agentleFS
Sign inStart free
F0rger123F0rger123/claude-meta-ads-god-mode/skills/ads-audit/SKILL.md

ads-audit

Skill1 starsChanged 23 days agoMITView on GitHub

Structured ad account audits for Meta and Google Ads - structure, objectives, budgets, audiences, placements, keywords, creatives, copy, tracking, learning state, spend efficiency, fatigue, attribution and landing-page alignment, with severity, evidence, impact, confidence, action and approval flag per finding. Use for "audit", "review the account", "what's wrong with", "health check".

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ads-math, ads-test and 4 more.

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.
  • chriswesttSkill

    ads-math

    PPC financial calculator and modeling tool. CPA, ROAS, CPL calculations, break-even analysis, impression share opportunity sizing, budget forecasting, LTV:CAC ratio analysis, and MER (Marketing Efficiency Ratio) assessment. Requires zero API access. Works with pasted data from exports. Use when user says PPC math, ad calculator, break-even, budget forecast, ROAS calculator, CPA calculator, impression share, LTV CAC, or MER.

    Also in 3 projects that use this

  • chriswesttSkill

    ads-test

    A/B test design and experiment planning for paid advertising. Structured hypothesis framework, statistical significance calculator, test duration estimator, sample size calculator, and platform-specific experiment setup guides (Meta Experiments, Google Experiments, LinkedIn A/B). Use when user says A/B test, split test, experiment design, test hypothesis, statistical significance, sample size, or test duration.

    Also in 3 projects that use this

  • +4 more from chriswestt

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-only by nature. Load with ads-core and the platform skill, then follow workflows/account-audit.md with the platform checklist:

    line 8
  2. Distinctive:

    Start with tracking. If conversions are untrustworthy, say every CPA/ROAS finding below is provisional.

    line 27
  3. Distinctive:

    Never present breakdown-table averages as reasons to exclude segments (Meta breakdown effect).

    line 29

“Common” is measured: kept by at least 6 in 10 of the 13 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

Ads audit

Read-only by nature. Load with ads-core and the platform skill, then follow workflows/account-audit.md with the platform checklist:

  • Meta: skills/meta-ads/workflows/account-audit.md
  • Google: skills/google-ads/workflows/account-audit.md

Finding format (every finding, no exceptions)

[SEVERITY] Title
Evidence   : numbers, dates, entity ids/names (from data you read in this session)
Impact     : what it likely costs or blocks ($/month, leads, learning)
Confidence : HIGH | MODERATE | EXPERIMENT  (+ why, if not HIGH)
Action     : concrete next step
Approval   : yes | no   (no only for read-only follow-ups or paused drafts)

Severity: CRITICAL (money is being wasted or results are untrustworthy now: broken/duplicated tracking, spend outside service area, wrong account, disapproved core ads), HIGH (large measurable waste or blocked growth), MEDIUM (meaningful inefficiency), LOW (hygiene), OPPORTUNITY (upside, not a problem).

Rules

  • Start with tracking. If conversions are untrustworthy, say every CPA/ROAS finding below is provisional.
  • Rank findings by impact, not by checklist order. Top 3 first in an executive summary.
  • Never present breakdown-table averages as reasons to exclude segments (Meta breakdown effect).
  • Learning ad sets / new campaigns: "monitor", not verdicts.
  • Separate PLATFORM FACT vs HEURISTIC when a finding rests on a rule of thumb.
  • End with a prioritized action plan grouped: fix now (approval needed) / test next / monitor. Offer to draft the changes with adsgm plan.
  • Template: templates/optimization-report.md.

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