LandingSAFE

Open-source SEO, GEO, and marketing skills for AI agents.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: google-ads-landing
description: Score and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad groups, improve Quality Score's Landing Page Experience component, or compare an ad group's messaging against its landing page. Trigger on "landing page audit", "landing page score", "landing page quality", "why is my conversion rate low", "LPX", "landing page experience", "ad to page match", or when `/google-ads-audit` surfaces a high-CTR / low-CVR ad group.
argument-hint: "<landing page URL or ad group name>"
---

## Setup

Read and follow `../shared/preamble.md` (MCP detection, account selection) and `../shared/analysis-principles.md` (evidence requirement, guardrails). Both apply throughout this skill — every dimension below is a measurement, not an opinion.

# Landing Page Scoring + Diagnostic

Google Ads campaigns fail on the landing page more often than in the auction. A great RSA that sends traffic to a slow, unfocused, or mismatched page burns budget twice — once on the click, once on the lost conversion. This skill scores landing pages on **5 weighted dimensions** and emits concrete fixes.

Only score pages that actually run ad traffic. Don't score random marketing pages. Run this on direct request, on auto-handoff from `/google-ads-audit` (high-CTR / low-CVR ad groups), when QS diagnosis flags "Landing Page Experience: Below Average", or as a preflight before `/google-ads-copy` writes new copy for a page nobody's validated.

When the question is about ad-to-page fit, high CTR / low CVR, LPX, or testing ads and landing pages together, read `references/message-chain-testing.md` before scoring. It keeps the diagnosis focused on the paid-search message chain instead of drifting into a generic web-design audit.

## Reference

- `references/scoring-rubric.md` — the 5-dimension weighted rubric, thresholds, and evidence fields. Read before scoring.
- `references/message-chain-testing.md` — query → ad → page message-chain diagnosis and ad+LP test design.
- `../manage/references/quality-score-framework.md` — only when the user's explicit goal is QS improvement.

## Phase 1: Resolve the target pages

Figure out which URLs to score. In priority order:

1. **User supplied a URL** — score that page, skip discovery.
2. **User supplied an ad group or campaign name** — retrieve the ads for that ad group or campaign using an available read capability and extract their final URLs. Normalize (strip tracking params, preserve path + query that affects routing).
3. **Auto-handoff from `/google-ads-audit`** — the handoff passes the specific ad groups flagged. Pull their final URLs the same way.
4. **No arguments** — retrieve account ad URLs and rank them by spend over an appropriate recent period, propose the top 3, ask the user to confirm.

**De-duplicate aggressively.** Many ads point to the same final URL — score each unique URL once, then map back to every ad group that uses it.

## Phase 2: Gather signal (parallel)

Do all of these in a single tool-use turn:

1. **WebFetch the landing page** — capture visible headline, subheadline, primary CTA text, form fields, trust signals, body copy tone. Capture the full HTML so we can spot script bloat and above-the-fold content.
2. **PageSpeed Insights API call** — `https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url={url}&strategy=mobile&category=performance&category=accessibility&category=best-practices&category=seo` via WebFetch. No API key needed for single-URL queries. Extract LCP, CLS, INP, TTI, performance score, and the top 3 opportunities from `lighthouseResult.audits`.
3. **Pull the referring ad copy and the ad group's conversion metrics** — retrieve headline/description text for message match and the associated clicks, conversions, and conversion rate for the impact estimate. Choose the available reads and batch them when useful.
4. **Read `{data_dir}/business-context.json`** — for brand voice, differentiators, offers, target audience. If missing, point the user to `/google-ads-audit` first. Don't guess the business.

If any single call fails, continue — note the gap in the report rather than blocking. PageSpeed Insights can rate-limit; if it does, fall back to a manual timing annotation ("PSI unavailable — could not score Page Speed") and deflate the final report's confidence rather than skipping the dimension.

## Phase 3: Score the page

Read `references/scoring-rubric.md` and score each dimension 0-100 with evidence. The dimension scores are real measurements (PageSpeed Insights numbers, word-for-word copy comparison, form field counts, etc.) — they're not artificial ratings, they're observations.

Compute the weighted composite only as an **internal reference number** for the dollar-lift formula below. Do not surface it as a letter grade. The user sees the dimension-level measurements and the estimated dollar lift — the composite is plumbing.

```
internal_composite = 0.25 * Message Match
                   + 0.25 * Page Speed
                   + 0.20 * Mobile Experience
                   + 0.15 * Trust Signals
                   + 0.15 * Form & CTA
```

**Dollar lift is the headline.** If `business-context.json.unit_economics` has `aov_usd` + `profit_margin`, compute the estimated monthly lift from raising the composite by 15 points (see `../shared/ppc-math.md`):

```
Target lift           = min(+15, 90 - internal_composite)    # cap at 90 internal
Assumed CVR lift      = target_lift / 100 * 0.5              # cap at 50% relative lift
Current conversions   = ad group conversions from last 30d
Additional conversions = current_conversions * assumed_CVR_lift
Additional revenue    = additional_conversions * AOV
Additional profit     = additional_conversions * AOV * profit_margin
```

Present the lift as `fixing this page is worth ~$X/mo in profit` — never as a guarantee. The 50% cap on CVR lift and the 15-point cap on score improveme

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.