Meta ads analyzer
Skill charlieviettq/awesome-agent-skill/.cursor/skills/marketing/meta-ads-analyzer
Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).
npx -y skills add charlieviettq/awesome-agent-skill --skill meta-ads-analyzerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 22 stars22 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Analyze Meta (Facebook/Instagram) ad performance—campaign structure, breakdowns, marginal vs average CPA, and scaling decisions. Analytical workflow only, not financial or legal advice. Triggers: "Meta ads", "Facebook ads", "CPA", "ROAS", "ad account", "Breakdown Effect".
SKILL.md
2.3 KB, 462 tokens by cl100k_base, as published. Nobody here has run it
Meta Ads Analyzer
Structured analysis of Meta advertising accounts. Helps interpret metrics and structure experiments; does not replace professional media buying or compliance review.
When to use
- Reviewing campaign performance or budget allocation
- Explaining CPA/ROAS changes across ad sets
- Planning scale/pause/hold decisions with data
When not to use
- Creating ad creative (out of scope)
- Legal/compliance sign-off on claims or targeting
- Non-Meta platforms (adapt patterns manually)
Core concepts
Breakdown Effect
As spend increases, average CPA often rises even when incremental (marginal) ROI is still acceptable. Compare:
- Average CPA — total spend / total conversions (blends history)
- Marginal CPA — cost of the next incremental conversion (recent window or cohort)
Do not pause winning ad sets solely because average CPA crossed a target if marginal performance remains profitable.
Analysis workflow
- Scope — date range, attribution window, conversion event
- Structure — campaign → ad set → ad; note learning phase status
- Breakdowns — placement, age, gender, device, region (one at a time)
- Trends — 7d vs prior 7d; flag sudden frequency or CPM spikes
- Recommendations — scale, hold, refresh creative, consolidate, or test
Metrics table
| Metric | Use |
|---|---|
| CPA / CPL | Efficiency vs target |
| ROAS | Revenue campaigns |
| Frequency | Creative fatigue signal |
| CTR / CPM | Top-of-funnel health |
| Conversion rate | Landing/offer fit |
Output template
## Meta ads readout
- **Period:**
- **Spend / conversions / CPA:**
- **Top performers:**
- **Underperformers:**
- **Breakdown insights:**
- **Recommended actions:** (with rationale)
- **Experiments to run:**
Disclaimer
Analytical guidance only. Verify against Meta Business Help Center and your organization's policies. Past performance does not guarantee future results.
Clean-room analytical workflow; not copied from external ad tooling.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.