Customer Service Skill

SkillCommunication

Respond to buyer messages and negative reviews, draft refund and return replies, review-request emails, Plan of Action appeals, FAQ, and CS KPI tracking. Use for complaint handling, account appeal, or after-sales support.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Customer Service Skill skill

What this skill tells your AI

The instructions your AI receives, as published by kangise/ecommerce-ai-skills in skills/ecom-customer-service/SKILL.md and read by ahel’s review.

When to Use

Respond to buyer messages and negative reviews, draft refund and return replies, review-request emails, Plan of Action appeals, FAQ, and CS KPI tracking. Use for complaint handling, account appeal, or after-sales support.

Method

Step 1: Read Platform Constraints

Read references/constraints.md for platform-specific rules (response deadlines, commitment boundaries, AI-content licensing).

Step 2: Review Boundaries

Read references/boundaries.md to know when this skill should NOT be used.

Step 3: Pick the Prompt

Pick the appropriate prompt from references/playbook.md for your scenario (review analysis, public reply, appeal letter, multilingual templates, review-request email, FAQ, return analysis, KPI design, sentiment monitoring).

Step 4: Execute and Verify

Execute the prompt with your data. Use the <自检>/<self_check>/<セルフチェック> self-check block in each prompt to verify output quality before delivering results. Never send customer-facing content without a human check on commitments (refunds, compensation, timelines).

References

Templates

Copy-ready prompt templates (in assets/templates/):

Signals

GitHub stars
68
Forks
10
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
ecom-customer-service
Source
github.com/kangise/ecommerce-ai-skills