agentleFS
gomarble-aigomarble-ai/marketing-agent/skills/meta-ads-audit/SKILL.md

meta-ads-audit

Skill15 starsChanged 37 days agoMITView on GitHub

30-day comprehensive Meta Ads health audit. Checks pixel/CAPI integrity, scans creative fatigue across the account, profiles audience-segment spend split, surfaces ROAS/CPA outliers (top + bottom decile), evaluates budget allocation efficiency, and produces a professional written report. Read-only — no changes applied. Use for quarterly reviews, new-account onboarding, or any "what's actually happening in this account" deep dive.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use meta-ads-creative.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bartlomiejborzuckiSkill

    meta-ads-creative

    Generate genuinely different creative angles, hooks, primary text, headlines, descriptions, and CTAs for Meta (Facebook/Instagram) ads, constrained by the brand's voice, banned phrases, and claims policy. Use for "write me three angles", "new ad copy", "variations on the winning ad", "creative concepts for this offer", or when a campaign build needs copy.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    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:

    If the user didn't name an account, list their connected accounts and ask which one to use.

    line 11

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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 Audit — 30 Days (Read-Only)

Comprehensive health audit of the ad account the user names. Read-only — produces analysis only, never applies changes.

If the user didn't name an account, list their connected accounts and ask which one to use.

Sections to cover

1. Tracking integrity

  • Pixel events firing in the last 30d (PageView, ViewContent, AddToCart, Purchase)
  • CAPI vs Pixel delta on Purchase events — flag if > 15% mismatch
  • Event Match Quality score per pixel
  • Recommendation: any missing events, gaps in CAPI, or low EMQ

2. Spend distribution

  • Top 5 campaigns by spend, % of total
  • Top 5 ad sets by spend within those campaigns
  • Pareto check — is 80% of spend concentrated in < 20% of entities? (healthy or risky?)

3. Performance — ROAS / CPA outliers

  • Identify campaigns in top decile of ROAS (scaling candidates)
  • Identify campaigns in bottom decile of ROAS or above-target CPA (cut candidates)
  • For each outlier: 30d trend (improving / declining / volatile)

4. Creative fatigue scan

  • Per ad: hook rate, hold rate, frequency, CTR delta vs ad-set median
  • Score each ad as Healthy / Early Warning / Fatigued / Dead
  • Surface top 10 fatigued ads with specific refresh recommendations

5. Audience segment split

  • Spend share by audience type (lookalikes, interest, broad, retargeting)
  • ROAS per audience type
  • Recommendation: is the mix balanced? Over-indexed on saturated audiences?

6. Budget allocation efficiency

  • Compare budget % to revenue % per campaign
  • Identify campaigns where budget % >> revenue % (over-funded)
  • Identify campaigns where budget % << revenue % (under-funded relative to performance)

Output format

A clean structured report. Use sections, tables for outliers, and a short Top 5 priorities section at the end.

End with: _Audit complete — no changes applied. Use this report to plan optimization passes._

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.