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 29-dropshipping-mastery-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/29-dropshipping-mastery-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/29-dropshipping-mastery-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/29-dropshipping-mastery-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/29-dropshipping-mastery-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/29-dropshipping-mastery-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 407 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00198 | $0.06166 |
| Opus 5 | $0.00099 | $0.03083 |
| Sonnet 5 | $0.00040 | $0.01233 |
| Haiku 4.5 | $0.00020 | $0.00617 |
Grade B, and why
29-dropshipping-mastery-global scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- No income claims without disclaimers ("make $5K/month" with typical-results disclosure) How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dropshipping Mastery — Global
Flagship skill for building a profitable dropshipping operation in US/EU/global markets. Covers the full pipeline from product research to scaling — with realistic 2025-2026 tools, prices, and benchmarks.
1. For newbies — Read this first
What is dropshipping? A retail model where you sell products online without holding inventory. When a customer orders, you forward the order to a supplier (AliExpress, CJ, etc.) who ships directly to the customer. You keep the margin between supplier price and your retail price.
Difference vs other models:
- Amazon FBA: You buy inventory upfront, ship to Amazon warehouses. Higher capital, faster shipping, brand-locked to Amazon ecosystem.
- Branded e-commerce: You manufacture or white-label, hold inventory, build long-term brand. Highest capital, highest margins, durable moat.
- White label / private label: Custom-branded products from suppliers, often with MOQ. Middle path between dropshipping and full brand.
- Dropshipping: Lowest capital, fastest iteration, lowest margins per unit, weakest moat.
When to choose dropshipping:
- Low starting capital ($500-2K to begin)
- Want to validate product-market fit before investing
- Comfortable iterating fast (test products in days, not months)
- OK with thin margins (15-30% net) and reliance on suppliers
When NOT to dropship:
- You're building a long-term brand with quality differentiation
- Your market expects 2-3 day shipping (premium fashion, urgent gifts)
- Product requires customization or quality control
- You need defensible IP or proprietary tech
Realistic expectations: 90% of dropshippers fail in the first 6 months. The top 10% who survive iterate fast, master ad creative, and reinvest profits. Successful operators do $10K-$1M+/month, but most plateau at $1K-5K/month before quitting. The lever is creative quality + product selection — not "secret hacks."
2. Information collection
Ask up to 4 questions before generating output:
- Niche: What product category interests you? (e.g., pet, beauty, home, fitness, gadgets) Or "I need help picking."
- Supplier preference: Fast shipping (Spocket/Zendrop, premium cost) or cheapest (AliExpress, slow shipping)?
- Ad platform priority: Facebook/Instagram, TikTok, both, or unsure?
- Monthly ad budget: <$500 (validate only), $500-2K (test + scale), $2K+ (aggressive scale)?
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 · 438 lines · 198 tokens per session scan B 15582abf445c
29-dropshipping-mastery-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 198 tokens to every session and 6,166 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
shop
Shop catalog search, checkout, order tracking, returns.
shopify
Query Shopify Admin/Storefront GraphQL APIs via curl.
stripe-link-cli
Agent payments via Stripe Link — cards, SPT, approvals.
product-price-monitor
Watch product, flight, or listing prices; alert on target.
shop-best-sellers
Run a strict best-sellers workflow for a shop app using orders and catalog data, and return a fixed-format report. Use by default whenever the user wants top products, seller ranking, revenue leaders, merchandising priorities, or a view of what is selling best, even indirectly or with approximate wording. Prefer this…
shop-orphan-products
Find orphan products (products with no assigned collection), return them in a table with direct back-office links, and propose a practical collection assignment plan based on similar catalog items. Read-only. Use by default whenever the user wants to find products missing collections or clean up catalog organization…