Skip to main content
Agent skill

Googleads Automation

Automate Google Ads analytics tasks via Rube MCP (Composio): list Google Ads links, run GA4 reports, check compatibility, list properties and accounts. Always search tools first for current schemas.

Get started

Get the complete skill folder, including its scripts and reference files.

This workflow depends on an external MCP integration. Check the source for the server, account access and setup it requires.

When to use this skill

Use Googleads Automation when an AI agent needs a reusable SKILL.md workflow for this job: Automate Google Ads analytics tasks via Rube MCP (Composio): list Google Ads links, run GA4 reports, check compatibility, list properties and accounts. Always search tools first for current schemas.

When not to use it

Skip Googleads Automation when the task is outside the productivity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/googleads-automation
# Save SKILL.md to ~/.claude/skills/googleads-automation/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/googleads-automation/SKILL.md. For a shared project, commit the folder at .claude/skills/googleads-automation/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Googleads Automation skill for this task: Use Googleads Automation when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

72/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
63/100
Source signals
80/100
Model compatibility evidence
  • claudeinferred

    The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Google Ads Automation via Rube MCP

Access Google Ads data through Google Analytics integration, run performance reports, list linked Ads accounts, and analyze campaign metrics using Rube MCP (Composio).

**Toolkit docs**: [composio.dev/toolkits/googleads](https://composio.dev/toolkits/googleads)

## Prerequisites - Rube MCP must be connected (RUBE_SEARCH_TOOLS available) - Active connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `google_analytics` - Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas

## Setup **Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds 2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `google_analytics` 3. If connection is not ACTIVE, follow the returned auth link to complete setup 4. Confirm connection status shows ACTIVE before running any workflows

> **Note**: Google Ads data is accessed through the Google Analytics toolkit integration. The tools below use GA4 properties linked to Google Ads accounts.

## Core Workflows

### 1. List Google Ads Links for a Property Use `GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS` to retrieve all Google Ads account links configured for a GA4 property. ``` Tool: GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS Parameters: - parent (required): Property resource name (format: "properties/{propertyId}") - pageSize: Max results (1-200, default 50) - pageToken: Pagination token ```

### 2. Run a GA4 Performance Report Use `GOOGLE_ANALYTICS_RUN_REPORT` to run customized reports with dimensions, metrics, date ranges, and filters. ``` Tool: GOOGLE_ANALYTICS_RUN_REPORT Parameters: - property (required): Property resource (format: "properties/{property_id}") - dimensions: Array of dimension objects (e.g., [{"name": "sessionCampaignName"}, {"name": "date"}]) - metrics: Array of metric objects (e.g., [{"name": "sessions"}, {"name": "totalRevenue"}]) - dateRanges: Array with startDate and endDate (e.g., [{"startDate": "2025-01-01", "endDate": "2025-01-31"}]) - dimensionFilter: Filter by dimension values - metricFilter: Filter by metric values (applied after aggregation) - orderBys: Sort results - limit: Max rows to return (1-250000) ```

### 3. Check Dimension/Metric Compatibility Use `GOOGLE_ANALYTICS_CHECK_COMPATIBILITY` to validate dimension and metric combinations before running a report. ``` Tool: GOOGLE_ANALYTICS_CHECK_COMPATIBILITY Description: Validates compatibility of chosen dimensions or metrics before running a report. Note: Call RUBE_SEARCH_TOOLS to get the full schema for this tool. ```

### 4. List GA4 Accounts Use `GOOGLE_ANALYTICS_LIST_ACCOUNTS` to enumerate all accessible Google Analytics accounts. ``` Tool: GOOGLE_ANALYTICS_LIST_ACCOUNTS Parameters: - pageSize: Max accounts to return - pageToken: Pagination token - showDeleted: Include soft-deleted accounts ```

### 5. List GA4 Properties Under an Account Use `GOOGLE_ANALYTICS_LIST_PROPERTIES` to list properties for a specific GA4 account. ``` Tool: GOOGLE_ANALYTICS_LIST_PROPERTIES Parameters: - account (required): Account resource name (format: "accounts/{account_id}") - pageSize: Max properties (1-200) - pageToken: Pagination token - showDeleted: Include trashed properties ```

### 6. Get Available Dimensions and Metrics Use `GOOGLE_ANALYTICS_GET_METADATA` to discover all available fields for building reports. ``` Tool: GOOGLE_ANALYTICS_GET_METADATA Description: Gets metadata for dimensions, metrics, and comparisons for a GA4 property. Note: Call RUBE_SEARCH_TOOLS to get the full schema for this tool. ```

## Common Patterns

- **Discover then report**: Use `GOOGLE_ANALYTICS_LIST_ACCOUNTS` to find account IDs, then `GOOGLE_ANALYTICS_LIST_PROPERTIES` to find property IDs, then `GOOGLE_ANALYTICS_RUN_REPORT` to pull data. - **Validate before querying**: Use `GOOGLE_ANALYTICS_CHECK_COMPATIBILITY` to validate dimension/metric combinations before running reports to avoid 400 errors. - **Campaign performance**: Run reports with dimensions like `sessionCampaignName`, `sessionSource`, `sessionMedium` and metrics like `sessions`, `activeUsers`, `totalRevenue`. - **Ads link discovery**: Use `GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS` to find which Google Ads accounts are linked to each GA4 property. - **Field discovery**: Use `GOOGLE_ANALYTICS_GET_METADATA` to list all available dimensions and metrics before constructing complex reports.

## Known Pitfalls

- **Dimension/metric compatibility**: The GA4 API has strict compatibility rules. Not all dimensions can be combined with all metrics. Demographic dimensions (e.g., `userAgeBracket`, `userGender`) are often incompatible with session-scoped dimensions/filters (e.g., `sessionCampaignName`, `sessionSource`). - **`dateRange` is NOT a dimension**: Do not include `dateRange` in the dimensions array. Use `date`, `dateHour`, `year`, `month`, or `week` instead. - **`exits` is NOT valid**: Neither `exits` as a dimension nor as a metric is valid in GA4. - **Property ID format**: Must be `properties/{numeric_id}` (e.g., `properties/123456789`). Do not use Google Account IDs (long OAuth IDs). - **Account ID format**: Must be `accounts/{numeric_id}` where the numeric ID is 6-10 digits. - **Filter separation**: Use `dimensionFilter` only for dimension fields and `metricFilter` only for metric fields. Mixing them will cause errors. - **Max 9 dimensions and 10 metrics** per report request.

## Quick Reference | Action | Tool | Key Parameters | |--------|------|----------------| | List Ads links | `GOOGLE_ANALYTICS_ANALYTICS_ADMIN_PROPERTIES_GOOGLE_ADS` | `parent` | | Run report | `GOOGLE_ANALYTICS_RUN_REPORT` | `property`, `dimensions`, `metrics`, `dateRanges` | | Check compatibility | `GOOGLE_ANALYTICS_CHECK_COMPATIBILITY` | (see full schema via RUBE_SEARCH_TOOLS) | | List accounts | `GOOGLE_ANALYTICS_LIST_ACCOUNTS` | `pageSize` | | List properties | `GOOGLE_ANALYTICS_LIST_PROPERTIES` | `account`, `pageSize` | | Get metadata | `GOOGLE_ANALYTICS_GET_METADATA` | (see full schema via RUBE_SEARCH_TOOLS) |

--- *Powered by [Composio](https://composio.dev)*

Intended uses

  • Use Googleads Automation when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.