← 返回 Skills 市场
linkfox-ai

Amazon Reviews

作者 linkfox-ai · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
120
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install linkfox-amazon-reviews
功能描述
按ASIN获取并分析亚马逊商品评论,支持15个站点(含美国站),按星级筛选评论。当用户提到亚马逊评论、美国站评论、商品评价、买家投诉、差评、好评、星级评分、评论分析、评论情感、产品改良建议、Vine评论、已验证购买评论、竞品评论研究、Amazon reviews, US reviews, Amazon.com r...
使用说明 (SKILL.md)

Amazon Product Reviews

Fetch and analyze Amazon product reviews to help sellers extract actionable insights from customer feedback.

Core Concepts

This tool retrieves real customer reviews for a given Amazon ASIN across 15 marketplaces. You can control how many reviews to fetch per star rating (1-5 stars, up to 100 each), sort by recency or helpfulness, and apply various filters. Only one ASIN per request; for multiple ASINs, make separate calls.

API Routing

US and non-US marketplaces use different backend endpoints. Route by marketplace:

  • USscripts/amazon_us_reviews.py, pass marketplace: "US". See references/api_us.md
  • Othersscripts/amazon_reviews.py, pass domainCode: "\x3Ccode>". See references/api.md

Parameter Guide

Parameter Type Required Scope Description Default
asin string Yes All Amazon product ASIN -
star1Num integer No All 1-star reviews to fetch (0-100) Non-US: 10, US: 0
star2Num integer No All 2-star reviews to fetch (0-100) Non-US: 10, US: 0
star3Num integer No All 3-star reviews to fetch (0-100) Non-US: 10, US: 0
star4Num integer No All 4-star reviews to fetch (0-100) Non-US: 10, US: 0
star5Num integer No All 5-star reviews to fetch (0-100) Non-US: 10, US: 0
sortBy string No All recent (newest) or helpful (most helpful) recent
formatType string No All current_format or all_formats current_format
domainCode string No Non-US Marketplace code (see Supported Marketplaces) ca
filterByKeyword string No Non-US Filter reviews by keyword (max 1000 chars) -
reviewerType string No Non-US all_reviews or avp_only_reviews (verified only) all_reviews
mediaType string No Non-US all_contents or media_reviews_only all_contents
marketplace string No US Fixed value US US
allStarsNum integer No US Reviews across all stars (0-100); active when star1-5Num are all 0 10
positiveNum integer No US 4-5 star positive reviews (0-100) 0
criticalNum integer No US 1-3 star critical reviews (0-100) 0

Supported Marketplaces

Marketplace Code
United States US
Canada ca
United Kingdom co.uk
Germany de
France fr
Italy it
Spain es
Japan co.jp
India in
Australia com.au
Brazil com.br
Mexico com.mx
Netherlands nl
Sweden se
United Arab Emirates ae

US uses the marketplace parameter; all others use domainCode. Always confirm the user's intended marketplace.

Usage Examples

1. Fetch US reviews — balanced snapshot

{"asin": "B08N5WRWNW", "marketplace": "US", "allStarsNum": 20, "sortBy": "recent"}

2. Fetch negative reviews with keyword filter (Germany)

{"asin": "B08N5WRWNW", "domainCode": "de", "star1Num": 30, "star2Num": 30, "filterByKeyword": "quality", "reviewerType": "avp_only_reviews"}

3. Fetch 5-star reviews with media (Japan)

{"asin": "B08N5WRWNW", "domainCode": "co.jp", "star5Num": 50, "star1Num": 0, "star2Num": 0, "star3Num": 0, "star4Num": 0, "sortBy": "helpful", "mediaType": "media_reviews_only"}

Display Rules

  1. Present data clearly: Show reviews grouped by star rating with key fields: rating, title, text, date, verified status, helpful count.
  2. Summarize when appropriate: For many reviews, provide a theme/pain-point summary before listing individuals.
  3. Highlight actionable insights: Call out recurring complaints in negative reviews; note praised features in positive reviews.
  4. Vine and verified labels: Clearly indicate Vine Voice and verified purchase status.
  5. Media indicators: Note when reviews include images or videos.
  6. Response normalization: US reviews return rating as full text (e.g., "5.0 out of 5 stars") and numberOfHelpful as string — extract numeric values for consistent display. US reviews may also include attributes (color, size, etc.) — display them to show which variant was reviewed.
  7. Error handling: When a query fails, explain the reason based on the response message and suggest adjusting parameters.
  8. Single ASIN limitation: If the user asks about multiple ASINs, make separate requests for each.

Important Limitations

  • One ASIN per request: Only a single ASIN can be queried at a time.
  • Per-star cap: Each star rating returns max 100 reviews per request.
  • Parameter scope: filterByKeyword, reviewerType, mediaType are only available for non-US marketplaces; allStarsNum, positiveNum, criticalNum are only available for the US marketplace.
  • No historical snapshots: Reviews are fetched in real-time.
  • Review text language: Reviews are returned in their original language as posted.

