ai-amazon-return-reduction

ai-amazon-return-reduction Amazon Return Diagnostic Assistant

Quick Start

More Skills

Overview

The Amazon Return Diagnostic Assistant is used to answer "why are returns increasing," organize materials, clean data, and define action items. It is suitable for operations, product, sales, and software to call after clarifying business goals, content materials, or analysis targets. It combines product, store, or operational materials, pasted product information, store pages, review materials, competitor information, sales goals, or channel requirements. and other inputs, organizes key context, and outputs product/store diagnostics, selling points and risk alerts, and operational action recommendations, making it easy to continue execution, review, or delivery. Capability positioning supplement: the skills.sh hot signal shows that amazon-return-reduction has user demand; the platform displays it as an ecommerce_retail business assistant directory, outputting reviewable diagnostics, recommendations, or production preparation packages.

When to Use

Applicable Scenarios

• Users raise questions such as "why are returns increasing" and need to quickly break down goals, determine priorities, and form executable results
• Operations, product, sales, and software need to generate product/store diagnostics, selling points and risk alerts, and operational action recommendations around the Amazon Return Diagnostic Assistant
• Users have already prepared operational goals (describing the click, conversion, repurchase, inventory, profit, review, or campaign goals they hope to optimize.), target buyers (describing target buyers, market, platform, channel, or use scenarios.), and product or store links (filling in publicly accessible product, store, competitor, review, or platform page links.), and hope to organize them into executable analysis or optimization results
• Users need to turn materials related to the Amazon Return Diagnostic Assistant into clear conclusions, priorities, and next steps

How to Call

Call the AI Skills API directly through the exported Python runner:

Command Example

Basic Call

python3 scripts/run.py --params '{}'

Call with Common Parameters

python3 scripts/run.py --params '{"goal":"运营目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	Describe the click, conversion, repurchase, inventory, profit, review, or campaign goals you hope to optimize
audience	string	No	-	Describe the target buyers, market, platform, channel, or use scenarios
materialUrl	string	No	-	Fill in publicly accessible product, store, competitor, review, or platform page links; a complete accessible URL must be provided
materialFile	string	No	-	Upload product materials, review tables, competitor screenshots, operational data, store plans, or material files
materialText	string	No	-	Paste product information, store pages, review materials, competitor information, sales goals, or channel requirements
brandRequirements	string	No	-	Supplement platform rules, price boundaries, inventory constraints, brand restrictions, uncommittable content, or manual review priorities

See the complete machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

This skill currently has no categorical parameters that require additional lookup tables.

Supported Input Formats

The current skill directly accepts JSON parameters; if the parameters include a link field, pass a complete, accessible URL.

Example request

The example parameters below can be passed directly to scripts/run.py, and the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"goal":"运营目标"}'

Equivalent --params JSON：

{
  "goal": "运营目标"
}

Example return result

{
  "success": true,
  "data": {
    "message": "示例结果请以技能真实返回结构为准。"
  },
  "meta": {
    "executionTime": 842,
    "cached": false
  }
}

Deliverables

• Product/store diagnosis, selling points and risk alerts, operational action recommendations: organize the core results around the user's goals that can be directly read, reviewed, or delivered.
• Interpretation of input materials: combine the operational goals (explain the desired optimization of clicks, conversion, repurchase, inventory, profit, reviews, or campaign goals.), target buyers (explain the target buyers, market, platform, channel, or usage scenario.), product or store links (fill in publicly accessible product, store, competitor, review, or platform page links.) to extract key context and the basis for judgment.
• Next steps: provide priorities, execution suggestions, or a content framework that can be further processed.

Suggestions for using the results

• First determine whether the output answers the user's core question about the "Amazon Return Diagnosis Assistant".
• Then check whether the results cover product/store diagnosis, selling points and risk alerts, and operational action recommendations, and whether they provide clear next steps.
• If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or original materials before running.

Preparation before running

• AISKILLS_BASE_URL: default https://ai-skills.ai
• AISKILLS_API_KEY: required, used for authenticated calls
• AISKILLS_TENANT_ID: default default