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.
npx skills add Ad-Superpowers/ad-superpowers-plugin --skill google-ads-pmax-retail-optimizergit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote 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.
[](https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-retail-optimizer)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-retail-optimizer"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-retail-optimizer/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.
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-retail-optimizer"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-pmax-retail-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.03940 |
| Opus 5.5 | $0.00045 | $0.01576 |
| Sonnet 5.5 | $0.00023 | $0.00788 |
| Haiku 4.5 | $0.00011 | $0.00394 |
Grade A, and why
google-ads-pmax-retail-optimizer 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.
How it starts
The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PMax Retail Optimizer
Specific optimizations for Performance Max campaigns with product feeds (PMax Retail). Focused on e-commerce accounts using Merchant Center feeds.
Quick Diagnostic
PMAX RETAIL HEALTH CHECK
==========================
1. Zombie Products?
-> >20% products without impressions (30d) --> ACTION NEEDED
2. Listing Group Filters set?
-> Only UNIT_INCLUDED (all) --> SUBOPTIMAL
3. Custom Labels active in feed?
-> No custom labels --> OPPORTUNITY MISSED
4. Asset group spend distribution?
-> >60% budget to 1 asset group --> REBALANCE
5. Product ROAS spread?
-> Top 20% products = 80% revenue --> SEGMENT
1. Zombie Inventory Detection
Data Retrieval
Zombie products = products with 0 impressions in the last 30 days.
-- Products WITH impressions (active products)
SELECT segments.product_title, segments.product_brand,
segments.product_type_l1, segments.product_item_id,
metrics.impressions, metrics.clicks,
metrics.cost_micros, metrics.conversions
FROM shopping_performance_view
WHERE segments.date DURING LAST_30_DAYS
ORDER BY metrics.impressions ASC
LIMIT 100
-- Total shopping performance (for zombie % calculation)
SELECT segments.product_title, metrics.impressions,
metrics.clicks, metrics.cost_micros
FROM shopping_performance_view
WHERE segments.date DURING LAST_30_DAYS
AND metrics.impressions = 0
LIMIT 200
Zombie Analysis Framework
ZOMBIE PRODUCT CLASSIFICATION
==============================
TYPE 1: Feed Quality Zombies
+-- Cause: Disapprovals, poor data quality
+-- Detection: Products with warnings/disapprovals in MC
+-- Solution: Fix feed issues (title, image, price)
+-- Impact: High -- these products CANNOT run
TYPE 2: Competition Zombies
+-- Cause: Too much competition, bids too low
+-- Detection: Product exists in feed, no disapprovals, 0 impressions
+-- Solution: Higher bids OR separate asset group with more budget
+-- Impact: Medium -- bid increase can help
TYPE 3: Low Demand Zombies
+-- Cause: Little search volume for this product
+-- Detection: Niche product, few search terms
+-- Solution: Accept OR improve titles with more popular terms
+-- Impact: Low -- sometimes there's just no demand
TYPE 4: Structural Zombies
+-- Cause: Product not in active listing group filter
+-- Detection: Product in feed but outside asset group scope
+-- Solution: Expand listing group filters
+-- Impact: High -- configuration error
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.
- 1mo ago First seen · 514 lines · 113 tokens per session scan A 58305ee6521b
google-ads-pmax-retail-optimizer is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 113 tokens to every session and 3,940 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.
Other skills, from other repositories
sealeap-amazon-ca-apparel-ads
An Amazon Canada advertising planning guide for apparel products such as coats and underwear. It combines product life-cycle stages, seasonal timing, English and French search coverage, account evidence, profitability, and inventory considerations.
sealeap-amazon-listing-optimizer
Audit, diagnose, rewrite, creatively brief, test, and safely prepare updates for Amazon product detail pages using live marketplace and product-type requirements, verified product facts, Brand Analytics, Search Query Performance, Ads search terms, customer feedback, competitor observations, and optional third-party…
ai-model-expert-1688-ecommerce-video-generation-editing
An AI tool workflow for creating and editing 1688 e-commerce videos from text, images, videos, or audio. 1688 is a Chinese online wholesale marketplace.
302-ai-alternative-ai-hive
A migration guide for teams moving between AI model API platforms, especially for image and video generation. It helps review an existing OpenAI-compatible integration and plan testing, routing, and fallback options.
ai-hive-animation-167-e6ff654
An AI-HIVE workflow for creating original 8-bit pixel-art animation or game-oriented content. It covers characters, settings, storyboards, key frames, animation clips, and checks for visual consistency and originality.
ai-hive-agentic-ocr-targeted-evidence
A document-search workflow that first finds likely pages and then uses OCR, or software that reads text from images, on only the relevant scans, tables, or small text.