Foreign Trade Research logo

Foreign Trade Research

Community
liangdabiao
foreign-trade-research

Deep foreign-trade and overseas market-entry research for a target country plus product/category. Use for Chinese exporters, manufacturers, and cross-border teams that need competitor landscapes, local brands, manufacturers, distributors/importers, pricing, channels, market gaps, risks, and a cited Chinese business report. Portable across Codex, OpenClaw, Claude Code, and other SKILL.md-compatible agents.

Overview

Publisherliangdabiao
Repositoryexa-research-mcp-skill
Skill nameforeign-trade-research
Stars
117
Forks
17
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by liangdabiao on GitHub. Read the source before you install it.

Installation

Install the Foreign Trade Research AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/foreign-trade-research
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/liangdabiao/exa-research-mcp-skill.git /tmp/exa-research-mcp-skill
mkdir -p .claude/skills
cp -r /tmp/exa-research-mcp-skill/skills/foreign-trade-research .claude/skills/foreign-trade-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Foreign Trade Research in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Foreign Trade Research on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Foreign Trade Research is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Foreign Trade Research

Core Rules

  • Prefer Exa advanced web search when available; otherwise use the best configured web-search/MCP tool in the host agent.
  • Search in English plus the target market's local language when possible.
  • Keep evidence traceable: cite official sites, marketplaces, company databases, regulator/import records, credible news, and review/social platforms.
  • Distinguish verified facts from estimates and strategic inference.
  • If the user asks to exclude Chinese companies, explicitly filter them during search and mark any unavoidable Chinese-owned subsidiaries.

Five-Step Workflow

1. Identify the Competitive Landscape

Build a TOP20 market map for the target country and product:

  • Local or market-facing brands: TOP7 companies with visible branded products.
  • Manufacturers: TOP7 local factories or international manufacturers with local production/distribution.
  • Distributors / wholesalers / importers: TOP6 major channel players.

For each company capture: full name, website, HQ/location, role, market position, and evidence.

Search patterns:

text
[target country] [product] leading companies manufacturers brands 2026
best [product] brands in [target country] distributors importers
[target country local-language product term] manufacturer distributor retailer
site:. [target country TLD] [product] supplier distributor

2. Deep-Dive Each Competitor

For each prioritized company, extract:

  1. Company background: size, history, ownership, subsidiaries, locations.
  2. Product lines: models/SKUs, technical claims, certifications, differentiators.
  3. Pricing strategy: premium/mid/economy positioning, listed prices, promos, MOQ if available.
  4. Customers/channels: B2B/B2C, ecommerce, distributors, dealers, sectors served.
  5. Strengths/weaknesses: evidence-based advantages, gaps, complaints, unmet needs.

Use official websites first, then marketplaces, news, social, reviews, and trade databases.

3. Build a Comparison Matrix

Create a table with:

markdown
| Company | Role | Market position | Core products | Price band | Channels/customers | Strengths | Weaknesses | Sources |
|---|---|---|---|---|---|---|---|---|

Then analyze:

  • Is the market monopolistic, oligopolistic, or fragmented?
  • Which players are the most threatening competitors?
  • Where are the product, price, channel, or service gaps?
  • What entry points are realistic for Chinese suppliers?

4. Cross-Validate Key Data

Validate important claims across multiple source types:

  • Official company/product pages for identity and product claims.
  • Ecommerce/B2B marketplaces for price, assortment, sales signals, and reviews.
  • Local news and trade media for launches, partnerships, expansion, and regulation.
  • Social/professional pages for activity, headcount signals, and decision makers.
  • Customer review sites and forums for complaints and unmet demand.

When sources conflict, show the conflict and assign confidence instead of hiding uncertainty.

5. Write the Final Report

Default report structure in Chinese:

markdown
# [目标国]_[产品/品类]_市场调研报告

## 一、执行摘要
- 核心发现(3-5条)
- 市场机会评级(高/中/低)与理由

## 二、市场概述
1. 市场规模与增长趋势(注明年份和来源)
2. 需求驱动因素与主要挑战
3. 竞争格局总览

## 三、主要品牌商分析(TOP7)

## 四、主要制造商分析(TOP7)

## 五、主要经销商/进口商分析(TOP6)

## 六、竞争格局深度分析
1. 市场份额或影响力估算
2. 价格竞争
3. 渠道竞争
4. 产品/技术竞争
5. 市场空白点

## 七、中国供应商进入机会与建议
1. 市场切入点
2. 产品定位
3. 定价策略
4. 渠道策略
5. 本地化与认证建议

## 八、风险提示
- 政策/认证/关税风险
- 汇率/物流/售后风险
- 竞争与合规风险

## 九、资料来源与置信度说明

Report requirements:

  • Default length: 5,000-8,000 Chinese characters unless the user requests otherwise.
  • Save to [目标国]_[产品]_市场调研报告.md when working in a repository or workspace and the user expects a file.
  • Use citations inline for key numbers, company claims, and current events.
  • Preserve original English/local company names and technical terms where useful.

Search Depth

  • Quick scan: landscape 20-30 results; company deep dives 5-10 results each for priority players.
  • Standard report: landscape 30-50 results; company deep dives 10-25 results each.
  • Comprehensive report: landscape 50-100 results; company deep dives 25-50 results each.
  • For tight time budgets, reduce company count before reducing citation quality.

Chrome MCP / Browser Fallback

Use Chrome MCP as the preferred fallback when Exa/search results are insufficient and the user has configured/sanitized Chrome MCP. It is appropriate for official websites, dynamic pages, ecommerce listings, review pages, PDF downloads, maps, or source verification that needs a real browser.

Store only distilled evidence in the report or JSON notes: source title, URL, publisher/platform, accessed date, key facts, and confidence. Do not store cookies, credentials, account identifiers, private profile data, or unrelated browsing history.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Foreign Trade Research AI skill do?

Deep foreign-trade and overseas market-entry research for a target country plus product/category. Use for Chinese exporters, manufacturers, and cross-border teams that need competitor landscapes, local brands, manufacturers, distributors/importers, pricing, channels, market gaps, risks, and a cited Chinese business report. Portable across Codex, OpenClaw, Claude Code, and other SKILL.md-compatible agents.

Why use Foreign Trade Research on TypingMind?

Because you install it once and use it with any model. Foreign Trade Research is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Foreign Trade Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/foreign-trade-research. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Foreign Trade Research?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Foreign Trade Research?

As many as you like. As long as a model supports skills, you can use Foreign Trade Research with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Foreign Trade Research AI skill free?

It is published on GitHub by liangdabiao. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