21-ads-audit-global
Comprehensive ads audit for Meta/Google/TikTok with Health Score 0-100. 84 checkpoints across 6 dimensions (Account/Campaign/AdSet/Ad/Tracking/Optimization). Has 4 region variants for benchmarks. INCLUDES Dropshipping Audit Checklist (creative testing velocity, CRO signals, attribution accuracy). Trigger: 'ads audit', 'ad account audit', 'Meta audit', 'Google Ads audit', 'TikTok audit', 'dropshipping ads audit'.
Profile →npx skills add minhnv0807/ai-business-skills --skill 21-ads-audit-global --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill conducts a comprehensive ads audit across Meta, Google, and TikTok, producing a Health Score (0-100), a list of Quick Wins, and a 7-day Action Plan. It evaluates 84 checkpoints spanning Account, Campaign, Ad Set/Ad Group, Ad/Creative, Tracking, and Optimization, and includes a Dropshipping Audit Checklist for creative testing velocity, CRO signals, and attribution accuracy. It supports region variants to benchmark performance and uses a structured workflow with region selection, data gathering questions, and MCP auto-pull options when connected.
How it works
It begins by distinguishing between current performance evaluation and account-configuration auditing, leading with qualitative judgment backed by metrics. It instructs the user to gather context (product context and regional variant file) and ask up to four questions to determine platforms, industry/model, monthly spend/region, and data access. If an MCP server is connected, it fetches data via MCP tools and samples, otherwise relies on provided fields like spend, impressions, clicks, conversions, ROAS, and event data. The Health Score is computed using a weighted formula across six dimensions with defined severity multipliers and a nine-dimension checkpoint set (84 checks). It provides a Quick Wins decision tree prioritizing critical issues (billing, tracking, policy violations) and then lists top improvements with action, impact, time, and owner. The Dropshipping section presents specialized tests for creative velocity, CBO/ABO setups, and pixel/CAPI dual tracking, with explicit pass criteria and severities.
When to use it
Use when ROAS drops (>20% WoW), when inheriting a new account, when monthly spend exceeds $5K without review, when pixel/CAPI errors occur, when planning to scale spend, or for dropshipping attribution challenges. Trigger keywords include: 'ads audit', 'ad account audit', 'Meta audit', 'Google Ads audit', 'TikTok audit', 'dropshipping ads audit'.
What it can touch
The skill references tools and data sources such as:
- MCP integration and commands for Meta Ads, Google Ads, and TikTok (e.g., MCP URLs and GAQL sample).
- Regions variants with specific benchmark files and currencies.
- Data fields for MCP pull: spend, impressions, clicks, etc. (sample fields shown).
Caveats
The skill defines a structured, rules-based evaluation with a health scoring system and region-specific benchmarks. It relies on access to ad accounts or exported data, and on MCP connectivity if available. No outcomes are guaranteed beyond the described Health Score, Quick Wins, and 7-day plan, and the Dropshipping checklist supplements the universal 84 checks rather than replacing them.
# Ads Audit (Global) — Health Score & Action Plan > **Difference from `03-performance-eval-global`:** > - `03` evaluates current performance (CPM, ROAS, funnel) — diagnoses symptoms. > - `21` audits account configuration (setup, structure, tracking, creative) — scores 0-100 and finds systemic issues. > > Insight before numbers. Lead with judgment; illustrate with metrics. --- ## For Newbies — Start Here **What is an ads audit?** A structured review of your ad accounts (Meta, Google, TikTok) to find leaks, misconfigurations, and missed opportunities. The output is a **Health Score (0-100)**, a list of **Quick Wins**, and a **7-day Action Plan**. **When do you need one?** - ROAS dropped suddenly (>20% week-over-week). - New account inherited from another agency or in-house team. - Spending >$5K/month with no clear performance review process. - Pixel/CAPI showed errors or duplicate events. - About to scale spend by 2-3x and want to verify foundation. - Dropshipping store with attribution confusion (Shopify vs Meta vs Triple Whale numbers don't match). **What you'll need before starting:** 1. Read access to ad accounts (or screen-share / data export). 2. Last 30 days of spend, impressi
- For Newbies — Start Here
- Step 0 — Read Context + Select Region Variant
- Information Gathering
- Auto-pull via MCP (if connected)
- Health Score Framework (0-100)
- Formula
- Severity weights
- Grade scale
- 6 Dimensions
- 84 Checkpoints (Universal Core)
- Dimension 1 — ACCOUNT (12 checks, weight 10%)
- Dimension 2 — CAMPAIGN (14 checks, weight 15%)
- Dimension 3 — AD SET / AD GROUP (16 checks, weight 20%)
- Dimension 4 — AD / CREATIVE (18 checks, weight 25%)
What does the 21-ads-audit-global skill do?
Comprehensive ads audit for Meta/Google/TikTok with Health Score 0-100. 84 checkpoints across 6 dimensions (Account/Campaign/AdSet/Ad/Tracking/Optimization). Has 4 region variants for benchmarks. INCLUDES Dropshipping Audit Checklist (creative testing velocity, CRO signals, attribution accuracy). Trigger: 'ads audit', 'ad account audit', 'Meta audit', 'Google Ads audit', 'TikTok audit', 'dropshipping ads audit'.
How do I install it?
Run `npx skills add minhnv0807/ai-business-skills --skill 21-ads-audit-global --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From minhnv0807/ai-business-skills, a repository with 521 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.