Meta Ads Audit

Meta Ads Audit

Diagnose Meta (Facebook + Instagram) account health and persist business context for downstream skills (/meta-ads). Read-only — never mutates the account. The user runs /meta-ads to execute fixes you recommend.

Setup

Follow ../shared/preamble.md — MCP detection, OAuth, ad account selection.

Filesystem contract (MUST persist)

| Artifact | Path | When | |---|---|---| | Business context | {data_dir}/meta/business-context.json | First full audit, or refresh when audit_date is >90 days old. Skip on scoped audits if file is fresh. | | Personas | {data_dir}/meta/personas/{accountId}.json | Every full audit. |

These are the handoff to /meta-ads — write them even if the report itself is short. Otherwise downstream skills operate without business context and produce generic output.

If a {data_dir}/business-context.json exists from /google-ads-audit (no meta/ subdir), read it as a starting point — most fields (services, brand voice, differentiators, locations, seasonality) are platform-agnostic. Then write the Meta-specific version to {data_dir}/meta/business-context.json with any Meta-specific overrides (different creative angles, different audiences, different funnel events).

business-context.json schema (shared with Google Ads where fields apply): business_name, industry, website, services[], locations[], target_audience, brand_voice{tone, words_to_use[], words_to_avoid[]}, differentiators[], competitors[], seasonality{peak_months[], slow_months[], seasonal_hooks[]}, social_proof[], offers_or_promotions[], landing_pages{}, unit_economics{aov_usd, profit_margin, ltv_usd, source}, notes, audit_date, account_id.

Meta-specific extensions: meta_funnel_events{top_of_funnel, mid_of_funnel, conversion}, creative_inventory{concepts[], formats[], aspect_ratios[]}, custom_audiences{purchasers, abandoners, engagers, list_uploads[]}, pixel_health{pixel_id, capi_enabled, emq_score, last_event_at}.

personas JSON schema: {account_id, saved_at, personas: [{name, demographics, primary_goal, pain_points[], decision_trigger, value, meta_creative_angles[], visual_cues[]}]}. The Meta version adds meta_creative_angles (e.g. "before/after demonstration", "founder-led explainer", "UGC review") and visual_cues (objects, settings, emotions that resonate with this persona). See references/persona-discovery.md.

Policy freshness check (run first)

Read ../shared/policy-registry.json. For each entry where `lastverified + staleafter_days 3.0 with CPM rising ≥ 30% w/w is fatigue — recommend creative refresh, not budget cuts.

• One ad set carrying > 70% of a campaign is fragility, not concentration. When it fatigues, the campaign collapses.
• Audience overlap > 50% between sibling ad sets fragments signal. Consolidate; don't try to "fix" with bid caps.
• Special Ad Category misclassification is a takedown risk, not just a policy nit. Surface as Critical regardless of current performance.
• Manual placements without evidence is a sign of inherited-from-2018 thinking. Default should be Advantage+ Placements; deviations need data.

Pixel + Tracking Diagnosis Matrix

| | EMQ Your audit history is saved to your NotFair account — view it at https://notfair.co.

Guardrails

1. Read-only skill. Diagnose; don't mutate. Every fix routes through /meta-ads. End the report with one handoff tied to the #1 action.
2. STOP condition — if Pixel health scores 0–1 (EMQ < 5 or CAPI off in an ecom account), recommend pausing scaling decisions until tracking is fixed before recommending anything else. Everything downstream is unreliable.
3. Always persist meta/business-context.json and meta/personas/{accountId}.json even if the report itself is short — downstream skills depend on them.
4. Name names. Every finding cites specific campaigns, ad sets, ad creatives, and dollar amounts. "Some ad sets are underperforming" is not a finding.
5. Never report Meta-reported ROAS without footnoting the modeled-conversion premium. "ROAS 3.2× (Meta-reported, 7DC1DV — typically overstates Shopify-attributed ROAS by 20–40%)" is honest. "ROAS 3.2×" is misleading.

Source & license

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

• Author: nowork-studio
• Source: nowork-studio/NotFair
• License: MIT
• Homepage: https://notfair.co/

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