agentsclimarketplace

Google ads audit

Skill kastriasani/google-ads-skills/skills/google-ads-audit

13 Claude Code Agent Skills for Google Ads (research, planning, build, optimization, reporting) with a premium visual dashboard and a live example per skill.

Install
npx -y skills add kastriasani/google-ads-skills --skill google-ads-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Run a weighted Google Ads account-health audit and produce a prioritized fix list. Use whenever someone wants an account audit, a health check, a Google Ads review, a "what is wrong with my account" diagnosis, a quick-wins list, a Quality Score check or estimate, or a check for wasted spend, missing negatives, missing Enhanced Conversions, weak Ad Strength, or Performance Max hygiene. Trigger phrases include audit my Google Ads account, account health score, what should I fix first, find wasted spend, estimate Quality Score, grade this account, and pre-onboarding ad account audit.

SKILL.md

5.0 KB, as published. Nobody here has run it

Google Ads Account Audit

Score the account, find the landmines, and hand back a fix list ordered by impact. This skill runs a weighted health check across the six Google Ads categories, applies hard rules that the raw score can miss, and surfaces the quick wins that move the needle fastest. The output is a grade plus a ranked to-do list, not a vague "looks fine."

When to use

Reach for this skill when someone wants an account audit or health check, a pre-onboarding review of a prospect's account, a quick-wins list, a wasted-spend hunt, or a Quality Score check. If the focus is specifically the post-click experience (landing page, message match, conversion-tracking config), use google-ads-funnel; if the focus is producing a client report from the numbers, use google-ads-reporting. This skill is the diagnostic that feeds both.

Workflow

  1. Score the account. Run python3 scripts/account_health_scorer.py --demo to see the format, then audit a real account with --checks checks.json --platform google (each check is {category, check, result, severity, detail}). It returns a weighted 0-100 score, a grade band, per-category breakdown, all findings sorted by severity, and an auto-generated quick-wins list. See references/audit-rubric.md for the formula, weights, and the current Google checklist (Enhanced Conversions, negatives, search-terms review, QS >= 6, RSA

    = 3 headlines and Ad Strength, assets, Performance Max hygiene).

  2. Apply the hard rules. Scan for the combinations in references/hard-rules.md that must never co-occur - broad match + manual CPC, pageview as a primary conversion, tCPA too low on a tiny budget, duplicate conversion counting, auto-tagging off, Smart Bidding with no tracking, EEA/UK with no Consent Mode v2. Any hit is a critical finding that jumps to the top of the list regardless of the weighted score's ordering, because one landmine can invalidate an otherwise healthy average.

  3. Estimate Quality Score where it matters. For top-spend keywords or ad groups, run python3 scripts/quality_score_estimator.py --ctr above --relevance average --lp below. It estimates the 1-10 score and names the single highest-leverage fix for the weakest component. See references/quality-score.md. Lifting the weakest component is usually the cheapest way to cut CPC.

  4. Sanity-check the economics. Run python3 scripts/roas_calculator.py --spend ... --revenue ... --margin ... (or --demo) to confirm whether the account is actually profitable against break-even ROAS, and to size the cost of any wasted-spend finding.

  5. Deliver the fix list. Lead with the grade and the headline number, then critical hard-rule violations, then the quick wins (high-severity warnings that are cheap to fix), then the rest ordered by severity. Every item states what is wrong, why it matters in budget or signal terms, and the one action that fixes it.

Inputs and data sources

The skill runs standalone: hand-write the checks JSON from a manual walkthrough, or paste spend/revenue/margin numbers for the ROAS and Quality Score tools. No live connection is required.

Optional sources that deepen the audit:

  • Google Ads API / UI for the real check results: Quality Score components, search-terms report, conversion-action settings, Ad Strength, Impression Share, and Performance Max asset-group detail.
  • GA4 to verify conversion import and attribution.
  • Google Sheets / BigQuery for bulk keyword and search-term exports.

Outputs

  • A weighted 0-100 account health score with a grade and per-category breakdown.
  • A severity-ranked findings list with a separate quick-wins list.
  • Hard-rule violations flagged as critical.
  • A Quality Score estimate per key ad group with the highest-leverage fix.
  • A profitability check against break-even ROAS to size the wasted spend.

References

  • references/audit-rubric.md - the scoring formula, severity multipliers, the six Google Ads category weights, grade bands, the quick-wins rule, and the current Google checklist.
  • references/hard-rules.md - the combinations that must never co-occur and why each one wastes budget or corrupts the bidding signal.
  • references/quality-score.md - the three Quality Score components and the highest-leverage way to lift each one.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.