菜单
Diagnose and improve Google Ads Quality Score — Expected CTR, Ad Relevance, and Landing Page Experience — to cut CPCs and lift Ad Rank. Use when CPCs look high for the vertical, impression share is capped by rank, or keywords sit at QS 5 and below.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | google-ads-quality-score |
| description | Diagnose and improve Google Ads Quality Score — Expected CTR, Ad Relevance, and Landing Page Experience — to cut CPCs and lift Ad Rank. Use when CPCs look high for the vertical, impression share is capped by rank, or keywords sit at QS 5 and below. |
Quality Score is a keyword-level 1-10 diagnostic built from three rated components: Expected CTR, Ad Relevance, and Landing Page Experience. Low QS means you pay more per click for the same position — fixing the weakest component is the cheapest CPC reduction available.
Confirm the account: list_connected_accounts.
Use run_gaql_query against keyword_view selecting ad_group_criterion.quality_info.quality_score, search_predicted_ctr, creative_quality_score (Ad Relevance), post_click_quality_score (Landing Page), plus impressions, cost, and conversions over LAST_30_DAYS. Filter to enabled keywords with meaningful impressions.
Rank the fix list by cost, not by QS: a QS 3 keyword spending $4K/month matters more than twenty QS 4 keywords spending nothing. Pull the below-average components on the highest-spend keywords first.
Rough mechanics worth knowing: Ad Rank scales with bid times quality, and actual CPC is the ad rank of the advertiser below you divided by your quality. Moving a keyword from QS 4-5 to QS 7 typically cuts its CPC on the order of 25-30% — quantify the monthly savings before recommending work.
Rewrite the RSAs: keyword in 2-3 headlines, concrete numbers and differentiators in the rest, distinct headlines with no near-duplicates. Fill every relevant asset type — sitelinks, callouts, structured snippets, images — since assets lift CTR directly. Generate variants with generate_text_ad and check what is live with get_ad_readback. Expect 2-4 weeks for the rating to move.
Restructure to tightly themed ad groups: if no headline in the ad group contains the keyword or a close synonym, the keyword is in the wrong ad group. Split mixed-intent groups (one theme per group), then write ads that name the theme. Keyword insertion helps only when the group is already tight. Expect 1-2 weeks after restructuring. Query bleed between groups is a negatives problem — see negative-keywords.
If the page needs replacing, build one with create_landing_page and ship it with publish_landing_page. This component is slowest to update — Google re-crawls on its own schedule, so allow 4-8 weeks.
Google keeps no QS history, so snapshot weekly with the same GAQL query and track impression-weighted average QS, percent of spend on QS 7+ keywords, and percent of keywords at QS 3 and below. Report movement against those, not single-keyword anecdotes.
Expand targeting without wrecking CPA — lookalike ladders, seed quality, audience layering, and exclusion hygiene across platforms. Use when a user wants to scale beyond exhausted audiences, build lookalikes, fix audience fatigue, or set up exclusion lists.
Build a post-cookie first-party data strategy — Enhanced Conversions, server-side tracking, Consent Mode v2, and activating owned data for targeting. Use when a user wants to recover lost conversion data, set up Enhanced Conversions or CAPI, implement consent mode, or plan for cookie deprecation.
Verify that ad campaigns actually target the geographies they claim — location criteria exist, presence-only matching is set, and click geography matches intent. Use when auditing campaigns, investigating cheap clicks or missing conversions, or reviewing any campaign before and after launch.
Optimize Google Shopping — product feed quality, titles, Merchant Center disapprovals, supplemental feeds, custom-label segmentation, and Shopping vs Performance Max structure. Use when Shopping impression share is low, products are disapproved, or feed titles and labels need work.
Design and run incrementality tests that measure true lift from ads — geo holdouts, platform lift studies, significance math, and iCPA decisions. Use when a user wants to know whether ads actually cause conversions, design a holdout test, or decide budget based on real lift.
Build LinkedIn Ads audiences with job title, seniority, and company targeting, ABM company lists, lookalikes, and lead gen form optimization. Use when building LinkedIn audiences, setting up ABM, choosing ad formats, optimizing lead gen forms, or estimating LinkedIn costs.
