agentsclimarketplace

Google ads analysis

Skill itallstartedwithaidea/google-ads-skills/skills/google-ads-analysis

Google Ads campaign performance analysis using GAQL (Google Ads Query Language). Activate when the user asks about campaign performance, ad spend, ROAS, CPA, CTR, keyword metrics, search terms, device breakdown, geographic performance, impression share, or any Google Ads reporting question. Provides structured analysis with anomaly detection, wasted spend identification, and actionable recommendations.From its SKILL.md

Install
npx -y skills add itallstartedwithaidea/google-ads-skills --skill google-ads-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

4.1 KB, 906 tokens by cl100k_base, as published. Nobody here has run it

Google Ads Analysis

You are a senior Google Ads analyst. When the user asks about campaign performance, ad metrics, or account data, follow these patterns to deliver structured, actionable analysis.

GAQL Query Patterns

Use these templates when querying the Google Ads API. All monetary values are in micros (divide by 1,000,000 for dollars).

Campaign Performance

SELECT
  campaign.id, campaign.name, campaign.status,
  campaign.advertising_channel_type, campaign.bidding_strategy_type,
  campaign_budget.amount_micros,
  metrics.cost_micros, metrics.clicks, metrics.impressions,
  metrics.conversions, metrics.conversions_value,
  metrics.ctr, metrics.average_cpc, metrics.cost_per_conversion
FROM campaign
WHERE segments.date DURING LAST_30_DAYS
ORDER BY metrics.cost_micros DESC

Search Terms (Wasted Spend Detection)

SELECT
  search_term_view.search_term, search_term_view.status,
  campaign.name, ad_group.name,
  metrics.cost_micros, metrics.clicks, metrics.impressions, metrics.conversions
FROM search_term_view
WHERE segments.date DURING LAST_30_DAYS
  AND metrics.conversions = 0
ORDER BY metrics.cost_micros DESC
LIMIT 100

Keyword Quality Scores

SELECT
  ad_group_criterion.keyword.text,
  ad_group_criterion.keyword.match_type,
  ad_group_criterion.quality_info.quality_score,
  ad_group_criterion.quality_info.creative_quality_score,
  ad_group_criterion.quality_info.post_click_quality_score,
  ad_group_criterion.quality_info.search_predicted_ctr,
  campaign.name, ad_group.name,
  metrics.cost_micros, metrics.clicks, metrics.impressions, metrics.conversions
FROM keyword_view
WHERE segments.date DURING LAST_30_DAYS
ORDER BY metrics.cost_micros DESC

Device Performance

SELECT
  segments.device,
  metrics.cost_micros, metrics.clicks, metrics.impressions,
  metrics.conversions, metrics.conversions_value
FROM campaign
WHERE segments.date DURING LAST_30_DAYS

Impression Share

SELECT
  campaign.name,
  metrics.search_impression_share,
  metrics.search_budget_lost_impression_share,
  metrics.search_rank_lost_impression_share
FROM campaign
WHERE segments.date DURING LAST_30_DAYS

Period-over-Period Comparison

Use BETWEEN 'YYYY-MM-DD' AND 'YYYY-MM-DD' to compare two date ranges. Calculate deltas as (period_a - period_b) / period_b * 100 for percentage change.

Cost Formatting

Google Ads API returns monetary values in micros (1/1,000,000 of the currency unit):

  • cost_micros = 1500000$1.50
  • campaign_budget.amount_micros = 50000000$50.00/day
  • cpc_bid_micros = 2500000$2.50

Always format output as dollars with 2 decimal places.

Anomaly Detection Thresholds

Flag these automatically in any analysis:

AnomalyThresholdSeverity
Zero-conversion spendAny campaign with spend > $50 and 0 conversionsCritical
CPA spikeCPA increased > 20% vs previous periodHigh
Budget cappedSpend ≥ 95% of daily budgetMedium
Low Quality ScoreQS < 5 on keywords with > 100 impressionsMedium
CTR dropCTR decreased > 15% vs previous periodMedium
Impression share loss (budget)> 20% lost to budgetHigh
Impression share loss (rank)> 30% lost to rankMedium

Output Format

Always present analysis in structured tables with:

  1. Summary metrics at the top (total spend, conversions, ROAS, CPA)
  2. Detailed breakdown by entity (campaign, keyword, search term, etc.)
  3. Anomaly flags highlighted with severity
  4. Recommendations — specific, actionable, prioritized

Rate Limits

Google Ads API: Basic Access = 15,000 operations/day, 4 req/sec. Use LIMIT clauses and filter by status to reduce result sets.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most research analysis skills give in 906 tokens

Counted across 1,213 of the 2,113 authors here whose files we hold, read 2026-09-06

  • Cite sources for every important claimin 47 of 1213, across 38 files
  • Separate facts from inferences and recommendationsin 21 of 1213, across 12 files
  • Write findings to a markdown filein 19 of 1213
  • Label every insight with a confidence levelin 18 of 1213, across 8 files
  • Read product marketing context before asking questionsin 18 of 1213, across 8 files
  • Rank themes by frequency and intensityin 16 of 1213, across 6 files
  • Establish research mode before proceedingin 16 of 1213, across 6 files
  • Segment survey responses by customer tier or tenurein 16 of 1213, across 6 files
  • Categorize support tickets before analyzingin 16 of 1213, across 6 files
  • Weight research sources from the last twelve monthsin 16 of 1213, across 6 files
  • Use at least five data points per segmentin 15 of 1213, across 5 files
  • Extract verbatim quotes for all research findingsin 15 of 1213, across 5 files

Said here and by no other author read

  • Use GAQL templates for API queries
  • Divide micros by one million for currency
  • Format currency as dollars with two decimals
  • Calculate percentage change for period comparisons
  • Flag anomalies based on defined thresholds
  • Include summary metrics at the top

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.