Amazon Review Advisor
帮助亚马逊卖家分类评论情绪,提供差评合规应对方案,优化好评邀请,提炼产品改进和运营策略。 Skill: Amazon Review Advisor Owner: wangm-a3 Summary: 帮助亚马逊卖家分类评论情绪,提供差评合规应对方案,优化好评邀请,提炼产品改进和运营策略。 Tags: latest:1.4.0 Version history: v1.2.1 | 2026-05-09T01:45:29.836Z | auto - Updated and restructured documentation, including new sections for security & privacy, functionality boundaries, and expanded related skills recommendations. - Adjusted terminology to emphasize compliance and reference-only guidance, clarifyi
Rank
62
Safety
84
Downloads
1.0k
Updated
Oct 11, 2026
Version
1.2.1
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 11, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 11, 2026
- Adoption signal
- 1K downloadsadoption · observed Oct 11, 2026
- Latest release
- 1.2.1release · observed May 9, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s178tfk08y1fqgtvraxrr20g4h84g03e:amazon-review-advisor- Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wangm-a3-amazon-review-advisor/snapshot"
Run-check
$0.02 USD1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.
Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.
Documentation
CLAWHUB
129,311 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
--- name: amazon-review-advisor slug: amazon-review-advisor version: 1.2.1 description: "评价管理顾问 - 亚马逊Review全生命周期管理。Use when 收到差评需要处理、需要评价分析策略、优化评价获取。Trigger on 评价管理, 差评处理, Review分析, 买家反馈, 评价策略, 好评获取, 评论监控, Vine计划, review management, negative review response" emoji: "⭐" author: name: 秒技工作室 link: https://xiaping.coze.site homepage: https://xiaping.coze.site category: e-commerce tags: - amazon - review analysis - seller tools - product reviews - customer feedback - e-commerce - review response - 亚马逊 - 评论分析 - 差评应对 triggers: - 评价管理 - 差评处理 - Review分析 - 买家反馈 - 评价策略 - 好评获取 - 评论监控 - Vine计划 - review management - negative review response - Amazon review - customer feedback license: MIT --- ## 🔒 Security & Privacy ✅ 数据隔离:所有操作仅在本地环境执行 ✅ 凭证保护:不存储第三方API密钥 ✅ 用户授权:所有写入/删除操作需用户明确确认 ✅ 最小权限:仅请求必要的环境变量 --- # Amazon Review Advisor(亚马逊评论应对助手) ## 定位声明 **不是评价分析工具**,而是卖家的**评论分析助手**与**品牌参考工具**。 帮助卖家合规应对差评、分析产品反馈、提炼改进方向,让评论区成为品牌资产的增值地,而非噩梦源头。 --- ## 核心功能 ### 功能1:评论情绪分类 **输入**:评论文本(单条或批量) **输出**: - 情绪标注:🟢正面 / 🔴负面 / 🟡中性 - 投诉焦点分类: - 📦 物流问题(配送慢、破损、丢件) - 🔧 质量问题(故障、不耐用、描述不符) - 📐 尺寸问题(偏差大、选错规格) - 🎁 包装问题(简陋、异味、礼盒损坏) - 👤 客服问题(响应慢、态度差、推诿) - 问题严重度:🔴高 / 🟡中 / 🟢低 - **需重点关注的异常模式标注** --- ### 功能2:分类应对方案 #### A. 真实体验型差评(值得尊重的反馈) **输出**: 1. **给内部团队的改进建议** - 工厂端:具体工艺/材料问题 - 运营端:详情页描述优化点 - 物流端:包装加固方案 2. **公开回复模板**(英文/中文双版) - 诚恳道歉 + 具体解决方案 - 引导私信联系(避免评论区过多交涉) - 语气:专业、不卑不亢、不甩锅 3. **产品改进方向提炼** - 高频问题优先级排序 - v2.0 版本迭代建议 #### B. 异常评论(需合规应对) **识别要素**: - 人身攻击/侮辱性语言 - 隐私泄露(真实姓名、地址、电话) - 与产品无关(不相关内容) - 明显虚假信息(从未购买/内容不符) **输出**: 1. **不合规要素梳理** 2. **合规参考路径指引** - Amazon Seller Central → Contact Us → "Review Reporting" - 需要的证据材料清单 3. **参考话术建议**(强调"考虑评估"而非"建议关注") > ⚠️ 注意:本技能提供的是**合规应对参考**,非评价处理服务。是否通过由平台判定。 --- ### 功能3:评价邀请指导 **核心原则**:通过亚马逊官方渠道,对所有已完成订单的买家发送客观公正的评价邀请,建立完整的评价档案。 > 所有评价邀请**仅使用亚马逊官方 "Request a Review" 功能**,不筛选、不区分买家满意度。 #### 评价邀请最佳时机 - ⏰ **黄金窗口**:订单送达后 **3-7 天** - 太早:买家还未使用,无法给出真实评价 - 太晚:热情消退,遗忘细节 #### 邀请话术模板 **英文版(通过 Amazon 官方请求)**: ``` Subject: How's your experience with [Product Name]? Hi [Buyer Name], Thank you for your recent purchase! We'd love to hear about your experience. If you have a moment, we'd appreciate it if you could share your thoughts by clicking "Request a Review" on your order page. Your feedback helps us improve and assists other shoppers in making informed decisions. Best regards, [Store Name] ``` #### 差评应对策略 - 第一时间公开回复差评(展示重视态度) - 通过亚马逊站内信联系买家(提供解决方案) - **重要**:如需退款或补偿,必须在买家主动提出申请后处理,禁止以任何利益交换为条件诱导买家修改评价 --- ### 功能4:评论趋势梳理 **输入**:一段时间内的评论数据(可粘贴评论列表) **输出**: 1. **问题频率统计** - 按类型汇总投诉数量 - 识别"集体投诉"模式(同一批次问题) 2. **同类产品对比发现** - 买家常提及的对比品牌 - 同类产品优势/劣势分析 3. **运营优化建议** - 详情页优化优先级 - 库存/物流方案调整 - 客服响应SLA制定 4. **产品迭代方向** - 基于真实用户反馈的改款建议 - 新品开发灵感 --- ## 输入格式 ``` 产品信息:[ASIN / 产品名称 / 产品描述] 待分析评论:[粘贴评论内容] 关注点(可选):[具体想解决的问题,如"物流投诉多"] ``` **示例输入**: ``` 产品信息:无线蓝牙耳机,型号X1,支持降噪 待分析评论: 1. "Sound quality is amazing but the ea
README.md
# Amazon Review Advisor
> 🔰 亚马逊卖家的「情绪免疫系统」与「品牌护盾」
[](https://opensource.org/licenses/MIT)
[](https://coze.com)
## 🎯 核心定位
**不是删评工具**,而是帮助卖家**合规应对差评**、**分析反馈**、**提炼改进方向**的情绪免疫系统。
## ✨ 功能概览
### 1. 评论情绪分类
- 🟢正面 / 🔴负面 / 🟡中性 自动识别
- 投诉焦点分类:物流/质量/尺寸/包装/客服
- 异常模式标注
### 2. 分类应对方案
| 类型 | 处理策略 |
|------|----------|
| **真实体验差评** | → 内部改进建议 + 公开回复模板 |
| **异常评论** | → 违规要素梳理 + 合规申诉路径 |
### 3. 评价邀请指导
- ⏰ 最佳时机:送达后 **3-7 天**
- 📝 话术模板(英文/中文)
- ✅ 仅使用官方渠道,对所有买家一视同仁
### 4. 评论趋势梳理
- 问题频率统计
- 产品迭代建议
- 运营优化方向
## 🚀 快速开始
### 输入格式
```
产品信息:[ASIN / 产品名称 / 产品描述]
待分析评论:[粘贴评论内容]
关注点(可选):[具体想解决的问题]
```
### 示例
```
产品信息:无线蓝牙耳机,型号X1
待分析评论:
1. "Sound quality is amazing but the earbuds fell out easily." - 3 stars
2. "Battery lasted only 2 hours, not 8 as advertised." - 1 star
关注点:了解产品质量问题类型
```
## ⚠️ 合规声明
1. 本技能**不提供删评服务**,只提供合规应对指导
2. 严禁虚假评论、刷单等违规行为
3. 评价邀请**仅使用官方 "Request a Review" 功能**,对所有买家一视同仁
4. **禁止以补偿、退款等利益交换诱导买家修改评价**
5. 平台政策请以 Amazon 官方最新指南为准
## 📁 文件结构
```
amazon-review-advisor/
├── SKILL.md # 技能主文件
├── clawhub.yaml # ClawHub 元数据
├── README.md # 本说明文档
└── references/
└── response-templates.md # 回复模板库
```
## 🔗 相关资源
- [Amazon Seller Central](https://sellercentral.amazon.com)
- [Review Reporting Guidelines](https://www.amazon.com/gp/help/customer/html.html?plattr=FOOT)
- [Request a Review Feature](https://sellercentral.amazon.com/learn/courses?moduleId=8eb9f36c&quizId=34b&readId=a5e5c43a)
## 📄 License
MIT License - feel free to use and modify._meta.json
{
"ownerId": "kn7ch74w4kf43pffbq4pxda0w584hy2v",
"slug": "amazon-review-advisor",
"version": "1.2.1",
"publishedAt": 1778291129836
}references/response-templates.md
# 评论回复模板库 > 包含英文版(Amazon官方回复)和中文版(内部参考) --- ## 一、公开回复模板 ### 1.1 质量问题类 **英文版**: ``` Dear Customer, Thank you for bringing this to our attention. We're truly sorry that [specific issue] did not meet your expectations. We take product quality very seriously and have already shared your feedback with our quality control team for immediate investigation. [Specific improvement action] As a next step, we'd like to make this right for you. Please contact us at [email] with your order number so we can discuss options. We appreciate your honesty and hope to serve you better in the future. Best regards, [Store Name] Customer Support ``` **中文参考**: ``` 尊敬的买家, 感谢您的反馈。我们对[具体问题]给您带来的不便深表歉意。 我们已将您的反馈转达给质量控制团队进行核查。同时[已采取的改进措施]。 为了让您满意,我们愿意提供解决方案。请通过[邮箱]联系我们,提供订单号,我们会尽快处理。 感谢您的反馈,期待为您做得更好。 此致敬礼 [店铺名称] 客服团队 ``` ### 1.2 物流问题类 **英文版**: ``` Dear Customer, We're sorry to hear about your [shipping/delivery experience]. This is not the standard we strive for. We've raised this with our logistics partner to prevent similar issues in the future. In the meantime, please reach out to [email] with your order number so we can look into a resolution for you. Thank you for your patience and understanding. Best regards, [Store Name] ``` **中文参考**: ``` 尊敬的买家, 很遗憾听到您的[物流/配送体验]未达标准。