paid ads performance doctor
Diagnostic tool for analyzing paid ad performance, identifying funnel leaks, and prioritizing low-cost experiments.
$5
Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentspaid ads performance doctor
Example session with this skill installed
My Facebook Ads ROAS dropped from 3.0 to 1.2 this week. Spend: $500. Impressions: 40k. Clicks: 400. Purchases:
2. AOV is $150. Objective is conversions. What's wrong?
- Read your context and instructions
- Compiled the paid ads performance
- Generated the document
I have analyzed your Facebook Ads performance drop. The data suggests a significant breakdown in the middle of your funnel, specifically between the click and the purchase action.
1. Decision Snapshot
Current evidence supports a pause or immediate audit of the landing page and tracking setup. With a 1.0% CTR but only a 0.5% conversion rate on those clicks, the traffic is reaching the site but failing to convert, or the conversions are not being recorded.
2. Inputs & Assumptions
| Item | Value | Status |
|---|---|---|
| Platform | Meta (Facebook) | Verified |
| Ad Spend | $500 | Verified |
| ROAS | 1.2 | Calculated |
| CTR | 1.0% | Verified |
| CR (Click-to-Purchase) | 0.5% | Verified |
| Tracking Setup | Unknown | Hypothesis |
3. Analysis
| Dimension | Score 0–5 | Evidence | Why It Matters |
|---|---|---|---|
| CTR / Creative | 3 | 1.0% is average for conversion objectives. | Creative is likely not the primary failure point. |
| Conversion Rate | 1 | 0.5% is significantly below the 2-3% benchmark. | This is the primary bottleneck for ROAS. |
| CPC Quality | 2 | $1.25 CPC is standard, but intent seems low. | Traffic may be low-quality or landing page is slow. |
4. Key Risks / Gaps
- Pixel Mismatch: The drop from 3.0 to 1.2 might be a tracking failure (iOS14 issues or broken API).
- Landing Page Friction: Recent changes to the checkout flow could be killing conversions.
- Offer Fatigue: If the audience is small, you may have exhausted the high-intent segment.
5. Recommended Next Move
Primary Action: Perform a manual test purchase to verify that the Meta Pixel and Conversions API are firing correctly.
Supporting Actions:
- Check "Landing Page View" vs "Link Click" metrics to identify bounce rates.
- Compare this week's CPM to last week to see if competition spiked.
6. Validation Plan
| Question | Evidence Needed | Cheapest Test | Pass Signal | Fail Signal |
|---|---|---|---|---|
| Is tracking broken? | Event Manager logs | Test purchase | Event appears in real-time | No event recorded |
Next steps
- Run the manual purchase test immediately.
- Check your store's speed score for mobile users.
- Compare CPMs against the previous high-performance period.
paid-ads-performance-doctor.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Spending money on paid ads without knowing which lever to pull leads to wasted budget and "death by a thousand tweaks." Founders and freelancers often struggle to distinguish between a creative failure, a technical tracking issue, or a fundamental funnel break.
What it does
- Analyzes campaign data across eight dimensions including tracking reliability, CPM efficiency, and CTR response.
- Normalizes fragmented campaign inputs into a structured evidence ledger to separate facts from hypotheses.
- Scores performance from 0–5 based on objective evidence anchors rather than generic advice.
- Identifies high-impact uncertainties and proposes the cheapest possible test to validate them.
- Generates a decision-oriented recommendation that prioritizes reversible actions over large commitments.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate market benchmarks or give vague advice like "improve your creative." This skill uses a strict evidence-aware workflow that refuses to invent data, forces a multi-dimensional funnel audit, and validates tracking before suggesting spend increases.
Use cases
- Diagnosing why a previously profitable Meta or Google Ads campaign has seen a sudden ROAS drop.
- Auditing a new client's ad account to identify the highest-leverage optimization opportunities.
- Deciding whether to scale spend or pivot creative based on current funnel metrics.
Known limitations
Does not provide direct account access or automated bid changes. Requires manual input of campaign metrics. Analysis is only as accurate as the user-supplied data.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 12 days ago
- Passed all security checks, Safe to install