Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add minhnv0807/ai-business-skills --skill 21-ads-audit-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/minhnv0807/ai-business-skills/21-ads-audit-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/21-ads-audit-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/21-ads-audit-global/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/21-ads-audit-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/21-ads-audit-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.05458 |
| Opus 5 | $0.00078 | $0.02729 |
| Sonnet 5 | $0.00031 | $0.01092 |
| Haiku 4.5 | $0.00016 | $0.00546 |
Grade A, and why
21-ads-audit-global scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ads Audit (Global) — Health Score & Action Plan
Difference from
03-performance-eval-global:
03evaluates current performance (CPM, ROAS, funnel) — diagnoses symptoms.21audits 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:
- Read access to ad accounts (or screen-share / data export).
- Last 30 days of spend, impressions, clicks, conversions, ROAS.
- Pixel/CAPI status (Events Manager, GA4, TikTok Events).
- Region context (US, EU, SEA, LATAM) — benchmarks differ widely.
- Business model (DTC e-com, B2B SaaS, lead gen, dropshipping) — optimization rules differ.
How long does it take?
- Quick audit: 2-3 hours (Health Score + Quick Wins).
- Full audit: 6-10 hours (Health Score + 84 checkpoints + 7-day plan + creative review).
Step 0 — Read Context + Select Region Variant
Before audit, pull two contexts:
- Product context — call
product-marketing-context-globalif not already in conversation. This gives the auditor: pricing, target CAC, business model, current channels. - Region variant — load the appropriate file:
| Region | File | Currency | Key benchmarks |
|---|---|---|---|
| US / North America | variants/01-us.md |
USD | Meta CPM $7-12, Google CPC $1-3, ROAS 3-5x |
| EU / UK | variants/02-eu.md |
EUR / GBP | Meta CPM €5-10, Google CPC €1-3, ROAS 3-4x |
| SEA (VN, TH, ID, PH, SG, MY) | variants/03-sea.md |
USD-equivalent | Meta CPM $1-2, Google CPC $0.30-1, ROAS 2-3x |
| LATAM (BR, MX, AR, CO, CL) | variants/04-latam.md |
USD-equivalent | Meta CPM $0.50-1.5, Google CPC $0.20-0.80, ROAS 2-3x |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 480 lines · 157 tokens per session scan A 86dce4430a00
21-ads-audit-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 157 tokens to every session and 5,458 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
mcp-oauth-remote-gateway
Manual OAuth for remote MCP servers on headless gateways.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
honcho
Configure and troubleshoot Honcho memory for Hermes.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
hyperframes
Render MP4/WebM videos from HTML compositions.