Cross-Platform E-Commerce Customer Service Assistant
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md and install @user_ef64daef/kefuzhushou.
About this skill
Problem to solve
Running customer support across Taobao, JD, Pinduoduo, Amazon, Shopee, and Lazada creates three practical issues: platform rules differ, buyer languages are fragmented, and uncontrolled automation can make wrong promises, over-send reminders, or touch money-related actions.
How it works
The skill treats replies as a configurable pipeline: detect the platform and buyer language, then generate answers from the customer's product library and FAQ content. Its core capabilities include coverage of 14 domestic and international platforms, 100+ language detection, knowledge-base-first answers, emotion monitoring, order association, and FAQ generation. A six-boundary safety model constrains behavior: operation boundary only replies and does not process refunds, order edits, or payments; content boundary avoids promises, liability judgments, and review baiting; knowledge boundary is read-only; operations boundary limits reminder and repurchase cadence; compliance boundary blocks banned words; data-security boundary protects privacy and cleans records. Operation-related requests are routed to a human.
Fit and limits
It suits pre-sales questions, after-sales explanations, order-status QA, and multilingual support, and can run on a local PC, cloud phone, or cloud PC. If the workflow requires automatic refunds, order edits, payments, or backend platform actions, use it as a reply assistant rather than an order or funds execution system.
Use Cases
- When overseas buyers ask in English, draft an accurate after-sales reply grounded in the product knowledge base.
- Handle Taobao and Shopee payment reminders while keeping reminder frequency within the stated operations boundary.
- For upset buyers, detect emotion, generate a calming reply, and avoid making promises or assigning liability.
- Turn confirmed FAQs into reusable answers for recurring pre-sales or after-sales inquiries.
Best For
- Customer support leads for Taobao, JD, or Pinduoduo stores who want consistent answers to routine inquiries.
- Cross-border sellers on Amazon, Shopee, or Lazada who need multilingual replies to overseas after-sales questions.
- E-commerce operations managers who need guardrails against promises, order edits, review baiting, and reminder spam.
- Knowledge-base maintainers who want product info and confirmed FAQs to drive repeatable replies.
Related Skills
AI agent tool for generating HTML proposals for client visit business scenarios, featuring deep research and dynamic mainline mapping.
Bid Proposal Verification Tool is used to verify the consistency between bid proposals and tender documents, checking table of contents, page numbers, attachments, and seals, based on Shibot Technology's bid data API.
An AI engine built on extensive bidding data to precisely search for tender projects and potential clients using natural language or structured criteria.
Automates bid document, response table, and material list generation from bid files and enterprise data using Shibuo Technology API.