domains / families / marketing / ad-campaign-analyzer

ad-campaign-analyzer

combined

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling. Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.

When to use

• "Analyze my Google Ads performance"
• "Which ads should I kill?"
• "Is this campaign working?"
• "Where am I wasting ad spend?"
• "Optimize my Meta Ads"
• "How should I split my ad budget?"
• "Should I spend more on Google or Meta?"
• "Reallocate my ad spend across channels"

When not to use

• Aggregate platform exports support descriptive analysis but usually cannot establish causality, incrementality, or CPA significance.
• Tracking gaps, attribution windows, view-through credit, consent loss, duplicated conversions, currency, timezone, and conversion definitions can make channels non-comparable.
• Small samples, seasonality, auction dynamics, creative fatigue, and budget saturation can invalidate historical extrapolation.
• ROAS is not profit and attributed revenue is not necessarily incremental revenue.
• Benchmarks vary by market, vertical, placement, objective, and date; never invent or silently generalize one.
• Budget recommendations are hypotheses. Validate them with bounded tests, monitoring, and rollback rules before wider changes.
• The skill cannot see platform-side experiments or customer-level outcomes unless the user supplies appropriate, privacy-safe data.

Skill page

Conflict

The sickn33 copy is a re-wrapped, more cautious version of the gooseworks-ai skill, but it changes the procedure in ways that would hide a real alternative if one copy were crowned. The original prescribes concrete waste thresholds (e.g., CPA > 3x target, CTR < 50% of campaign average) and direct cut/scale/test actions, while the mirror replaces those with investigation candidates, requires sourced benchmarks, and adds data-handling and comparability constraints. The copies overlap heavily on intake, normalization, and funnel-adjusted CAC, but each has material steps the other lacks, so a combined instruction is needed.