agentleFS
Sign inStart free
HainrixzHainrixz/claude-ads/skills/ads-audit/SKILL.md

ads-audit

Skill102 starsChanged 6 months agoMITView on GitHub

Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Use when user says audit, full ad check, analyze my ads, account health check, or PPC audit.

13 other projects use a version of this, 8 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 2

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    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. Distinctive:

    Validate: verify each subagent returned valid scores with required fields before aggregating

    line 20
  2. Common:

    Ask the user for available data.

    line 26
  3. Common:

    If no exports available, audit from screenshots or manual data entry.

    line 31
  4. Very specific:

    Read ads/references/scoring-system.md for full algorithm.

    line 35

“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
<!-- Portions Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) - see LICENSE for original authors · tododeia.com · id er-fd4fa55b -->

Full Multi-Platform Ads Audit

Process

  1. Collect account data: request exports, screenshots, or API access
  2. Validate: confirm at least one platform's data is available before proceeding
  3. Detect business type: analyze account signals per ads orchestrator
  4. Identify active platforms: determine which platforms are in use
  5. Delegate to subagents (3 parallel deep specialists, one per platform):
    • audit-google: Conversion tracking, wasted spend, structure, keywords, ads, settings, PMax, AI Max, Demand Gen, CTV, YouTube video campaigns (G01-G74, G-PM*, G-AI*, G-DG*, G-CTV*)
    • audit-meta: Pixel/CAPI health, creative fatigue, structure, audience, Andromeda, Advantage+ (M01-M40, M-AN*, M-AT*, M-CR*, M-ST*, M-IA*, M-TH*) — MCP-wired
    • audit-tiktok: Pixel + Events API + ttclid, creative diversity, Smart+, GMV Max, Symphony, learning phase (T01-T25, T-SR*)
  6. Validate: verify each subagent returned valid scores with required fields before aggregating
  7. Score: calculate per-platform and aggregate Ads Health Score (0-100)
  8. Report: generate prioritized action plan with Quick Wins

Data Collection

Ask the user for available data. Accept any combination:

  • Meta Ads: Capa 1 (claude.ai Facebook MCP, free), Capa 2 (scripts/api/meta_fetch.py → meta-data.json), Capa 3 (Ads Manager export + Events Manager screenshot + EMQ)
  • Google Ads: Capa 1 (cohnen/mcp-google-ads, free), Capa 2 (scripts/api/google_fetch.py → google-data.json), Capa 3 (account export + Change History + Search Terms Report)
  • TikTok Ads: Capa 1 (AdsMCP/tiktok-ads-mcp, free), Capa 2 (scripts/api/tiktok_fetch.py → tiktok-data.json), Capa 3 (Ads Manager export + Pixel/Events API status)

If no exports available, audit from screenshots or manual data entry.

Scoring

Read ads/references/scoring-system.md for full algorithm.

Per-Platform Weights

PlatformCategory Weights
GoogleConversion 25%, Waste 20%, Structure 15%, Keywords 15%, Ads 15%, Settings 10%
MetaPixel/CAPI 30%, Creative 30%, Structure 20%, Audience 20%
LinkedInTech 25%, Audience 25%, Creative 20%, Lead Gen 15%, Budget 15%
TikTokCreative 30%, Tech 25%, Bidding 20%, Structure 15%, Performance 10%
MicrosoftTech 25%, Syndication 20%, Structure 20%, Creative 20%, Settings 15%

Aggregate Score

Aggregate = Sum(Platform_Score x Platform_Budget_Share)
Grade: A (90-100), B (75-89), C (60-74), D (40-59), F (<40)

Output Files

  • ADS-AUDIT-REPORT.md: Comprehensive multi-platform findings
  • ADS-ACTION-PLAN.md: Prioritized recommendations (Critical > High > Medium > Low)
  • ADS-QUICK-WINS.md: Items fixable in <15 minutes with high impact

Report Structure

Executive Summary

  • Aggregate Ads Health Score (0-100) with grade
  • Per-platform scores
  • Business type detected
  • Active platforms identified
  • Top 5 critical issues across all platforms
  • Top 5 quick wins across all platforms

Per-Platform Sections

Each platform section includes:

  • Platform Health Score with grade
  • Category breakdown with pass/warning/fail per check
  • Platform-specific Quick Wins
  • Detailed findings with remediation steps

Cross-Platform Analysis

  • Budget allocation assessment (actual vs recommended)
  • Tracking consistency (are all platforms tracking the same events?)
  • Creative consistency (is messaging aligned across platforms?)
  • Attribution overlap (are platforms double-counting conversions?)

Strategic Recommendations

  • Platform prioritization based on business type
  • Budget reallocation recommendations
  • Scaling opportunities (platforms/campaigns ready to scale)
  • Kill list (campaigns/ad groups to pause immediately)

Priority Definitions

  • Critical: Revenue/data loss risk (fix immediately)
  • High: Significant performance drag (fix within 7 days)
  • Medium: Optimization opportunity (fix within 30 days)
  • Low: Best practice, minor impact (backlog)

Quick Wins Criteria

IF severity == "Critical" OR severity == "High"
AND estimated_fix_time < 15 minutes
THEN flag as Quick Win
SORT BY (severity_multiplier x estimated_impact) DESC

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