User Expression & Scenario Quick Reference

Applicable — Tasks involving Amazon product reviews:

User Says Scenario
"Show me the reviews for this ASIN" Direct review lookup
"Get US reviews for B08N5WRWNW" Marketplace-specific lookup
"What are customers complaining about" Negative review analysis
"Get me all the 1-star reviews" Star-filtered retrieval
"Any common issues in the bad reviews" Pain point mining
"What do people like about this product" Positive review analysis
"Find reviews mentioning 'battery'" Keyword-filtered reviews (non-US)
"Show me reviews with photos" Media-filtered reviews (non-US)
"Verified purchase reviews only" Reviewer-type filtering (non-US)
"Help me analyze competitor reviews" Competitor review research
"Product improvement suggestions from reviews" Actionable insight extraction

Not applicable — Needs beyond product review data:

  • ABA search term data / keyword research (use ABA Data Explorer instead)
  • Sales estimation or revenue analysis
  • Listing copywriting or A+ content creation
  • Advertising / PPC strategy
  • Pricing strategy or profit margin calculations

Boundary judgment: If "product research" or "competitor analysis" boils down to reading customer reviews for specific ASINs, this skill applies. If it involves search volume, keyword rankings, sales estimates, or market sizing, it does not.

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

  1. The functionality or purpose described in this skill does not match actual behavior
  2. The skill's results do not match the user's intent
  3. The user expresses dissatisfaction or praise about this skill
  4. Anything you believe could be improved

Call the feedback API as specified in the references. Do not interrupt the user's flow.


For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.

安全使用建议
This skill contacts external LinkFox endpoints and requires an API key (LINKFOXAGENT_API_KEY) to function, but that credential is not declared in the skill metadata — a mismatch you should not ignore. Before installing: (1) Confirm you trust the LinkFox service and the registry owner (owner ID present but homepage/source unknown). (2) Do not provide sensitive org credentials; the API key grants a third party the ability to receive requests you make through the skill (ASINs, any text sent). (3) Verify where to obtain the API key (the scripts point to a Feishu wiki) and review LinkFox's privacy/security policy. (4) If you cannot verify the endpoint/operator, decline installation or require the maintainer to correct the manifest to list LINKFOXAGENT_API_KEY as a required credential and provide publisher/legal info. If you want, I can draft questions to ask the publisher (e.g., data retention, encryption, intended use of submitted review text, and why the env var is missing from metadata).
能力标签
cryptocan-make-purchasesrequires-sensitive-credentials
能力评估
Purpose & Capability
The skill fetches and analyzes Amazon reviews via backend APIs (tool-gateway.linkfox.com / skill-api.linkfox.com), which is coherent with the description. However, the code and API docs require an API key (LINKFOXAGENT_API_KEY) to call those endpoints, while the skill registry metadata declares no required environment variables or primary credential — a clear mismatch.
Instruction Scope
SKILL.md and the example scripts limit behavior to fetching and formatting Amazon reviews and calling the documented endpoints. They do not attempt to read arbitrary system files or unrelated credentials. The instructions do route US vs non-US marketplaces to different scripts and recommend grouping/summary rules, which is within scope.
Install Mechanism
No install spec (instruction-only plus small Python scripts). The python scripts use only standard libraries and make HTTPS POST requests; nothing is downloaded from unknown URLs during install. This is low install risk.
Credentials
The scripts and reference docs require LINKFOXAGENT_API_KEY (read from environment) to authenticate to the LinkFox API. The registry metadata, however, lists no required env vars or primary credential. Requiring an API key for an external service is proportionate to the task, but the omission from metadata is a red flag and prevents automatic vetting of required secrets.
Persistence & Privilege
No elevated privileges requested. always is false; the skill does not request persistent/always-on presence or modify other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install linkfox-amazon-reviews
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /linkfox-amazon-reviews 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
Update from 1.0.0 to 1.0.1
v1.0.0
Initial release
元数据
Slug linkfox-amazon-reviews
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Amazon Reviews 是什么?

按ASIN获取并分析亚马逊商品评论,支持15个站点(含美国站),按星级筛选评论。当用户提到亚马逊评论、美国站评论、商品评价、买家投诉、差评、好评、星级评分、评论分析、评论情感、产品改良建议、Vine评论、已验证购买评论、竞品评论研究、Amazon reviews, US reviews, Amazon.com r... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 120 次。

如何安装 Amazon Reviews?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install linkfox-amazon-reviews」即可一键安装,无需额外配置。

Amazon Reviews 是免费的吗?

是的,Amazon Reviews 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Amazon Reviews 支持哪些平台?

Amazon Reviews 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Amazon Reviews?

由 linkfox-ai(@linkfox-ai)开发并维护,当前版本 v1.0.1。

💬 留言讨论