agentleFS
Sign inStart free
Eugenevdm01Eugenevdm01/eugenes-meta-agent/skills/meta-ads-performance-analyst/SKILL.md

meta-ads-performance-analyst

Skill4 starsChanged 6 months agoMITView on GitHub

Analyze Meta campaign, ad set, and ad-level performance to surface winners, losers, anomalies, fatigue, and budget inefficiencies. Use when reviewing daily or weekly ad performance, diagnosing CPL spikes, or evaluating split tests.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    High-Level Review: Check overall spend pacing, account-level CPL, and ROAS/ROI if applicable.

    line 25
  2. Distinctive:

    Look for learning phase issues or audience overlap.

    line 28
  3. Distinctive:

    Check frequency metrics to spot potential ad fatigue.

    line 29
  4. Distinctive:

    If CTR is high but landing page CVR is low, investigate message match or landing page friction before changing the ad.

    line 54
  5. Distinctive:

    If frequency is high (>3-4 over a short period) and CPL is rising, recommend new creative to combat fatigue.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Meta Ads Performance Analyst

Purpose

Analyze campaign, ad set, and ad-level performance to surface winners, losers, anomalies, fatigue, and budget inefficiencies. Optimize for profitable, qualified leads and customers, not just cheap leads.

When to Use This Skill

  • Daily monitoring of active Meta ad campaigns.
  • Diagnosing sudden drops in performance or spikes in Cost Per Lead (CPL).
  • Evaluating the results of creative or audience split tests.
  • Recommending budget shifts or campaign restructuring.

Inputs Required

  • Meta Ads Manager performance data (spend, impressions, CPM, CTR, CPC, leads, CPL, etc.).
  • Downstream funnel data (landing page views, form completions, booked calls, qualified leads).
  • Current campaign structure and objectives.

Step-by-Step Workflow

  1. Data Gathering: Pull performance data from Meta Ads Manager and downstream CRM/funnel metrics.
  2. High-Level Review: Check overall spend pacing, account-level CPL, and ROAS/ROI if applicable.
  3. Campaign & Ad Set Analysis:
    • Identify which campaigns/ad sets are driving the most qualified leads.
    • Look for learning phase issues or audience overlap.
    • Check frequency metrics to spot potential ad fatigue.
  4. Ad-Level Analysis:
    • Compare CTR (all) vs. Outbound CTR to gauge link click intent.
    • Evaluate hook rate (if video) and conversion rate from click to lead.
    • Identify winning creatives and copy combinations.
  5. Downstream Quality Check:
    • Correlate Meta CPL with CRM qualified lead rate and booked call rate.
    • Flag campaigns with cheap leads but poor downstream quality.
  6. Diagnosis & Recommendations:
    • Diagnose root causes before proposing actions (e.g., is high CPL due to high CPM, low CTR, or low landing page CVR?).
    • Formulate recommendations prioritized by impact and effort.

Output Format

Provide a structured performance summary including:

  • Summary of what happened: High-level overview of performance trends.
  • Best opportunities: Areas to scale or optimize.
  • Biggest problems: Bottlenecks or inefficiencies identified.
  • Action Plan:
    • What to pause.
    • What to scale.
    • What to test next.
    • What to monitor tomorrow.

Decision Rules

  • Never optimize for low CPL at the expense of poor lead quality.
  • If CTR is high but landing page CVR is low, investigate message match or landing page friction before changing the ad.
  • If frequency is high (>3-4 over a short period) and CPL is rising, recommend new creative to combat fatigue.

Escalation Rules

Escalate to the user immediately if:

  • CPL rises sharply (>30% above target) without a clear explanation.
  • Qualified lead rate or booking rate drops significantly.
  • Meta account has delivery or policy issues.
  • Tracking or attribution appears broken.

Templates & Resources

  • checklists/daily-review.md: Checklist for daily account monitoring.
  • templates/performance-report.md: Template for summarizing findings.
  • scripts/pull-meta-data.py: (Optional) Script to pull data via Meta Marketing API.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free