# Build a Google Shopping dashboard in Claude

> Tier: recipe. Operating recipe: real tool sequence, core rules, known traps.

Builds the Get MCP Ads Google Shopping template as a Claude dashboard: Shopping KPIs against an equivalent comparison period, a brand map, top and rising brands, products spending without selling, movers and the full product table.

**Intent.** A live Shopping report by brand, product and product type that shows where the feed earns and where it burns.

## When to use

- Someone asks for a Shopping dashboard, a product or brand performance report, or a feed review they can keep in Claude.

## When not to use

- One product's figures: answer in the conversation.
- Hosts without Claude's Dashboard artifact type: answer in the conversation with the matching reports instead.

## Sources

Required: Google Ads

## Preconditions

- The organisation is on Team or Enterprise: ready-made dashboards are not offered on Free or Pro.
- The account is ticked in the dashboard, confirmed via list_accounts.

## Inputs

- `window`: Analysis window. Default: last 30 days.

## Procedure

1. Resolve the client's Google Ads account with Shopping campaigns with list_accounts.
2. Fetch the google-shopping template for that account. — tools: `get_dashboard_template`
3. Create a Dashboard artifact, write every document exactly as given in one batch, read its check, hand over with the lines given.

## Decision rules

- **When** The template is refused with PLAN_REQUIRED → **conclude** Say the dashboards come with Team and Enterprise and that only the account owner changes the plan; answer the question in the conversation meanwhile.
- **When** The account runs no Shopping or Performance Max with a feed → **conclude** Say the template needs Shopping product data and offer the Performance Max or scorecard dashboard instead.
- **When** A reader sees a source fail to load → **conclude** Their own Get MCP Ads access decides: check that their connection covers this client's workspace and that their plan includes dashboards before changing the dashboard.

## Evidence requirements

- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.

## Human approval boundary

- The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.

## Failure modes

- Editing the template's page or queries by hand loses the provenance of each figure: ask for changes by name instead.

## Output

- **Readout**: The figures, with windows and accounts named.
- **Flags**: What deserves a deeper skill or a human decision.

## Related

- Skill: [performance-max-dashboard](https://www.getmcpads.com/skills/performance-max-dashboard.md)
- Skill: [scorecard-dashboard](https://www.getmcpads.com/skills/scorecard-dashboard.md)