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 62-marketing-review-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/62-marketing-review-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/62-marketing-review-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/62-marketing-review-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/62-marketing-review-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/62-marketing-review-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 | $0.00161 | $0.02439 |
| Opus 5 | $0.00081 | $0.01220 |
| Sonnet 5 | $0.00032 | $0.00488 |
| Haiku 4.5 | $0.00016 | $0.00244 |
Grade A, and why
62-marketing-review-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 9d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Review (Global)
Reviewing a brief before writing means one round of edits. Skipping it means five rounds after writing. Reviewing ads before launch prevents burning budget on the wrong creative — one hour of review saves days of bad CPA. A leader review is not about personal taste; it is about whether the work matches the objective, the audience, and the brand. For visual and design work, use
47-design-review-global.
Information gathering
Ask up to 4 questions:
- What is being reviewed? A content brief, or ad copy plus creative? Paste the content or share the file.
- Campaign context: which campaign, which funnel stage (TOFU/MOFU/BOFU), which platform?
- Target audience and the primary KPI for this campaign (CPL / ROAS / CTR)?
- Which review round is this? First pass, or already revised — if it is still wrong after two rounds, the problem is the original brief, not the person.
Principles
- Review against a checklist, not a feeling. "I like it / I don't like it" is not a criterion.
- Feedback must be specific and actionable. "The hook is weak" is not enough — say "the hook must hit pain [X] within the first 3 seconds / first 125 characters."
- Review inside the SLA: content briefs within 24 hours, ads within 4-8 hours. Do not leave the team waiting.
- One revision round maximum after review. If it is still off, the leader and the maker sit together — no ping-pong.
- Approve means ship within 24 hours. Approved work that sits loses momentum.
- Give feedback about the system, not the person. Repeated misses on the same brief mean the brief is broken.
Workflow
1. Identify the review type
| Output type | Checklist to use | Note |
|---|---|---|
| Content brief (before the writer writes) | Mode A below | |
| Ad copy + creative (before ads go live) | Mode B below | |
| Visual / design (banner, carousel, landing page) | 47-design-review-global |
Separate skill for visuals |
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.
- 9d ago First seen · 183 lines · 161 tokens per session scan A 63b48f950de2
62-marketing-review-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 161 tokens to every session and 2,439 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 2026-09-03.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
tldraw-offline
Drive and script tldraw offline canvases with an agent.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
adversarial-ux-test
Roleplay a hostile user to find and triage UX pain points.