ppc-analyticslisted

Analyze paid-ads (PPC) performance over the ad data connected in your Coupler.io workspace — spend, impressions, clicks, CTR, CPC, CPM, conversions, CPA, ROAS — with per-platform funnel traces, an efficiency-first comparison table, brand vs non-brand splits, budget pacing, and a weekly PPC review. Use this skill when the user asks "how are my ads performing", "weekly PPC report", "why did CPA spike", "ROAS by platform", "Facebook vs Google Ads", "compare Meta and Google", "am I overspending my ad budget", "which campaigns should I scale or pause", "ad fatigue check", "blended CAC". Facebook Ads + Google Ads are first-class; other ad platforms best-effort. It never silently sums platform-reported conversions across platforms — attribution double-counts; it reports per platform and computes blended CAC from an independent source when one exists. Paid-ads deep dives only: for cross-channel marketing (email, social, SEO) use marketing-analytics; report formatting composes report-generation.
coupler-io/skills · ★ 33 · AI & Automation · score 72

Install: claude install-skill coupler-io/skills

# Paid Ads Performance Analysis (PPC) Analyze paid-ads performance across whatever ad platforms the user has connected — answering plain-language questions about ad spend, delivery, and return with grounded numbers computed from their own data. Built for marketing agencies and eCommerce businesses (business owners and marketing managers): agencies care most about cross-channel comparison and cost efficiency; eCommerce cares most about ROAS and revenue. The senior-analyst outcome: a per-platform read of the paid funnel, an efficiency-ranked platform comparison, budget pacing against plan, and an honest treatment of attribution — never a naively blended number. ## Step 0 — Context Check (pre-requisite · HARD GATE) **Before any analysis, confirm the user has connected ad data AND that the dataset has meaningful context.** This check is inlined here on purpose — it must fire even if no other skill loads. - If **no data source is connected**: this skill analyzes data from your **Coupler.io** workspace. Connect a source first — for the full source-connection and credential flow, **use the `create-dataflow` skill**. - If a source **is** connected but the dataset's **saved context is missing** (no `ai_context` beyond the raw schema — no business rules or metric definitions) → offer to run the **`generate-data-set-context`** skill first. - If a source is connected and context is present → proceed to Step 1. Never duplicate the connection/credential flow inside this skill — hand o