google-ads-pmax-search-cannibalization-detector

google-ads-pmax-search-cannibalization-detector is a skill for Claude Code from Ad-Superpowers/ad-superpowers-plugin. It costs 123 tokens per session (3,502 once invoked), scanned A, original, MIT.

A framework for checking whether Performance Max takes branded searches away from separate Search campaigns. It compares search terms, traffic, conversions, and return on ad spend between the campaigns.

In plain words
What is it for?
Use it to compare branded and non-branded results, detect falling Search traffic, and decide whether to exclude brand searches from Performance Max.
Why use it?
Performance Max may claim conversions from people already searching for a brand, making its return on ad spend look better than its added contribution. This helps reveal that overlap and assess brand exclusions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ad-superpowers plugin — 120 skills, 35 commands, 5 agents, 1 MCP server shipped together

Good fit Use it to compare branded and non-branded results, detect falling Search traffic, and decide whether to exclude brand searches from Performance Max.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ad-Superpowers/ad-superpowers-plugin --skill google-ads-pmax-search-cannibalization-detector
Clone the repo
git clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-plugin

Made for: Claude Code.

Or install ad-superpowers, the plugin that ships this one along with the rest of its 120 skills, 35 commands, 5 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for google-ads-pmax-search-cannibalization-detector

README.md
[![agentmods](https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector/github.svg)](https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector)
Your own site
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for google-ads-pmax-search-cannibalization-detector

Your own site · 80×15
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-search-cannibalization-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.03502
Opus 5.5 $0.00049 $0.01401
Sonnet 5.5 $0.00025 $0.00700
Haiku 4.5 $0.00012 $0.00350

Measured 1mo ago against content hash bb51ace0a5c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

google-ads-pmax-search-cannibalization-detector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/google-ads-pmax-search-cannibalization-detector/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PMax Search Cannibalization Detector

Framework for detecting and resolving Performance Max stealing Search campaign traffic. The #1 frustration in the PPC community -- PMax claims branded conversions making ROAS appear artificially high.

Quick Diagnosis

IS PMAX CANNIBALIZING YOUR SEARCH?
====================================

Step 1: Check PMax search terms report
        -> Many branded terms? --> PROBABLY YES

Step 2: Compare blended vs non-brand ROAS
        -> PMax ROAS 2x higher than Search? --> RED FLAG

Step 3: Check Search campaign metrics since PMax launch
        -> Search impressions/clicks dropped? --> CONFIRMED

RISK LEVELS:
+-- LOW:      <20% brand traffic in PMax search terms
+-- MEDIUM:   20-50% brand traffic -> monitor + consider exclusion
+-- HIGH:     50-70% brand traffic -> enable brand exclusion
+-- CRITICAL: >70% brand traffic -> PMax ROAS is misleading

Step 1: Data Collection

1A: PMax Search Terms Report

Use google_ads_run_gaql to retrieve PMax search terms:

SELECT campaign.name, search_term_view.search_term,
    metrics.impressions, metrics.clicks, metrics.cost_micros,
    metrics.conversions, metrics.conversions_value
FROM search_term_view
WHERE campaign.advertising_channel_type = 'PERFORMANCE_MAX'
AND segments.date DURING LAST_30_DAYS
ORDER BY metrics.impressions DESC
LIMIT 200

1B: Search Campaign Search Terms

SELECT campaign.name, search_term_view.search_term,
    metrics.impressions, metrics.clicks, metrics.cost_micros,
    metrics.conversions, metrics.conversions_value
FROM search_term_view
WHERE campaign.advertising_channel_type = 'SEARCH'
AND segments.date DURING LAST_30_DAYS
ORDER BY metrics.impressions DESC
LIMIT 200

1C: Campaign Performance per Channel Type

SELECT campaign.name, campaign.advertising_channel_type,
    campaign.status, metrics.impressions, metrics.clicks,
    metrics.cost_micros, metrics.conversions,
    metrics.conversions_value, metrics.search_impression_share
FROM campaign
WHERE segments.date DURING LAST_30_DAYS
AND campaign.status = 'ENABLED'
ORDER BY metrics.cost_micros DESC

Read the full file on GitHub · 390 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 390 lines · 123 tokens per session scan A bb51ace0a5c7

Subscribe to this mod's changes

google-ads-pmax-search-cannibalization-detector is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 123 tokens to every session and 3,502 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.

Related

Other skills, from other repositories

analytics

Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.

LuuOW/meridian-mcp · 33 tokens

creative-generate

A workflow for creating advertising images and banners from a strategy brief. It separates the main visual artwork from the accurately typeset text and produces variants for display or social formats.

logly/mureo · 131 tokens

cro-optimizer

CRO specialist that pulls live analytics data via the Humblytics MCP, analyzes conversion funnels, identifies drop-off points, and generates prioritized A/B test hypotheses. Use when analyzing conversion rates, diagnosing funnel leaks, optimizing signup flows, or creating test roadmaps. Triggers: CRO, conversion rate…

Humblytics/humblytics-marketing-skills · 76 tokens

learn

Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…

logly/mureo · 98 tokens

lead-form-create

Create a Meta Instant Form (Lead Ad form) through a one-question-at-a-time interview. Use when the user asks to create a lead form, Instant Form, CV form, or similar. The agent collects required parameters via a guided dialogue, confirms, then calls metaadsleadformscreate. Also use when the user asks in Japanese…

logly/mureo · 93 tokens

ai-hive-simulate-dn-samuel

A research and content-planning workflow that studies DN-Samuel's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.

wubin1836/ai-hive-agent-skills · 334 tokens