google-ads-landing

Files (4)

• SKILL.md
• evals.json · evals/
• message-chain-testing.md · references/
• scoring-rubric.md · references/

SKILL.md (first lines)

## 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 improvement keep estimates out of fantasy territory. If `unit_economics` isn't available, skip the dollar line entirely rather than making up a number — the dimension measurements still stand on their own.

## Phase 4: Deliver the report

Max 60 lines. Lead with the dollar lift (when available) and the single biggest fix. No letter grade.

```
# Landing Page — [URL]
Ads sending traffic here: [N ad groups] · [X clicks/mo] · [$Y spent/mo] · CVR [Z%]
[If unit_economics available] **Estimated lift from top 3 fixes: ~$X/mo in profit**
[If unit_economics is missing] _(Dollar lift unavailable — no verified AOV/margin. Confirm unit economics in business-context.json for sharper estimates.)_

**Biggest leak:** [one sentence naming the dimension and the specific observation, e.g. "LCP is 5.8s on mobile — 2.8s slower than the 3s threshold that kills conversion rate."]

## Measurements
| Dimension | Measurement | Top Finding |
|-----------|-------------|-------------|
| Message Match | [word-for-word verdict: Match / Drift / Broken] | [one line citing ad H1 vs page H1] |
| Page Speed | LCP Xs · INP Xms · CLS X · PSI perf score X | [top blocking audit from Lighthouse] |
| Mobile Experience | PSI accessibility X · [mobile-specific issue count] | [one line: e.g. "No click-to-call, form below fold"] |
| Trust Signals | [review count, years in business, cert count] | [one line: e.g. "Zero named testimonials, copyright 2023"] |
| Form & CTA | [field count] fields · CTA text: "[button]" · [above/below fold] | [one line: e.g. "11 fields for a free quote"] |

## Fix First (top 3, ranked by estimated $ lift)
1. **[Action]** — est. +$X/mo · `<time_to_fix>`
   Evidence: [the actual text/number from the page or PSI audit]
2. **[Action]** — est. +$X/mo · `<time_to_fix>`
   Evidence: [...]
3. **[Action]** — est. +$X/mo · `<time_to_fix>`
   Evidence: [...]

## Message Match Detail
Ad headline: "[actual headline from top-spending ad]"
Page H1:    "[actual H1 from landing page]"
Observation: [Match / Drift / Broken] — [one-line rationale citing the specific words that match or don't]

## Handoff
[Pick one:]
- Page speed dominates the problem → "Share these fixes with your developer: [list]"
- Message mismatch dominates → "Run /google-ads-copy to rewrite ads to match the page, or update the page to match the ads"
- Form friction dominates → "Reduce form to [specific fields]. Every removed field is ~10% more conversions"
```

## Writing back to history

Append the score to `{data_dir}/landing-page-history.json` so re-audits can show deltas:

```json
{
  "pages": {
    "https://example.com/services/roofing": {
      "history": [
        {
          "date": "2026-04-14",

From Swastik023/marketing-api-automation-mcp, MIT.