google-ads-audit
Skill1 starsChanged 5 months agoMITView on GitHub
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.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- nowork-studio/notfair-plugintheir own version, first seen Nov 11, 2026
- oivanfelipe/claude-skillstheir own version, first seen Nov 8, 2026
- optmyzr-skills/google-ads-audittheir own version, first seen Nov 1, 2026
- irinabuht12-oss/marketing-skillstheir own version, first seen Oct 27, 2026
- tidycatc132/claude-skillstheir own version, first seen Oct 25, 2026
- thescottking/b2b-pmm-skillstheir own version, first seen Oct 25, 2026
Used with
Projects with it also use linkedin-ads-audit, meta-ads-audit and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
gmmh1Skilllinkedin-ads-audit
Perform a full LinkedIn Ads account health check. Triggers on 'audit my LinkedIn Ads account', 'is this LinkedIn account set up well', 'inherited this LinkedIn account, check it', or 'is this account ready to scale'. Broad structural review — for a specific known symptom, use linkedin-ads-optimization instead.
Also in 4 projects that use this
gmmh1Skillmeta-ads-audit
Perform a full Meta Ads account health check. Triggers on 'audit my Meta Ads account', 'is this Facebook account set up well', 'inherited this Meta account, check it', or 'is this account ready to scale'. Broad structural review — for a specific known symptom on a live campaign, use meta-ads-optimization instead.
Also in 5 projects that use this
chanktbSkillgoogle-ads-assets
Generates Google Ads creative assets shared across campaign types: responsive search ad headlines and descriptions, Performance Max asset-group copy and search themes, Demand Gen image/video briefs, and sitelinks/callouts. Enforces character limits, brand voice from account-context.yaml, and policy/ trademark safety. Use when the user says "ad copy", "headlines", "descriptions", "assets", "creative", "rsa", "asset group copy", "sitelinks", "callouts".
Also in 3 projects that use this
chrispanggSkillcontent-writer
Writing content across different platforms and styles. This skill should be used when creating blog posts, LinkedIn posts, X/Twitter threads, technical documentation, or other written content. It intelligently selects the appropriate writing style based on the platform, audience, and content type, then applies that style consistently throughout the piece.
Also in 3 projects that use this
webrenewSkillgoogle-ads
Plan, build, audit or run Google Ads search campaigns for a local service business (plumber, dentist, roofer, cleaner, lawyer, clinic) on a small budget, with the agent drafting and the owner approving every change that spends money. Use this skill for a new Google Ads account or campaign, keyword research from customer questions, match types, negative keywords, location targeting, responsive search ads and assets, landing page message match, conversion tracking from GA4 or the Google Ads tag, budgets and bidding, Local Services Ads, a weekly check, and when the user says "PPC", "Google Ads is not working", "too expensive per lead", "wasted ad spend", "search terms" or "should we run Google ads".
Also in 3 projects that use this
indranilbanerjeeSkillkeyword-research
Research keywords via the connected data source: intent, gaps. Grouping → keyword-cluster. \"what keywords should we target\"
Also in 4 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- irinabuht12-oss/marketing-skills★ 6.5ksame name
- nowork-studio/notfair-plugin★ 4.2ksame name
- nowork-studio/toprank★ 4.1ksame name
- cognyai/claude-code-marketing-skills★ 106same name
- itallstartedwithaidea/google-ads-skills★ 38same name
- optmyzr-skills/google-ads-audit★ 14same name
- chanktb/claude-google-ads★ 11same name
- advisorppc-org/advisorppc-plugin★ 1same name
- advisorppc/advisorppc-plugin★ 1same name
- 1clickreport/skills★ 0same name
5 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- google-ads-ab-testingSkill
- google-ads-ad-copySkill
- google-ads-biddingSkill
- google-ads-campaign-setupSkill
- google-ads-competitor-intelSkill
- google-ads-forecastSkill
- google-ads-funnelSkill
- google-ads-keyword-researchSkill
- google-ads-media-planSkill
- google-ads-presentationSkill
- google-ads-reportingSkill
- google-ads-researchSkill
- google-ads-roastSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Score the account: Run python3 scripts/account_health_scorer.py --demo to see the format, then audit a real account with --checks …
- Very specific: line 54
Sanity-check the economics: Run python3 scripts/roas_calculator.py --spend ...
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- Score the account. Run
python3 scripts/account_health_scorer.py --demoto 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. Seereferences/audit-rubric.mdfor 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).
- Apply the hard rules. Scan for the combinations in
references/hard-rules.mdthat 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. - 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. Seereferences/quality-score.md. Lifting the weakest component is usually the cheapest way to cut CPC. - 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. - 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

