply. It covers measurement, search terms and waste, account structure, keywords, creative assets, bidding and budgets, settings, eligibility and policy, and reads a GAQL notes file before building keyword or search term evidence.

It never suggests specific negative keywords without a search terms report and a business-relevance review, and it checks that an operation is really supported before recommending any change.

What You Get

  • Schema-valid findings for Google Ads controls, each tied to a supplied export, screenshot or API value
  • Search term and waste review based on real search terms evidence
  • Operation-capability notes for settings that may be immutable or unavailable
  • Unscored opportunities for beta or ineligible features

Common Use Cases

  • Auditing Search, Shopping and Performance Max campaigns
  • Reviewing a search terms report for waste
  • Checking conversion tracking and bidding setup
  • Preparing the Google slice of an all-platform audit

What Makes It Unique

It refuses to name sample, starter or commonly excluded negative keywords as a workaround when no search terms report exists, and it counts positive and negative keywords separately. It also verifies the current operation capability before recommending a removal or setting change, treating labels such as Smart Conversions as untrusted data.

Under The Hood

This is a prompt-only skill with no scripts. The agent reads the main ads contract, the Google audit reference and the GAQL notes, then works from the exports, API results or MCP data you provide, which can include GAQL queries against the Google Ads API when you have connected one. It treats account and web content as data, never instructions, calculates no final scores, and keeps every account change as a draft until the main mutation gate passes.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers