AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Ads Performance Analytics (Paid Media Dashboard Reading)

A discipline playbook for reading paid media dashboards without fooling yourself — attribution, reconciliation, incrementality, and a scale/hold/kill decision.

Marketing & SEOIntermediate★ 1,011⑂ 134AI score 9/10Last updated: Oct 27, 2026

What it does

  • Decodes platform-reported metrics: self-attribution bias, view-through, modeled conversions, mismatched attribution windows.
  • Gives a reconciliation pattern between platform reports and warehouse revenue, plus the correct blended-CAC formula.
  • Compares seven attribution models (last-click, first-click, linear, time-decay, U-shaped, DDA, MMM) with stage-based guidance.
  • Covers the ROAS-vs-LTV horizon trap, cohort cuts by month/channel/campaign, and statistical noise (day-of-week, seasonality, reporting lag).
  • Details incrementality testing: geo holdout, Conversion Lift, switchback, PSA tests, with expected incremental rates by channel type.
  • Ends in a 12-consideration checklist producing one of three answers: Scale / Hold / Kill.

Who it's for

  • Performance marketers, growth and agency analysts.
  • Founders building board-deck paid media metrics.
  • Data teams reconciling platform reports against warehouse truth.

Example uses

  1. "Platforms sum to 1,600 conversions but the warehouse shows 950 — where did they go?" → cross-platform double-count diagnosis and a board-safe restatement.
  2. "Retargeting shows 3.5x ROAS, should I 4x the budget?" → incrementality challenge plus a two-week geo holdout design.
  3. "Meta's ROAS beats Google's, should I shift budget?" → channel-level LTV and payback comparison that flips the decision.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/rampstackco/claude-skills/HEAD/dist/codex/.agents/skills/ads-performance-analytics/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the dist/codex/.agents/skills/ads-performance-analytics folder from the GitHub repo rampstackco/claude-skills into my ~/.claude/skills/rampstackco-ads-performance-analytics/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/rampstackco/claude-skills.git && mkdir -p ~/.claude/skills && cp -r claude-skills/dist/codex/.agents/skills/ads-performance-analytics ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/rampstackco/claude-skills.git
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r claude-skills/dist/codex/.agents/skills/ads-performance-analytics ~/.claude/skills/
  5. Confirm the bundled references/ files came along.
  6. Restart Claude Code and test with a prompt like "help me read this Meta Ads dashboard" or "compare ROAS vs LTV by channel".
View source on GitHub ↗License: MIT