Ads Apple

This analyzes Apple Ads campaigns with a structured scoring system covering campaign architecture, bid health, Custom Product Pages, AdAttributionKit attribution, and budget pacing across all four placement types (Search Results, Search Tab, Today Tab, Product Pages). It walks through 25 checkpoints weighted by importance and spits out a health score with specific findings. The skill knows the latest changes like the Creative Sets deprecation, Maximize Conversions bidding launched in early 2026, and the dual attribution setup from AdAttributionKit. Use it when you need to audit an Apple Ads account or diagnose why iOS user acquisition isn't hitting benchmarks. It's opinionated about campaign structure, like keeping Search Match isolated from Exact Match keywords.

skills.sh installs: 3.9K
GitHub stars: 10.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agricidaniel/claude-ads --skill ads-apple --agent claude-code

Installs into .claude/skills of the current project.

Files

Apple Ads Audit

Procedure

Read the main ads operating contract and thinking framework.
Collect objective, conversion definition, account and campaign age, geography, date window, timezone, currency, spend, targets, and available data sources.
Read ads/references/apple-audit.md (resolve it from the plugin root, the directory that holds ads/ and skills/, or from the skills directory in a standalone install) and only the relevant shared measurement, benchmark, creative, automation, policy, and scoring references.
Normalize inputs and retain lineage to each export, screenshot, API result, or manual value.
Evaluate applicable controls covering AdServices and AdAttributionKit, attribution reconciliation, campaign and keyword structure, Search Match, placements, product pages, bids, budgets, and policy.
Separate observations, diagnoses, recommendations, opportunities, and proposed mutations. Mark uncertainty and contradictions.
Return schema-valid findings to the conductor. Do not calculate final scores in the prompt or write a shared result file.
Render a platform report only from the validated JSON run bundle.