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-audit-ads-performancegit 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-audit-ads-performance)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/21-audit-ads-performance"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/21-audit-ads-performance/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-audit-ads-performance"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/21-audit-ads-performance.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 | $0.00238 | $0.07632 |
| Opus 5.5 | $0.00095 | $0.03053 |
| Sonnet 5.5 | $0.00048 | $0.01526 |
| Haiku 4.5 | $0.00024 | $0.00763 |
Grade A, and why
21-audit-ads-performance 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 2d 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Ads Performance — Health Score theo do phu & Action Plan
Quy tac van hanh chung:
skills/vi/references/quy-tac-van-hanh.md(dac biet quy tac 2, 3, 7).
Skill nay khac
03-danh-gia-hieu-suato cho:
03= So xau tuan nay, vi sao CPA tang dot ngot — chan doan trieu chung21= Audit cau hinh tai khoan (setup, cau truc, tracking, creative) — cham Health Score theo do phu va tim loi he thong- Quang cao noi san (GMV Max, Shopee Ads, Lazada) →
76-van-hanh-san-tmdt
Thu thap thong tin
Doc .agents/product-marketing-context.md truoc (quy tac 1): CPA muc tieu (tu 10-tinh-kpi-nguoc), AOV, bien dong gop truoc ads, noi chot don (web / san TMDT / inbox). Chi hoi phan con thieu, toi da 4 cau:
- Nen tang can audit? Meta Ads / TikTok Ads / Google Ads / Zalo Ads / Tat ca?
- Nganh, muc tieu chinh va noi chot don? (Spa, F&B, BDS, E-com... + CPMess / ROAS / Lead / Don hang; chot tren web, san hay inbox)
- Ngan sach/thang, AOV va bien dong gop truoc ads? (De tinh diem hoa von va ty trong ngan sach tung nen tang)
- Co the cung cap data? (Export 30 ngay tu Ads Manager: Spend, CPM, CPC, CTR, Conversion, CPMess, ROAS; Google them search terms report)
Export thieu cot nao → cac check can cot do la unknown, khong phai fail (quy tac 3).
Auto-pull data qua MCP (neu co ket noi)
Reference:
skills/vi/references/mcp-ads-integration.md— huong dan setup day du. Meta Official MCP [DA KIEM 2026-10, open beta tu 2026-04-29]: endpointhttps://mcp.facebook.com/ads, ket noi qua giao dien connector cua client; liet ke tool luc ket noi (so tool doi lien tuc, khong ghi cung). MCP nay co quyen ghi → audit chay o che do chi doc; moi lenh ghi phai qua muc "De xuat thay doi" ben duoi.
| Nen tang | MCP | Quyen | Dung cho audit |
|---|---|---|---|
| Meta Ads | Meta Official MCP (mcp.facebook.com/ads) |
Doc + ghi | Insights, entities, dataset/tracking quality — liet ke tool luc ket noi |
| Meta Ads (alt) | Pipeboard (cong dong) | Mac dinh chi doc | Insights, targeting research — liet ke tool luc ket noi |
| Google Ads | Google Official MCP | Chi doc | search voi GAQL query |
| TikTok Ads | AdsMCP/tiktok-ads-mcp-server (cong dong) | Mac dinh chi doc | Performance report |
| Cross-platform | Adspirer ads-mcp (cong dong) | Mac dinh chi doc | Bao cao hop nhat — liet ke tool luc ket noi |
What ships with it
2 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.
- 2d ago Changed · +37 lines · +70 tokens per session 1315390351d3
- 1mo ago First seen · 416 lines · 168 tokens per session scan A ae46597e130b
21-audit-ads-performance is a skill published in the GitHub repository minhnv0807/ai-business-skills (638 stars, last pushed yesterday), licensed MIT. It adds 238 tokens to every session and 7,632 once invoked, about $0.0010 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
anatomy
Explain an idea as an interactive isometric machine figure.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
creative-ideation
Generate ideas via named methods from creative practice.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.