What does this skill do, and when should you use it?
This skill uses Google Ads MCP server tools to diagnose account performance problems, including declines in conversion volume or value, low lead flow, and impression share lost to ad rank, bids, or budgets. It analyzes Google Ads data with GAQL queries across campaigns, ad groups, devices, conversion actions, and dates, and checks offline conversion upload health. When no customer ID is provided, it first discovers accessible enabled client accounts and excludes manager accounts. It is intended for troubleshooting, not campaign setup, direct conversion-event uploads, or general Google Mobile Ads SDK integration issues.
Retrieves accessible customers and filters for enabled, non-manager client accounts; uses resource metadata to confirm fields; queries campaign or ad group conversions, conversion value, cost, dates, devices, and conversion actions; retrieves search impression share and impression share lost to rank or budget; checks recent bid, budget, and targeting changes through change_event; queries offline conversion upload summaries and compares successful events, total events, and status; then reports diagnostic findings.
- An advertiser sees a sudden decline in conversions or conversion value and needs a breakdown by date, device, or conversion action.
- A marketing team sees low search impression share and needs to distinguish budget loss from ad-rank loss.
- A business owner asks why lead flow has fallen over the last few days and needs traffic separated from conversion-rate problems.
- An account using offline conversion imports stops showing a specific action or reports upload failures.
How do you install this skill?
- Confirm the MCP/API permission scope and user authorization before use; diagnostic access should not be assumed to include account modification rights.
- No standardized output or evidence-reporting format is defined, so results may require manual review.
- Service reachability, authentication, and mainland-China network availability for Google Ads MCP/API are not documented.
- The example resources, fields, and date conditions are not validated by committed tests or CI, so API-version changes may cause failures.
- Network access
- MCP Server
Google Ads MCP server
In an environment that supports skills.sh, run npx skills add google/skills and select skills/ads/google-ads-api-account-diagnostics. The README does not document other clients’ installation steps.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/google/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/ads/google-ads-api-account-diagnostics" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Diagnose why conversions dropped in my Google Ads account recently
- Determine whether lost impression share is caused by budget or ad rank.
After installation, ask prompts such as “Diagnose why conversions dropped in my Google Ads account recently” or “Determine whether lost impression share is caused by budget or ad rank.” If no customer ID is supplied, the skill first looks for accessible enabled client accounts. The source does not document client-specific triggering or Google Ads MCP server configuration.
What are this skill's strengths and limitations?
- Covers four concrete workflows: conversion loss, impression-share loss, low lead flow, and offline upload diagnostics.
- Includes account filtering rules, GAQL fields, date constraints, and API-specific gotchas.
- Explicitly directs the agent to use Google Ads MCP tools instead of custom scripts or the client library in the evaluation environment.
- The source provides no test suite, platform validation record, or accuracy evidence.
- Requires an available and authenticated Google Ads MCP server plus access to target customer accounts.
- Provides diagnostic guidance only; it does not set up campaigns or upload conversion events directly.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Google Ads Account Diagnostics this page ✓ Google · Official | 53 · Use with care | ★ 21k | 12d ago | Apache-2.0 |
| Google Cloud Agent Evaluation Flywheel ✓ Google · Official | 51 · Use with care | ★ 21k | 12d ago | Apache-2.0 |
| Google Analytics Data Reporting Assistant ✓ Google · Official | 50 · Use with care | ★ 21k | 12d ago | Apache-2.0 |
| Probability Analysis — Event Probability Analyst | 60 · Recommended | ★ 76 | 27d ago | MIT |
| Paid Ads Account Auditor | 59 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill restricts diagnostics to Google Ads MCP queries, requires ENABLED non-manager client accounts, and prohibits custom scripts, showing some permission scoping and data-isolation intent. Points are deducted because it does not specify user confirmation, OAuth/API permission scope, account-data flows, sensitive advertising-data handling, recovery, or result-disclosure controls.
The workflows cover account discovery, conversion loss, impression share, low lead flow, and offline uploads, with some GAQL constraints and field gotchas documented. Points are deducted because tool schemas, input/date validation, API error handling, field compatibility checks, and abnormal-input feedback are absent; static review also prevents higher scores.
The description clearly identifies triggers such as performance drops, low lead volume, and impression-share loss, and excludes campaign setup, direct conversion uploads, and Mobile Ads SDK integration. Points are deducted because input/output formats and additional non-fit boundaries are unspecified, Chinese support is absent, and reachability from mainland-China networks is not addressed despite reliance on Google Ads MCP/API.
The skill includes structured name, description, category, author, and version metadata, stepwise workflows, GAQL examples, repository installation instructions, an Apache-2.0 license, and an issue-support path. Points are deducted for missing skill-specific dependency setup, FAQs, known limitations, changelog, and clearly defined maintenance/update ownership.
The procedures directly target account-performance diagnosis and cover conversions, traffic, impression share, change events, and offline-upload health, so the core task is plausibly supported. Points are deducted because no final report format, causal decision criteria, completeness checks, or representative outputs are specified, and static evidence cannot prove direct usability.
The document supplies concrete resources, fields, filters, and GAQL examples, while the README, license, and repository metadata provide limited traceability. Points are deducted because there is no committed test suite, CI coverage, third-party execution evidence, or independent corroboration; the assessment is based only on static text.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →