agentleFS
kastriasanikastriasani/google-ads-skills/skills/google-ads-funnel/SKILL.md

google-ads-funnel

Skill1 starsChanged 5 months agoMITView on GitHub

Audit the Google Ads post-click funnel - landing-page conversion readiness, ad-to-page message match, and conversion-tracking integrity. Use when a campaign gets clicks but few conversions, when CPA or ROAS is disappointing, when Quality Score or Landing Page Experience is low, or when someone asks to review a landing page, fix conversion tracking, check Enhanced Conversions, validate gclid or auto-tagging, audit a tracking setup, or figure out why paid traffic is not converting. Trigger phrases include landing page audit, message match, post-click, conversion tracking broken, conversions not counting, low conversion rate on ads, funnel drop-off, and improve Quality Score landing page.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the problem is upstream of the click (keywords, bids, ad copy), use the audit, bidding, or ad-copy skills instead.

    line 32
  2. Very specific:

    Diagnose where the drop-off is: Run python3 scripts/funnel_drop_analyzer.py --demo to see the format, then feed real step counts …

    line 37
  3. Very specific:

    Audit the landing page: Run python3 scripts/landing_page_audit.py --url https://...

    line 45
  4. Very specific:

    Validate conversion tracking: Run python3 scripts/conversion_tracking_checker.py --demo to see the schema, then audit the real setup with …

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Google Ads Funnel Audit

Clicks are only the start. This skill audits everything that happens after the click: whether the landing page is built to convert, whether the page keeps the promise the ad made, and whether conversion tracking is actually counting the right things. A great campaign sending traffic to a weak page or into broken tracking burns budget and lies to your bidding model.

When to use

Reach for this skill when:

  • A campaign has healthy impressions and clicks but a low conversion rate, high CPA, or weak ROAS, and you need to know whether the problem is the traffic or the post-click experience.
  • Quality Score or Landing Page Experience is rated average or below average.
  • Someone wants a landing page reviewed before launching paid traffic to it.
  • Conversion numbers look wrong, do not match GA4, or you suspect double counting, a pageview is set as a primary conversion, or Enhanced Conversions is off.
  • You are validating a new account's tracking before spending money.

If the problem is upstream of the click (keywords, bids, ad copy), use the audit, bidding, or ad-copy skills instead. This skill starts at the click.

Workflow

  1. Diagnose where the drop-off is. Run python3 scripts/funnel_drop_analyzer.py --demo to see the format, then feed real step counts (impressions, clicks, landing views, engaged, leads, conversions) via --steps steps.json or --stdin. The worst step by absolute loss is the highest revenue-impact fix. If most loss is at impression-to-click, the problem is upstream (ads/keywords); if loss is concentrated after the click, continue with this skill.
  2. Audit the landing page. Run python3 scripts/landing_page_audit.py --url https://... (or --file page.html, or --demo). The weighted 0-100 score is a proxy for Google's Landing Page Experience rating. A weak score predicts a low Quality Score, higher CPC, and lower Ad Rank. Use the score to anchor the audit and the category flags to seed Quick Wins. See references/landing-page-cro.md.
  3. Check ad-to-page message match. For each top-spending ad group, line up the query intent, the ad headline, and the page H1. Score the five match dimensions in references/message-match.md. Broken scent is usually the biggest single lever on both conversion rate and Quality Score.
  4. Validate conversion tracking. Run python3 scripts/conversion_tracking_checker.py --demo to see the schema, then audit the real setup with --config config.json. It returns severity-ranked gaps with fixes and specifically flags pageview-as-primary, Enhanced Conversions off, duplicate counting (GA4 import plus a Google Ads tag), auto-tagging/gclid off, missing Consent Mode v2 in EEA/UK, last-click attribution, and short conversion windows. See references/conversion-tracking.md. Treat critical findings as blocking: fix tracking before trusting any other number.
  5. Assemble the output. Lead with the tracking trust score (a broken tracker invalidates everything downstream), then the landing-page score, then message-match findings. Organize recommendations as Quick Wins -> High-Impact -> Test Ideas, each tied to its dimension and expected effect on conversion rate or Quality Score.

Inputs and data sources

The skill runs standalone: paste page HTML or a URL, paste funnel step counts, or hand-write the tracking-config JSON. No live integration is required.

Optional sources that sharpen the audit:

  • Google Ads API / UI for real conversion-action settings, Quality Score components, and campaign-level CPA/ROAS.
  • GA4 for funnel step counts, key events, and the import that feeds Google Ads conversions.
  • Search Console / PageSpeed Insights (CrUX) for field Core Web Vitals on the landing page.

Outputs

  • A post-click funnel breakdown with the worst step and the highest-impact fix.
  • A 0-100 Landing Page Experience proxy score with weighted category scores and prioritized Quick Wins.
  • A message-match assessment per top ad group.
  • A conversion-tracking trust score with a severity-ranked, fix-by-fix gap list.
  • A consolidated Quick Wins -> High-Impact -> Test Ideas recommendation list.

References

  • references/landing-page-cro.md - the 7-dimension landing-page audit, paid- traffic rules (single CTA, no nav, low-friction forms), and Core Web Vitals thresholds and fixes.
  • references/message-match.md - the query-to-ad-to-page scent chain, the five match dimensions, and how match lifts Quality Score.
  • references/conversion-tracking.md - Google Ads conversion setup: primary vs secondary actions, Enhanced Conversions, GA4 import vs tag, auto-tagging, data-driven vs last-click attribution, conversion windows, and Consent Mode v2.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.