这不是我们追求的服务水平。 我们已经与物流合作伙伴沟通,以避免类似问题再次发生。 同时,请通过[邮箱]联系我们并提供订单号,我们会为您跟进解决方案。 感谢您的耐心与理解。 此致敬礼 [店铺名称] ``` ### 1.3 尺寸/描述不符类 **英文版**: ``` Dear Customer, Thank you for your feedback. We're sorry the product didn't match your expectations regarding [size/specs/description]. To help future customers, we've updated our listing with more accurate measurements and clearer photos [if applicable]. If you'd like to return or exchange the item, please visit our returns portal at [link] or contact us directly. We value your input and apologize for any confusion. Best regards, [Store Name] ``` **中文参考**: ``` 尊敬的买家, 感谢您的反馈。很抱歉产品的[尺寸/规格/描述]与您的预期不符。 为帮助其他买家做出准确判断,我们已在详情页更新了更准确的测量数据和图片[如适用]。 如需退换货,请访问我们的退换货页面[链接]或直接联系我们。 感谢您的反馈,对造成的不便深表歉意。 此致敬礼 [店铺名称] ``` ### 1.4 中性/体验型差评 **英文版**: ``` Dear Customer, Thank you for sharing your experience. We appreciate the balanced perspective. We've noted your feedback about [specific point] and are working on improvements. If there's anything we can assist you with, please don't hesitate to reach out. Best regards, [Store Name] ``` --- ## 二、私信跟进模板(差评后48小时内) ### 2.1 问题解决型 **英文版**: ``` Hi [Buyer Name], I noticed your recent review and wanted to personally reach out. I'm [Name] from [Store Name] customer experience team. We're sorry [specific issue] affected your experience. We'd like to make this right for you. Could you please email us at [email] with your order number so we can discuss options? Thank you for giving us the chance to improve. Best, [Name] ``` **中文参考**: ``` 您好 [买家姓名], 我注意到了您最近的反馈,想亲自与您联系。 我是[店铺名称]客服团队的[姓名]。[具体问题]给您带来了不便,我们深感抱歉。 我们希望能为您妥善解决这个问题。能否请您的邮箱联系我们[邮箱],并提供订单号,以便我们讨论解决方案? 感谢您给予我们改进的机会。 此致敬礼 [姓名] ``` ### 2.2 售后关怀型
clawhub.yaml
name: amazon-review-advisor
version: "1.2.1"
tagline: 评价管理顾问 - 亚马逊Review全生命周期管理
description:
zh: >
🔰 定位:卖家的「评论分析助手」与「品牌参考工具」
核心价值:
• 评论情绪分类 — 识别反馈焦点,标注需要关注的模式
• 分类应对参考 — 真实差评给改进建议,不合规评论引导参考官方渠道
• 评价邀请指导 — 官方渠道 + 最佳时机建议 + 参考话术
• 评论趋势梳理 — 提炼产品/运营优化方向
⚠️ 重要提醒:
• 本技能仅提供合规应对参考,不保证处理结果
• 评价邀请仅使用官方功能,对所有买家一视同仁
• 禁止以任何利益交换诱导买家修改评价
Use when 收到差评需要处理、需要评价分析策略、优化评价获取
Trigger on 评价管理, 差评处理, Review分析, 买家反馈, 评价策略, 好评获取, 评论监控, Vine计划
en: >
🔰 Positioning: Seller's "Review Analysis Assistant" & Brand Reference Tool
Core Features:
• Review sentiment classification — Identify feedback focus, flag patterns
• Categorized response references — Real negative feedback → improvement suggestions; Policy-violating reviews → official channel guidance
• Review invitation guidance — Official channels + timing recommendations + reference scripts
• Review trend analysis — Extract product/operation optimization directions
⚠️ Disclaimer:
• This skill provides compliant response references only, does not guarantee outcomes
• All review invitations use official Amazon features, treating all buyers equally
• Prohibited: offering compensation/incentives in exchange for review modifications
keywords:
- amazon
- review analysis
- seller tools
- product reviews
- customer feedback
- e-commerce
- review response
- 亚马逊
- 评论分析
- 差评应对
- 卖家工具
- review management
- negative review response
- Amazon review
category: e-commerce
author:
name: 秒技工作室
link: https://xiaping.coze.site
changelog:
- version: 1.2.1
date: 2026-05-09
changes:
- 增强合规声明,明确功能边界
- 添加"不参与、不支持、不指导任何形式的评价操纵"声明
- 添加功能边界清单(可以/不可以)
- 更新触发词覆盖
- version: 1.2.0
