29-xuat-khau-b2b

29-xuat-khau-b2b is a skill for Claude Code from minhnv0807/ai-business-skills. It costs 209 tokens per session (3,623 once invoked), scanned A, original, MIT.

An export-marketing guide for Vietnamese businesses that want to sell to overseas business buyers.

In plain words
What is it for?
It helps research target markets, prepare English company profiles and pitch decks, write international sales emails, and plan trade-fair or Alibaba outreach.
Why use it?
It helps turn a local business’s product information into materials and market choices that international buyers can understand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-business-skills plugin — 144 skills, 6 agents, 10 MCP servers shipped together

Good fit It helps research target markets, prepare English company profiles and pitch decks, write international sales emails, and plan trade-fair or Alibaba outreach.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b
Install

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.

Any agent
npx skills add minhnv0807/ai-business-skills --skill 29-xuat-khau-b2b
Clone the repo
git clone --depth 1 https://github.com/minhnv0807/ai-business-skills

Made for: Claude Code.

Or install ai-business-skills, the plugin that ships this one along with the rest of its 144 skills, 6 agents, 10 MCP servers.

Wrote 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.

agentmods badge for 29-xuat-khau-b2b

README.md
[![agentmods](https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b/github.svg)](https://agentmods.dev/skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b)
Your own site
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b/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.

agentmods 80×15 button for 29-xuat-khau-b2b

Your own site · 80×15
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/29-xuat-khau-b2b.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00209 $0.03623
Opus 5 $0.00105 $0.01811
Sonnet 5 $0.00042 $0.00725
Haiku 4.5 $0.00021 $0.00362

Measured 9d ago against content hash 21d2dd5ccd95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

29-xuat-khau-b2b 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.

skills/vi/29-xuat-khau-b2b/SKILL.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xuat Khau B2B — Export Marketing Intelligence

Dung khi: Doanh nghiep VN muon mo rong sang thi truong nuoc ngoai, tim buyer quoc te, tham du hoi cho xuat khau, hoac can tai lieu marketing bang tieng Anh.


Buoc 0: Kiem tra context file

Doc file sau neu ton tai:

  • .agents/product-marketing-context.md — lay thong tin san pham, USP, gia tri khac biet
  • .agents/export-context.md — lay thong tin thi truong muc tieu, buyer persona quoc te (neu da tao)

Neu chua co export-context.md → chay Module 1 truoc.


Thu thap thong tin

Hoi toi da 4 cau truoc khi bat dau:

  1. San pham xuat khau la gi? Ten san pham, ma HS code (neu biet), chung nhan san co (GlobalGAP, ASC, BRC, FDA, Halal...)
  2. Thi truong muc tieu? Quoc gia cu the (TQ, My, EU, Nhat, Han...) hay con dang tim hieu?
  3. Da co kinh nghiem xuat khau chua? Lan dau hay da xuat, gap kho khan gi?
  4. Can lam gi ngay? Ho so cong ty / Email chao hang / Ke hoach hoi cho / Nghien cuu thi truong / Chien luoc gia?

Module 1: Export Context — Hieu biet thi truong xuat khau

Chay 1 lan, luu vao .agents/export-context.md

Thong tin can thu thap

# Export Context — [Ten Cong Ty]

## San pham xuat khau
- Ten san pham: [VD: Tom the chan trang dong lanh / Frozen Whiteleg Shrimp]
- HS Code: [VD: 0306.17]
- Specification: [Size, dang che bien, quy cach dong goi]
- Chung nhan san co: [GlobalGAP / ASC / BAP / BRC / FDA / Halal / Kosher]
- Cong suat: [X tan/thang hoac X container/thang]
- MOQ (minimum order): [X tan / X container 20ft]
- Lead time: [X tuan ke tu dat hang]

## Nha may & nang luc
- Ten nha may: [Ten]
- Dia chi: [Tinh/TP]
- Chung nhan nha may: [HACCP / ISO 22000 / BRC / EU approved / FDA registered]
- Nam thanh lap: [YYYY]
- Cong suat che bien: [X tan nguyen lieu/ngay]
- So luong nhan vien: [X nguoi]

## Thi truong muc tieu
- Thi truong uu tien 1: [VD: Trung Quoc — kenh hien dang nhap manh]
- Thi truong uu tien 2: [VD: EU — gia cao, can chung nhan]
- Thi truong uu tien 3: [VD: My — thue chong ban pha gia can theo doi]
- Thi truong tranh (vi sao): [VD: Nga — thanh toan rui ro]

## Buyer persona quoc te
- Loai buyer uu tien: [Nha nhap khau / Sieu thi / Nha phan phoi / Che bien]
- Quy mo giao dich mong muon: [X container/don hang]
- Nen tang tim buyer: [Alibaba / SeaFood Expo / Hoi cho / Moi gioi]

## Gia canh tranh
- Gia ban hien tai (FOB): [USD/kg] theo size
- Doi thu chinh: Ecuador / An Do / Indonesia / Thai Lan
- Loi the canh tranh cua minh: [VD: chat luong on dinh, giao hang dung han, co chung nhan EU]
- Diem yeu can cai thien: [VD: gia cao hon Ecuador 15–20%]

## Kinh nghiem xuat khau
- Da xuat sang: [Danh sach quoc gia]
- Khach hang tiem nang hien co: [Ten / quoc gia neu duoc]
- Vuong mac lon nhat: [VD: khong biet tim buyer o dau / gia cao / khong co chung nhan]

Read the full file on GitHub · 358 lines

Changes

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.

  1. 9d ago First seen · 358 lines · 209 tokens per session scan A 21d2dd5ccd95

Subscribe to this mod's changes

29-xuat-khau-b2b is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 209 tokens to every session and 3,623 once invoked, about $0.0010 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.