China Apparel & Accessories Suppliers

Comprehensive apparel and accessories industry suppliers guide for international buyers – provides detailed information about China's garment, footwear, bag,...

Security Scan

The skill is self-contained and behaves consistently with its description: it serves read-only, cluster-level sourcing intelligence from an included data.json and does not request credentials or perform network access.

Purpose & Capability

Name/description match the implementation: run.py exposes read-only functions that return industry overview, supply-chain structure, regional clusters, subsector info, and a sourcing guide from the bundled data.json. No unrelated capabilities (cloud access, system control, or extra services) are requested.

Instruction Scope

SKILL.md instructs natural-language use and documents the API supported by run.py. Everything stays within the stated purpose (reading/serving aggregated data). Minor inconsistency: example imports in SKILL.md use 'from do import ...' while the provided file is run.py (module naming/import path may not match packaging). Also, SKILL.md lists external sources as provenance but the skill contains a static snapshot (no runtime network calls) — this is expected but worth noting.

Install Mechanism

No install spec; code and data are bundled in the skill and loaded locally. There are no downloads, no extracted archives, and nothing written to disk beyond reading the included data.json.

Credentials

The skill requests no environment variables, no credentials, and no config paths. Its functionality (serving static industry data) does not warrant additional secrets or external service tokens.

Persistence & Privilege

always is false (default). disable-model-invocation is false (normal). The skill does not request persistent system-wide changes or access to other skills' configs.

Assessment

This skill is a static, read-only reference: it returns information from the included data.json via functions in run.py and does not contact external services or ask for credentials. Before installing, consider: (1) data freshness and provenance — the skill claims sources but uses a bundled snapshot (last_updated 2026-03-15); (2) if you will import the code programmatically, verify the import name/path (SKILL.md examples reference 'do' while the file is run.py); (3) run the code in a sandbox or review the files yourself if you plan to execute them in production, although there are no obvious red flags (no network I/O, no env var access, no subprocess calls). If you need supplier contact details or live lookups, this skill intentionally does not provide those and would require a different capability that would likely need network access and appropriate credentials.

China Apparel & Accessories Factory Skill

Description

This skill helps international buyers navigate China's apparel and accessories manufacturing landscape, which is projected to exceed ¥5.8 trillion in revenue by 2026. It provides data-backed intelligence on regional clusters, supply chain structure, and industry trends based on the latest government policies and industry reports. Coverage includes garments, footwear, bags, hats, scarves, fashion accessories, and more.

Key Capabilities

• Industry Overview: Get a summary of China's apparel and accessories industry scale, development targets, and key policy initiatives (digital transformation, sustainability, brand building).
• Supply Chain Structure: Understand the complete industry chain from raw materials (fibers, fabrics, trims) to manufacturing and sales channels (domestic retail, cross-border e-commerce).
• Regional Clusters: Identify specialized manufacturing hubs for different product categories (women's wear in Guangzhou, men's wear in Ningbo, sportswear in Fujian, accessories in Yiwu).
• Subsector Insights: Access detailed information on key subsectors (garments, footwear, bags/luggage, accessories, intimate apparel).
• Factory Recommendations: Get practical guidance on evaluating and selecting suppliers, including verification methods, communication best practices, typical lead times, and payment terms.

How to Use

You can interact with this skill using natural language. For example:

• "What's the overall status of China's apparel industry in 2026?"
• "Show me the supply chain structure for clothing"
• "Which regions are best for suppliers footwear?"
• "Tell me about garment manufacturing clusters in the Yangtze River Delta"
• "How do I evaluate suppliers of bags and luggage?"
• "What certifications should I look for in sustainable apparel?"

Data Sources

This skill aggregates data from:

• Ministry of Industry and Information Technology (MIIT)
• China National Textile and Apparel Council (CNTAC)
• China Leather Industry Association
• National Bureau of Statistics of China
• Industry research publications (updated Q1 2026)

Implementation

The skill logic is implemented in run.py, which reads structured data from data.json. All data is cluster-level intelligence without individual suppliers contacts.

API Reference

The following Python functions are available in run.py for programmatic access:

get_industry_overview() -> Dict

Returns overview of China's apparel and accessories industry scale, targets, and key policy initiatives.

Example:

from do import get_industry_overview
result = get_industry_overview()
# Returns: industry scale, 2026 targets, key drivers, export value, etc.