- Home
- Skills
- Composiohq
- Awesome Claude Skills
- Googleads Automation
googleads-automation_skill
- Python
35.4k
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill composiohq/awesome-claude-skills --skill googleads-automation- SKILL.md6.4 KB
Overview
This skill automates Google Ads analytics workflows by using Rube MCP (Composio) to access GA4 properties linked to Google Ads. It lets you list linked Ads accounts, enumerate GA4 accounts and properties, validate dimension/metric compatibility, and run custom GA4 performance reports. The skill focuses on discovery-first patterns and safe validation before querying to prevent API errors.
How this skill works
The skill communicates with Rube MCP toolkit endpoints for Google Analytics. Always call RUBE_SEARCH_TOOLS first to retrieve current tool schemas, then manage or verify the google_analytics connection via RUBE_MANAGE_CONNECTIONS. Use the provided toolkit calls to list accounts and properties, list Google Ads links for a property, fetch metadata, validate dimension/metric compatibility, and run GA4 RunReport requests with dimensions, metrics, dateRanges, filters, and ordering.
When to use it
- When you need to discover which Google Ads accounts are linked to a GA4 property
- When running custom GA4 performance reports for campaigns, sources, or revenue
- When validating dimension/metric compatibility before issuing heavy queries
- When enumerating accessible GA4 accounts and properties for automated workflows
- When building dynamic reports and you need available metadata (dimensions/metrics)
Best practices
- Always call RUBE_SEARCH_TOOLS at the start to fetch up-to-date tool schemas
- Verify the google_analytics connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before running workflows
- Use GOOGLE_ANALYTICS_GET_METADATA to discover available fields before building reports
- Validate combinations with GOOGLE_ANALYTICS_CHECK_COMPATIBILITY to avoid 400 errors
- Limit requests to GA4 constraints: max 9 dimensions and 10 metrics per report
Example use cases
- List Google Ads links for a property to confirm which Ad accounts feed campaign data into GA4
- Run a campaign performance report (sessionCampaignName, date) with sessions and revenue for a date range
- Validate that demographic dimensions can be combined with chosen metrics before running a report
- Automate a nightly job that enumerates accounts, lists properties, and pulls top-performing campaigns
- Fetch GA4 metadata to power a UI that helps non-experts build valid analytics queries
FAQ
No API keys are required; add the MCP server endpoint (https://rube.app/mcp) to your client configuration and authenticate connections via RUBE_MANAGE_CONNECTIONS.
How do I avoid invalid dimension/metric combinations?
Call GOOGLE_ANALYTICS_CHECK_COMPATIBILITY or fetch property metadata with GOOGLE_ANALYTICS_GET_METADATA before running reports to validate allowed combinations.