Individual skill
google-ads-audit
Use this skill when someone wants a Google Ads account audited or optimized at senior-media-buyer depth: Search campaigns, search terms and keywords, Shopping and product feeds, Performance Max, or keyword research. Classifies search terms into five intent tiers, separates rank pressure from budget pressure, grades Shopping SKUs (kill, downgrade, promote), gates PMax changes on maturity and asset labels, and compares PMax against Search on ROAS. Read-and-recommend only: it never changes the account, the user applies every recommendation in the Google Ads UI. Trigger phrases: Google Ads audit, wasted spend, search term report, PMax review, Shopping feed, keyword research, why is my CPC rising.
skills/aditya-sriram/google-ads-audit/SKILL.md
Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 237
- Repository last updated
- Oct 20, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ads Declared skill tag
- security Derived category
- design Derived category
- design-interface Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytesSKILL.mdcore · 57,456 bytes
Read excerpt
> Adapted from the GoMarble Paid Media Claude Skills repository (https://github.com/gomarble-ai/gomarble-ai-paid-media-claude-skills) by its author, shared under GoMarble's attribution license. Works with any data source: a connected ads MCP such as GoMarble, CSV exports, screenshots, or pasted tables.
A consolidated set of skills for analyzing and optimizing Google Ads accounts. These skills are **framework-agnostic** - the analytical logic (Q1–Q5 query tiers, auction-pressure diagnosis, PMax maturity gates, item classification) applies regardless of where the data comes from.
The skills define **what to know, what data to look for, how to interpret it, and how to recommend action**. They do not depend on any specific tool integration.
> **Read-and-recommend only.** These skills never make changes to the user's Google Ads account. Claude reads data and produces recommendations in plain language; the user applies the recommended changes themselves in the Google Ads UI.
---
## Data Sources Are Not All Equal
Data can come from four kinds of sources, but they have **very different completeness**. Some skill rules silently break on weaker sources - most notably, PMax asset performance labels and PMax search term insights are NOT in default Google Ads CSV exports. Always identify the source first and consult the **Data Source Compatibility Matrix** below before applying any rule.