Skip to content
Get MCP AdsGet MCP Ads, home
Start free
skills/creative-rotation-dashboard.md

RecipeMeta Ads

Build a creative rotation dashboard in Claude

Builds the Get MCP Ads Creative rotation template as a Claude dashboard: freshness (share of spend on creatives up to 7, 14 or 30 days old) against the window before, the spend-weighted age of a spent dollar, fresh against older CPA, weekly spend by creative age, weekly freshness against CPA, and launch cohorts by week or month, for Meta, Google Demand Gen, TikTok, Snapchat and Pinterest.

IntentA live page that shows how much spend goes to new creative and what CPA does as spend moves between fresh and older creatives.

3
Steps
1
Tools
4
Rules
2
Failure modes

When to use it

Use it when

  • Someone asks how fast they refresh creative, how much spend new ads get, whether fresh creative lowers CPA, or for a creative rotation or creative age report they can keep in Claude.
  • A team that sets a creative refresh cadence and wants to watch it every week.

Do not use it when

  • Which single creative wins or tires: that is the creative analytics dashboard or creative-fatigue.
  • Hosts without Claude's Dashboard artifact type: answer in the conversation with the matching reports instead.

What it needs first

Required

Optional

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

In order. Every tool named is one the gateway ships, and links to its reference.

  1. Resolve the client's ad accounts (one per platform among Meta, Google Ads, TikTok, Snapchat and Pinterest) and workspace by name with list_accounts.

  2. Fetch the creative-rotation template for those accounts: datasets, filters, page files and hand-over.

  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

The observable condition, what it lets you conclude, and what takes the conclusion back.

  • 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

    A Google Ads account runs no Demand Gen campaign

    Conclude

    Say Google creatives here are Demand Gen ads only, and build the dashboard on the other platforms.

  • When

    Freshness and CPA move together over the weeks

    Conclude

    Describe it as an observed pattern, not proof: budget, season and audience shift in the same weeks.

  • 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 every conclusion must carry

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

Where the agent stops

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

How it goes wrong quietly

The cases where the analysis is wrong and still looks right. Read them before trusting a number.

  • Editing the template's page or queries by hand loses the provenance of each figure: ask for changes by name instead.
  • Reading a creative's age as its true age when it was already spending at the start of the history: those creatives are at least that old, and count as 60+ days.

What the answer contains

01Readout
The figures, with windows and accounts named.
02Flags
What deserves a deeper skill or a human decision.