Breaks down Quality Score components for your Google Ads keywords — expected CTR, ad relevance, and landing page experience — and tells you exactly which component is dragging each keyword down, with specific fixes ranked by potential CPC impact. Platform: Google.
npx skills add https://github.com/irinabuht12-oss/marketing-skills --skill quality-score-breakdown
Breaks down Quality Score components for your Google Ads keywords — expected CTR, ad relevance, and landing page experience — and tells you exactly which component is dragging each keyword down, with specific fixes ranked by potential CPC impact.
Claude pulls your keyword-level Quality Score data along with historical QS trends, CTR benchmarks, ad copy relevance signals, and landing page metrics. It identifies which of the three components is below average for each keyword and cross-references with your actual ad copy and landing pages to pinpoint the exact issue.
You have 340 active keywords. Claude identifies 47 with Quality Score 5 or below. Of those, 28 have below-average landing page experience (mostly because 3 landing pages have slow mobile load times), 14 have below-average ad relevance (the ad groups contain too many unrelated keywords diluting relevance), and 5 have below-average expected CTR (they're in ad groups where CTR is dragged down by poor-performing ad copy variants). Fixing the 3 landing pages alone would impact 28 keywords and potentially reduce CPC by 15-25%.
This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:
https://connector.get-ryze.ai/mcpclaude mcp add ryze --transport http https://connector.get-ryze.ai/mcpSetup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
Take irinabuht12-oss/quality-score-breakdown from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.