← Back to Skills Marketplace
harrylabsj

Refund Assistant

by haidong · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
274
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install refund-assistant
Description
Guide users through refund and return decisions for ecommerce orders, including reasons, evidence preparation, and platform-specific strategy. Use when the u...
Usage Guidance
This skill appears to do what it says: analyze order details and generate refund/return strategies and templates. Before installing: confirm you trust the host's shared LocalStore implementation (the skill stores data under 'refund-assistant'); review what data you will pass to the skill (orders may contain personal details); test in a sandbox if you want to verify there is no unexpected network activity; and remove or clear stored data if you don't want the assistant to retain past order information.
Capability Analysis
Type: OpenClaw Skill Name: refund-assistant Version: 1.0.0 The refund-assistant skill is a logic-based tool designed to help users navigate e-commerce return policies for platforms like Taobao and JD. The code in index.js consists of static platform rules, strategy matching, and text template generation for refund applications, with no evidence of network requests, shell execution, or unauthorized data access.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and the included index.js are consistent: platform rules, reason strategies, evidence lists, timeline and template generation all align with a refund-assistant. The only minor mismatch is that the code instantiates a LocalStore ('refund-assistant') for persistent storage which is not mentioned in SKILL.md — this is reasonable for caching but worth noting.
Instruction Scope
SKILL.md contains only usage instructions and examples. The runtime code operates on order objects, computes timelines and steps, and generates templates; it does not read unexpected files, environment variables, or call external endpoints.
Install Mechanism
No install spec is present and the skill is instruction+code only. There are no downloads or external install steps. The code requires a shared LocalStore module by relative path, which implies reliance on the host environment but not an external network install.
Credentials
The skill declares no required env vars or credentials and the code does not access environment variables or secret values. The data it uses (order details) is reasonable and proportionate to the task.
Persistence & Privilege
The skill uses a LocalStore('refund-assistant') for local persistence. This is scoped to the skill and not combined with 'always:true' or other elevated privileges, but users should be aware that the skill may store order-related data locally.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install refund-assistant
  3. After installation, invoke the skill by name or use /refund-assistant
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial public release
Metadata
Slug refund-assistant
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Refund Assistant?

Guide users through refund and return decisions for ecommerce orders, including reasons, evidence preparation, and platform-specific strategy. Use when the u... It is an AI Agent Skill for Claude Code / OpenClaw, with 274 downloads so far.

How do I install Refund Assistant?

Run "/install refund-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Refund Assistant free?

Yes, Refund Assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Refund Assistant support?

Refund Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Refund Assistant?

It is built and maintained by haidong (@harrylabsj); the current version is v1.0.0.

💬 Comments