ab-test-setup
Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical…
Pull Google Ads performance data and generate reports. Use when asked about ad campaign performance, keyword costs, quality scores, ROAS, conversion tracking, or ad spend analysis. Trigger phrases: "google ads", "adwords", "campaign performance", "ad spend", "quality score",
$ npx -y skills add openclaudia/openclaudia-skills --skill google-ads-report --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/google-ads-reportContext preview
The summary Claude sees to decide when to auto-load this skill.
Pull Google Ads performance data and generate reports. Use when asked about ad campaign performance, keyword costs, quality scores, ROAS, conversion tracking, or ad spend analysis. Trigger phrases: "google ads", "adwords", "campaign performance", "ad spend", "quality score",
name: google-ads-report description: > Pull Google Ads performance data and generate reports. Use when asked about ad campaign performance, keyword costs, quality scores, ROAS, conversion tracking, or ad spend analysis. Trigger phrases: "google ads", "adwords", "campaign performance", "ad spend", "quality score", "CPC report", "ROAS", "ad conversion", "keyword performance", "google ads report".
Pull campaign, keyword, and conversion data from the Google Ads API.
Requires:
Set in `.env`, `.env.local`, or `~/.claude/.env.global`.
# Same OAuth flow as other Google APIs
# Scope needed: https://www.googleapis.com/auth/adwords
echo "https://accounts.google.com/o/oauth2/v2/auth?client_id=${GOOGLE_CLIENT_ID}&redirect_uri=urn:ietf:wg:oauth:2.0:oob&scope=https://www.googleapis.com/auth/adwords&response_type=code&access_type=offline"
# Exchange code for tokens
curl -s -X POST "https://oauth2.googleapis.com/token" \
-d "code={AUTH_CODE}" \
-d "client_id=${GOOGLE_CLIENT_ID}" \
-d "client_secret=${GOOGLE_CLIENT_SECRET}" \
-d "redirect_uri=urn:ietf:wg:oauth:2.0:oob" \
-d "grant_type=authorization_code"---
Google Ads API uses GAQL (Google Ads Query Language) via REST.
POST https://googleads.googleapis.com/v17/customers/{CUSTOMER_ID}/googleAds:searchStreamHeaders:
Authorization: Bearer {ACCESS_TOKEN}
developer-token: {DEVELOPER_TOKEN}
login-customer-id: {LOGIN_CUSTOMER_ID} # Only if using manager account
Content-Type: application/json---
Overview of all campaigns with key metrics.
curl -s -X POST \
"https://googleads.googleapis.com/v17/customers/${GOOGLE_ADS_CUSTOMER_ID}:searchStream" \
-H "Authorization: Bearer ${GADS_ACCESS_TOKEN}" \
-H "developer-token: ${GOOGLE_ADS_DEVELOPER_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"query": "SELECT campaign.name, campaign.status, metrics.impressions, metrics.clicks, metrics.ctr, metrics.average_cpc, metrics.cost_micros, metrics.conversions, metrics.cost_per_conversion, metrics.conversions_value FROM campaign WHERE segments.date DURING LAST_30_DAYS AND campaign.status != REMOVED ORDER BY metrics.cost_micros DESC"
}'curl -s -X POST "..." | python3 -c "
import json, sys
data = json.load(sys.stdin)
print(f\"{'Campaign':<35} {'Status':<10} {'Impr':>8} {'Clicks':>7} {'CTR':>7} {'Avg CPC':>8} {'Cost':>10} {'Conv':>6} {'CPA':>8}\")
print('-' * 110)
for batch in data:
for row in batch.get('results', []):
c = row.get('campaign', {})
m = row.get('metrics', {})
cost = int(m.get('costMicros', 0)) / 1_000_000
cpc = int(m.get('averageCpc', 0)) / 1_000_000
cpa = float(m.get('costPerConversion', 0)) / 1_000_000 if m.get('costPerConversion') else 0
print(f\"{c.get('name',''):<35} {c.get('status',''):<10} {int(m.get('impressions',0)):>8} {int(m.get('clicks',0)):>7} {float(m.get('ctr',0))*100:>6.2f}% \${cpc:>7.2f} \${cost:>9.2f} {float(m.get('conversions',0)):>6.1f} \${cpa:>7.2f}\")
"All cost values in Google Ads API are in **micros** (1/1,000,000 of the currency unit). Divide by 1,000,000 to get the actual amount.
---
See how individual keywords perform.
curl -s -X POST \
"https://googleads.googleapis.com/v17/customers/${GOOGLE_ADS_CUSTOMER_ID}:searchStream" \
-H "Authorization: Bearer ${GADS_ACCESS_TOKEN}" \
-H "developer-token: ${GOOGLE_ADS_DEVELOPER_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"query": "SELECT ad_group_criterion.keyword.text, ad_group_criterion.keyword.match_type, ad_group_criterion.quality_info.quality_score, metrics.impressions, metrics.clicks, metrics.ctr, metrics.average_cpc, metrics.cost_micros, metrics.conversions, metrics.conversions_value FROM keyword_view WHERE segments.date DURING LAST_30_DAYS AND ad_group_criterion.status != REMOVED ORDER BY metrics.cost_micros DESC LIMIT 50"
}'curl -s -X POST \
"https://googleads.googleapis.com/v17/customers/${GOOGLE_ADS_CUSTOMER_ID}:searchStream" \
-H "Authorization: Bearer ${GADS_ACCESS_TOKEN}" \
-H "developer-token: ${GOOGLE_ADS_DEVELOPER_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"query": "SELECT ad_group_criterion.keyword.text, ad_group_criterion.quality_info.quality_score, ad_group_criterion.quality_info.creative_quality_score, ad_group_criterion.quality_info.post_click_quality_score, ad_group_criterion.quality_info.search_predicted_ctr, metrics.impressions, metrics.average_cpc FROM keyword_view WHERE ad_group_criterion.quality_info.quality_score IS NOT NULL AND segments.date DURING LAST_30_DAYS ORDER BY ad_group_criterion.quality_info.quality_score ASC LIMIT 50"
}'Quality Score Components:
---
curl -s -X POST \
"https://googleads.googleapis.com/v17/customers/${GOOGLE_ADS_CUSTOMER_ID}:searchStream" \
-H "Authorization: Bearer ${GADS_ACCESS_TOKEN}" \
-H "developer-token: ${GOOGLE_ADS_DEVELOPER_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"query": "SELECT campaign.name, ad_group.name, ad_group.status, metrics.impressions, metrics.clicks, metrics.ctr, metrics.average_cpc, metrics.cost_micros, metrics.conversions FRO77 open-source marketing skills for Claude Code, Codex, and other AI coding agents. SEO, content, email, ads, analytics, and growth.
Repo: openclaudia/openclaudia-skills
Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical…
Build and manage an affiliate marketing program. Use when the user says "affiliate program", "affiliate marketing", "affiliate partners", "referral…
Manages Ahrefs API usage in Python using `ahrefs-python` library. Use when working with SEO / marketing related tasks or with data including backlinks,…
Generate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context…
Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce…
Research and enrich B2B leads using the Apollo.io API. Use when the user says "find leads", "prospect research", "company enrichment", "find decision makers",…