Ads Performance Analytics

Read paid-media dashboards honestly: attribution, reconciliation, incrementality

Tested · Works

Test report

Verdict
Tested · Works
Score
9.2/10
Tested
Jul 21, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 2a6acfd

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 21, 2026; it's queued for a re-test.

Fetched SKILL.md from dist/pi/.agents/skills/ads-performance-analytics/; frontmatter parses with name+description; spot-checked 4 of 7 reference files (attribution-model-comparison, platform-reporting-quirks, common-interpretation-failures, dashboard-reconciliation-patterns) all HTTP 200 with real substance. No security smells. Clone+copy into a temp HOME placed SKILL.md and references at the correct target. For output I built a Q3 reconciliation task (Google/Meta/LinkedIn reported 1,600 conversions, warehouse 950). Baseline computed blended CAC $62.50 from summed platform conversions and recommended SCALE the 3.5x-ROAS Meta retargeting campaign; skill-following used the warehouse denominator (950) for blended CAC $105, flagged retargeting as typically 20-40% incremental, and recommended HOLD + run a geo-holdout before scaling — a reversed, better-grounded decision.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 5/5

What Ads Performance Analytics does

A methodology skill for reading paid-media dashboards and reconciling platform-reported metrics against warehouse truth. Covers attribution models, view-through/modeled-conversion traps, multi-platform double-counting, ROAS-vs-LTV horizon, cohort analysis, statistical noise, and incrementality/geo-holdout testing. Triggers when deciding to scale/hold/kill a campaign on platform metrics, reconciling platform reports with revenue data, or evaluating agency reporting.

How to install Ads Performance Analytics

git clone --depth 1 https://github.com/rampstackco/claude-skills.git /tmp/ads-performance-analytics-src
mkdir -p ~/.claude/skills
cp -R /tmp/ads-performance-analytics-src/dist/pi/.agents/skills/ads-performance-analytics ~/.claude/skills/ads-performance-analytics
# Pure-knowledge skill: no scripts, deps, or API keys. SKILL.md + 7 reference .md files.
# Verified: lands at ~/.claude/skills/ads-performance-analytics/SKILL.md

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Ads Performance Analytics

  • /ads-performance-analytics Read paid-media dashboards honestly: attribution, reconciliation, incrementality

It also activates on plain-language prompts like these:

  • Reconcile our ROAS numbers across platforms
  • Explain this attribution discrepancy in our dashboard
  • Set up an incrementality test for this campaign

Frequently asked questions

Is the Ads Performance Analytics skill free?
Yes. The skill itself is free from rampstackco/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Ads Performance Analytics work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md from dist/pi/.agents/skills/ads-performance-analytics/; frontmatter parses with name+description; spot-checked 4 of 7 reference files (attribution-model-comparison, platform-reporting-quirks, common-interpretation-failures, dashboard-reconciliation-patterns) all HTTP 200 with real substance. No security smells. Clone+copy into a temp HOME placed SKILL.md and references at the correct target. For output I built a Q3 reconciliation task (Google/Meta/LinkedIn reported 1,600 conversions, warehouse 950). Baseline computed blended CAC $62.50 from summed platform conversions and recommended SCALE the 3.5x-ROAS Meta retargeting campaign; skill-following used the warehouse denominator (950) for blended CAC $105, flagged retargeting as typically 20-40% incremental, and recommended HOLD + run a geo-holdout before scaling — a reversed, better-grounded decision.
What is the Ads Performance Analytics SkillProof Score?
9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Ads Performance Analytics?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Ads Performance Analytics with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.