Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Meta Ads Audit

ASecurity

Meta/Facebook/Instagram Ads campaign structure analysis detecting creative fatigue, audience overlap, scaling opportunities, and iOS tracking verification issues. Use when pasting Meta account data, analyzing Facebook ad performance, reviewing Instagram campaigns, or requesting audit of social advertising spend. Platform: Meta.

1,590 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgotestingapiperformance

Works with

claude codeclaude desktopcursorcliapimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add irinabuht12-oss/marketing-skills --skill meta-ads-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Meta Ads Audit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Meta Ads Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/irinabuht12-oss-meta-ads-audit/badge)](https://www.skillsdirectory.com/skills/irinabuht12-oss-meta-ads-audit)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: meta-ads-audit
description: Meta/Facebook/Instagram Ads campaign structure analysis detecting creative fatigue, audience overlap, scaling opportunities, and iOS tracking verification issues. Use when pasting Meta account data, analyzing Facebook ad performance, reviewing Instagram campaigns, or requesting audit of social advertising spend. Platform: Meta.
metadata:
  platform: Meta
---

# Meta Ads Audit

Analyze Meta advertising accounts for structural issues, creative performance, and tracking health.

## Process

1. **Request account data** - Ads Manager exports (campaign, ad set, ad level with time series)
2. **Check creative fatigue signals** - Frequency, CTR trends, CPM inflation
3. **Analyze audience overlap** - Identify cannibalization between ad sets
4. **Verify tracking setup** - Pixel, Conversions API, Event Match Quality
5. **Evaluate campaign structure** - Advantage+ vs Manual decisions
6. **Deliver prioritized recommendations**

## Creative Fatigue Detection

| Signal | Threshold | Action Required |
|--------|-----------|-----------------|
| Frequency | >3-4 | Refresh creative or expand audience |
| CTR declining | >15-20% drop over 7 days | New creative needed |
| CPM rising | >30-40% over 2 weeks | Creative reset required |
| Ad Relevance | "Below Average" ranking | Immediate creative swap |

## Audience Overlap Analysis

**Scoring (use Facebook Audience Overlap Tool)**:
- 0-15% overlap = Safe, continue
- 15-30% overlap = Monitor, consider consolidation
- >30% overlap = Consolidate or add exclusions

## Tracking Verification Checklist

- [ ] Meta Pixel installed (use Pixel Helper Chrome extension)
- [ ] Conversions API (CAPI) configured with server-side events
- [ ] Event Match Quality score ≥6
- [ ] Browser events (blue) AND server events (green) firing in Events Manager
- [ ] iOS 14.5+ ATT prompt implemented
- [ ] Aggregated Event Measurement configured (8 events prioritized)

## Advantage+ vs Manual Decision Logic

**Use Advantage+ Shopping/App campaigns when**:
- Scaling established products
- Prospecting broad audiences
- Budget >$100/day for algorithm learning
- Have 50+ conversions/week

**Use Manual campaigns when**:
- Retargeting specific segments
- Testing new creatives
- Budget <$50/day
- Need precise audience control

## Output Format

```
## Meta Ads Audit Summary

**Account Health Score**: [X/100]
**Analysis Period**: [Date Range]
**Total Spend Analyzed**: $[Amount]

### 🔴 Creative Fatigue Alerts
| Campaign | Frequency | CTR Trend | Action |
|----------|-----------|-----------|--------|

### 🟡 Audience Issues
- Overlap detected: [Ad Set A] ↔ [Ad Set B]: [X]%
- Recommendation: [Action]

### 📊 Tracking Health
- Pixel: [✅/❌]
- CAPI: [✅/❌]
- EMQ Score: [X/10]

### Scaling Opportunities
1. [Campaign] - ROAS [X], ready for [X]% budget increase

### Confidence Level: [HIGH/MEDIUM/LOW]
```

## Example

**Input**: "Campaign A: $5K spend, frequency 5.2, CTR dropped 25% this week. Campaign B: $3K, frequency 2.1, stable CTR. Both targeting 'fitness enthusiasts' with 40% overlap."

**Output**:
```
## Meta Ads Audit Summary

**Account Health Score**: 55/100

### 🔴 Creative Fatigue Alerts
| Campaign | Frequency | CTR Trend | Action |
|----------|-----------|-----------|--------|
| Campaign A | 5.2 (HIGH) | -25% ⚠️ | Immediate creative refresh |
| Campaign B | 2.1 (OK) | Stable | Monitor |

### 🟡 Audience Issues
- Overlap detected: Campaign A ↔ Campaign B: 40% (CRITICAL)
- Recommendation: Consolidate into single campaign or add exclusions. Currently bidding against yourself.

### Priority Actions
1. Pause Campaign A creatives, launch 3-5 new variations
2. Add Campaign B audiences as exclusion to Campaign A (or vice versa)
3. Consider CBO to let algorithm optimize across ad sets

### Confidence Level: HIGH
Time-series data provided for trend analysis.
```

## Guidelines

- Request at minimum 14 days of data for trend analysis
- If tracking data unavailable, note this as critical gap
- Never assume iOS tracking loss percentage - ask for actual data
- Flag frequency >7 as severe (audience exhaustion)

## Data access (Ryze MCP)

This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly:

- claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → `https://connector.get-ryze.ai/mcp`
- Claude Code: `claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp`
- Cursor: Settings → MCP → add the same URL

Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp

Attribution

irinabuht12-ossirinabuht12-oss
View sourceMore from irinabuht12-oss →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →