Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Ads Performance Analytics

A discipline for reading paid media dashboards without fooling yourself — attribution, multi-platform reconciliation, ROAS vs LTV, and incrementality before you scale or kill.

Marketing & SEOIntermediate★ 865⑂ 120AI score 9/10Last updated: Sep 7, 2026

What it does

Gives Claude a data-mentor's playbook for interpreting paid media reports.

  • Nine-item checklist for a trustworthy result panel (conversion definition, attribution window, modeled-conversion share, frequency, saturation, time series)
  • Side-by-side of seven attribution models (last-click, first-click, linear, time-decay, U-shaped, DDA, MMM) plus stage-based guidance
  • Multi-platform reconciliation: why sum-of-platforms always exceeds reality, and how to compute blended CAC from the warehouse
  • ROAS vs LTV horizon trap with a worked payback example, plus cohort cuts by month, channel, and campaign
  • Incrementality methods: geo holdout, Conversion Lift/Experiments, switchback, PSA tests, with realistic incremental ranges by channel
  • Twelve recurring interpretation failures and their fixes
  • Every analysis lands on one of three answers: Scale, Hold, or Kill

Who it's for

  • Performance marketers, growth analysts, and agency-report reviewers
  • Founders who must justify budget shifts with evidence
  • Analysts building board-deck paid media metrics

Examples

  1. "Meta reports 500 conversions, the warehouse says 200 — who's right?" → explains self-attribution and walks a reconciliation procedure.
  2. "ROAS fell 20% week over week, should we kill it?" → checks noise, day-of-week, seasonality, and reporting lag before acting.
  3. "Retargeting shows 3.5x ROAS — can we 4x the budget?" → designs a geo holdout to measure real incremental lift first.

· · · 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/pi/.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 Claude Skill Mart.
Copy the dist/pi/.agents/skills/ads-performance-analytics folder from the GitHub repo rampstackco/claude-skills into my ~/.claude/skills/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/pi/.agents/skills/ads-performance-analytics ~/.claude/skills/

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

  1. Open a terminal (Terminal on macOS/Linux, Git Bash on Windows).
  2. Clone the repo: git clone https://github.com/rampstackco/claude-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy this skill only: cp -r claude-skills/dist/pi/.agents/skills/ads-performance-analytics ~/.claude/skills/
  5. Confirm both SKILL.md and the references/ folder came along.
  6. Restart Claude Code and ask something like "analyze attribution on this paid media dashboard" to trigger it.
  7. Supply real inputs (platform report exports, warehouse conversion/revenue figures) — the skill will state a data gap rather than guess.
View source on GitHub ↗License: MIT