- Home
- Skills
- E-commerce
- Meta Ads Doctor
Works with the AI Agents you already use
Meta Ads Doctor
Diagnose Meta campaign performance from verified account data, funnel quality, creative fatigue, and cost drivers.
$9.99
Meta Ads Doctor
Example session with this skill installed
Review this mock campaign: spend $4,000, 160,000 impressions, 2,400 clicks, 72 purchases, $68 average order, reported ROAS 1.22. What should we investigate before changing budgets?
- Read your context and instructions
- Compiled the meta ads doctor
Meta Ads Doctor: practical plan
Diagnosis: investigate before scaling or cutting
Quick calculations
- CPM = $4,000 / 160,000 × 1,000 = $25.00
- CTR = 2,400 / 160,000 = 1.5%
- CPC = $4,000 / 2,400 = $1.67
- Click-to-purchase rate = 72 / 2,400 = 3.0%
- Revenue from stated order value = 72 × $68 = $4,896
- Recomputed revenue/spend = 1.22, matching reported ROAS
What is still unknown
ROAS is not contribution margin. Verify discounts, returns, shipping, payment fees, repeat purchases, attribution window, view-through credit and whether purchase events deduplicate correctly. Compare platform conversions with backend orders.
Investigation order
- Check pixel/CAPI event match quality and purchase values.
- Segment results by audience, placement, device, creative and new/returning buyers.
- Compare frequency and recent CTR/conversion trends for fatigue.
- Check landing-page speed, stock, price changes and checkout errors.
- Calculate break-even ROAS from real gross margin and variable costs.
Decision rule
Do not raise budgets until tracking reconciles and marginal contribution is positive. If one segment has enough volume and stable quality, isolate it for a controlled test. Pause only clear tracking failures, policy risks or materially negative economics. Document the observation window and uncertainty.
Measurement and review
Record the baseline, source, date range, denominator and owner. Use one primary measure plus quality guardrails; compare like-for-like cohorts and disclose missing data. Treat estimates as scenarios, not observed outcomes.
Risks and controls
Check relevance, consent, disclosure, workload and downside before scaling. Keep an evidence trail, obtain human review for material commitments, and pause if trust, quality or compliance signals deteriorate.
Next steps
- Confirm the goal, audience and available capacity.
- Gather the minimum evidence for a first test.
- Assign an owner, budget and review date.
- Run a small pilot, record outcomes and decide whether to iterate, expand or stop.
Connects securely to your tools. The creator never sees your data.
About this skill
Create a practical, evidence-led Meta Ads Doctor workflow. Diagnose Meta campaign performance from verified account data, funnel quality, creative fatigue, and cost drivers. Distinguish observations from assumptions, request missing inputs, give actionable recommendations with owners and measurable outcomes, and flag uncertainty. Avoid fabricated metrics, unsupported guarantees, deceptive tactics and unnecessary personal data.
Requires manual data exports or connector access. Cannot guarantee financial outcomes or platform policy approval. Quantifying waste requires defensible evidence and user-supplied assumptions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected