AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Amazon Review Analyzer

skill-buluslan-n8n-to-skill-amazon-review-analyzer · by buluslan

把一批亚马逊商品评论变成「22 维度标签 + 标签分布统计 + 6 章深度洞察报告」，给跨境卖家做产品迭代决策（改款、差评应对、卖点提炼）。当用户提供评论 CSV 路径，并说「分析评论 / 给评论打标签 / 出评论洞察 / 从评论挖卖点 / 评论分析」时，必须使用本 skill。不负责实时采集评论（评论须现成 CSV）；不处理非亚马逊来源评论；不做选品分析（非评论维度）。

↗ Repository
— No reviews yet
0 installs
23 views
0.0% view→install

Install

$ agentstack add skill-buluslan-n8n-to-skill-amazon-review-analyzer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-buluslan-n8n-to-skill-amazon-review-analyzer)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Amazon Review Analyzer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

amazon-review-analyzer

定位

给跨境卖家：把一批亚马逊商品评论变成「每条评论的 22 维度标签 + 分布统计 + 6 章深度洞察报告」，支撑产品迭代决策（改款方向、差评应对、卖点提炼）。

触发

用户给一个评论 CSV 路径，并说「分析评论 / 打标签 / 出洞察 / 挖卖点 / 评论分析」任一关键词时启动。

输入

  • 评论 CSV（utf-8）。期望列：标题/标题(翻译)、内容/内容(翻译)（核心文本）、星级、VP评论；英文列名 title/text/rating/vp 同样识别。
  • 必须有评论文本列（内容 / 内容(翻译) / text 任一），否则报错终止。

输出（3 个文件，落执行目录的 output/）

  • tagged.csv：原评论列 + 22 个标签列
  • stats.csv：每个标签列的值分布（计数 + 占比）
  • insight.md：6 章深度洞察报告

核心能力

  1. 读 CSV 校验（脚本 scripts/io.py count）
  2. 22 维度打标（Agent 逐条评论，维度体系见 references/tagging.md）
  3. 标签统计（脚本 scripts/io.py stats，对 22 个标签列算分布）
  4. 6 章洞察生成（Agent，框架见 references/insight.md）

流程

  1. 校验：python3 scripts/io.py count → 打印行数 + 列名 → 确认有评论文本列。
  2. 打标：逐条评论按 references/tagging.md 输出 22 维 JSON 标签 → 汇总成 output/tagged.csv（原列 + 22 标签列）→ 打印进度（每 10 条一次）。
  3. 统计：python3 scripts/io.py stats output/tagged.csv output/stats.csv → 对 22 个标签列算值分布 → 写 stats.csv。
  4. 洞察：读 stats.csv + 精选正负各 Top3 评论，按 references/insight.md 的 6 章框架生成报告 → 写 output/insight.md。

凭证边界

无。目标对等重写后，原 workflow 的 Gemini API key 与 googleSheets OAuth 均已消化——LLM 能力由执行环境（Claude）直接提供，存储改为本地 CSV，无需任何外部凭证。

失败降级

  • CSV 缺评论文本列（内容 / 内容(翻译) / text）→ 报错并指明缺哪列，终止。
  • 单条评论 AI 打标失败 → 重试 3 次后该条标签全填 未提及 / 不明，标 [TAG_FAILED] 后继续，不阻塞整体。
  • 评论数 2000 字 → 截断到 2000 字打标，tagged.csv 标 [truncated]。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Data & Analytics