date: 2026-05-09
changes:
- Initial 1.2.x release (deprecated)
- version: 1.1.0
date: 2026-05-04
changes:
- 新增安全与隐私声明
- 扩展触发词覆盖(中英文混合)
- 优化Summary结构
- 添加亚马逊运营三件套互链
- version: 1.0.2
date: 2026-05-01
changes:
- Bug fixes and improvements
- version: 1.0.0
date: 2026-05-01
changes:
- Initial release
homepage: https://xiaping.coze.site
license: MIT-0
platform:
- coze
language:
- zh
- en
tags:
- amazon seller
- review analysis
- customer service
- product improvement
- compliance
compatibility:
coze:
min_version: "1.0.0"
readme: README.md
files:
- SKILL.md
- README.md
- clawhub.yaml
- references/response-templates.md
changelog:
- version: "1.0.2"
date: "2026-05-03"
changes:
- Updated: author and homepage branding
- Updated: softened language for compliance (appeal→reference, report→consider)
- version: "1.0.1"
date: "2025-01-14"
changes:
- Fix: removed review-manipulation-adjacent guidance
- Fix: aligned all review invitation guidance with Amazon review policies
- version: "1.0.0"
date: "2025-01-13"
changes:
- InitiAionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/wangm-a3/skills/amazon-review-advisor",
"sourceUrl": "https://clawhub.ai/wangm-a3/skills/amazon-review-advisor",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T19:03:19.180Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-wangm-a3-amazon-review-advisor/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-wangm-a3-amazon-review-advisor/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T19:03:19.180Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1K downloads",
"href": "https://clawhub.ai/wangm-a3/amazon-review-advisor",
"sourceUrl": "https://clawhub.ai/wangm-a3/amazon-review-advisor",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T19:03:19.180Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.2.1",
"href": "https://clawhub.ai/wangm-a3/amazon-review-advisor",
"sourceUrl": "https://clawhub.ai/wangm-a3/amazon-review-advisor",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-09T01:45:29.836Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-wangm-a3-amazon-review-advisor/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-wangm-a3-amazon-review-advisor/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.2.1",
"description": "- Updated and restructured documentation, including new sections for security & privacy, functionality boundaries, and expanded related skills recommendations. - Adjusted terminology to emphasize compliance and reference-only guidance, clarifying function and scope. - Enhanced clarity on what the skill can and cannot do, particularly regarding prohibited review manipulation practices. - Added more explicit security, privacy, and compliance statements. - Expanded the list of related and recommended skills for integration into broader Amazon seller workflows.",
"href": "https://clawhub.ai/wangm-a3/amazon-review-advisor",
"sourceUrl": "https://clawhub.ai/wangm-a3/amazon-review-advisor",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-09T01:45:29.836Z",
"isPublic": true
}
]
}Record generated Oct 11, 2026.
For crawlers
This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.
- One record, as JSON: card, facts, snapshot, contract, trust.
- Every agent, one feed: /.well-known/ai-catalog.json
- What this site sells, and the price: /.well-known/x402
- Paid run-check: /api/v1/agents/clawhub-wangm-a3-amazon-review-advisor/run-check
