Ads Meta

Meta Ads Deep Analysis

Andromeda AI Engine

Meta's Andromeda AI engine (Oct 2025) filters ads using 10,000x more complex models. Creative diversity is now the #1 performance lever. Ads with Similarity Score >60% get retrieval suppression. The algorithm clusters near-identical creatives and limits their delivery. 100 minor variations perform no better than 10. Prioritize genuinely distinct concepts, angles, and formats over volume of similar variants.

Data Collection (3-tier free-first)

• Capa 1 — MCP (preferred when available): if the user supplies an ad_account_id (format act_) and the claude.ai Facebook MCP is connected, call the Meta MCP tools listed in ads/references/mcp-meta-integration.md. Most M01-M40 checks become live data lookups.
• mcp__claude_ai_Facebook__ads_get_dataset_quality → M02-M04 (EMQ, CAPI, dedup)
• mcp__claude_ai_Facebook__ads_get_ad_entities → M11-M40 (structure, learning phase, placements)
• mcp__claude_ai_Facebook__ads_catalog_get_diagnostics → Advantage+ Shopping health
• mcp__claude_ai_Facebook__ads_insights_performance_trend → M28 (creative fatigue)
• mcp__claude_ai_Facebook__ads_insights_industry_benchmark → live benchmarks (override benchmarks.md when present)
• Capa 2 — Direct API (also free; OAuth setup once): if a meta-data.json file is present in the cwd, read it as the data source. The user generates it ahead of audit time with:

``bash export META_ACCESS_TOKEN='...' python3 scripts/api/meta_fetch.py --account-id act_ -o meta-data.json ` Full setup in scripts/api/README.md. Set datasource: "directapi"` in the JSON output.

• Capa 3 — Manual fallback (always works, no setup): Ads Manager CSV export + Events Manager screenshot + EMQ scores. Mark unevaluable checks "result": "N/A" in the JSON output.

Then follow the standard 7-step audit process in ads/references/audit-methodology.md using meta-audit.md as the check list. Emit dual output (meta-audit-results.json against audit-output-schema.json, plus meta-audit-results.md).

What to Analyze

Pixel / CAPI Health (30% weight)

• Meta Pixel installed and firing on all pages
• Conversions API (CAPI) active (30-40% data loss without it post-iOS 14.5)
• Event deduplication configured (event_id matching, ≥90% dedup rate)
• Event Match Quality (EMQ) ≥8.0 for Purchase event
• All standard events configured (ViewContent, AddToCart, Purchase, Lead)
• Custom conversions created for non-standard events
• Aggregated Event Measurement (AEM) configured for iOS
• Domain verification completed
• Server-side events include customer_information parameters
• Pixel fires with correct currency and value parameters

Creative (30% weight)

• ≥3 creative formats active (image, video, carousel, collection)
• ≥5 creatives per ad set (Meta recommendation)
• Creative fatigue detection: CTR drop >20% over 14 days = FAIL
• Video creative: 15s max for Stories/Reels, 30s max for Feed
• UGC/testimonial creative tested
• Dynamic Creative Optimization (DCO) tested
• Ad copy: headline under 40 chars, primary text under 125 chars
• Creative refresh cadence: every 2-4 weeks for high-spend

Account Structure (20% weight)

• Campaign Budget Optimization (CBO) vs Ad Set Budget (ABO) intentional
• Campaign consolidation: 1-3 campaigns total recommended
• Learning phase health: 50%)
• Budget per ad set: ≥5x target CPA (minimum for learning phase exit)
• Ad set audience overlap 5)
• Retargeting frequency (7-day): 12)
• Custom Audiences: website visitors, customer lists, engagement
• Lookalike Audiences: multiple seed sizes tested (1%, 3%, 5%)
• Advantage+ Audience tested vs manual targeting
• Interest targeting: broad enough for algorithm optimization
• Exclusions: purchasers excluded from prospecting, overlap managed
• Location targeting reviewed for relevance

Advantage+ Assessment

If Advantage+ features are in use:

• Advantage+ Sales Campaigns: catalog connected, existing customer cap set
• Advantage+ Audience: performance vs manual audience compared
• Advantage+ Creative: enhancements enabled (text, brightness, music)
• Advantage+ Placements: enabled (let Meta optimize placement mix)
• Budget allocation: Advantage+ campaigns getting fair test budget

Special Ad Categories

If ads are in restricted categories:

• Special Ad Category declared before campaign creation
• Targeting restrictions verified (no ZIP, age 18-65+ only, no Lookalike)
• Creative compliance with category-specific policies
• Read ads/references/compliance.md for full requirements

EMQ Optimization Guide

| EMQ Score | Status | Action | |-----------|--------|--------| | 8.0-10.0 | Excellent | Maintain current setup | | 6.0-7.9 | Good | Add more customer_information parameters | | 4.0-5.9 | Fair | Implement CAPI, improve data quality | | 50% | | Budget per ad set | ≥5x CPA | 2-5x CPA | 20%)

• Quick Wins sorted by impact
• Advantage+ adoption recommendations

Threads Placement

Threads placement GA Jan 2026, 400M+ MAU. Lower CPMs than Feed/Stories. Currently ~0.04% of total spend. Emerging channel. Evaluate:

• Is Threads placement enabled in Advantage+ Placements?
• Monitor CPM and engagement vs other placements
• Early-mover advantage for brands with active Threads presence

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Hainrixz
• Source: Hainrixz/claude-ads
• License: MIT

Install and usage instructions live in the source repository linked above.