⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
amz-rival-radar
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
📡 amz-rival-radar
Amazon 竞品雷达 · 一个 skill，打开网页、抓取 listing、生成对比分析。
为 OpenClaw 和 Claude Code 提供一个统一、可复用的 Amazon 竞品抽取器。 目标极简：能打开网页、抓 40+ 个关键字段、渲染成结构化报告 —— 没了。
能抓什么
三层结构 + v1.1 扩展，覆盖 40+ 字段：
- 识别层 — ASIN、标题、品牌、类目面包屑、卖家、Seller ID、发货方式（FBA / FBM / AMZ_SELF）、品牌店铺链接
- 流量层 — 现价、划线价、折扣、Coupon、Multibuy、Limited-time deal、大类 / 小类 BSR、颜色 / 尺寸变体、估算子 SKU 数、配送时效（Prime / 标准）
- 信任层 — 主图 / 附图数及 URL、视频数及流 URL、A+、Brand Story、五点描述、平均星级、评论数、评分分布、QA 数、近月购买量、Best Seller / Climate Pledge / Amazon's Choice 徽章、Customers Say AI 摘要及维度评分
完整字段文档：skill/references/field-mapping.md
🚀 快速开始
A. OpenClaw
把 skill 软链到 Skills 目录：
ln -s "$(pwd)/skill" "$HOME/Library/Application Support/LobsterAI/SKILLs/amz-rival-radar"
# Linux:
# ln -s "$(pwd)/skill" "$HOME/.config/LobsterAI/SKILLs/amz-rival-radar"
重启 OpenClaw，然后对你的 agent 说：
用 amz-rival-radar 分析这 3 个 ASIN：B0D2CQ62DX B0DPZ5JXZM B0DSDHJFFH
agent 会自动用内置 browser 工具打开页面、注入 extract.js、拿回 JSON，
再调 render-report.js 生成 Markdown 报告。
要每天 09:00 自动跑？直接让 agent 用 OpenClaw 原生 cron 工具：
"每天 09:00 Asia/Shanghai 跑一次上面这 3 个 ASIN 并推送结果"
详细用法见 docs/openclaw-quickstart.md。
B. Claude Code / 任意 Node 环境
推荐：browser-harness（更轻，直连真实 Chrome，无需额外浏览器二进制）
git clone https://github.com/howtimeschange/amz-rival-radar.git
cd amz-rival-radar
bash skill/scripts/browser-harness-run.sh --out raw.json \
B0D2CQ62DX B0DPZ5JXZM B0DSDHJFFH
node skill/scripts/render-report.js raw.json > report.md
备选：Playwright
npm install -g playwright && npx playwright install chromium
bash skill/scripts/batch-analyze.sh --out raw.json \
B0D2CQ62DX B0DPZ5JXZM B0DSDHJFFH
node skill/scripts/render-report.js raw.json > report.md
详细用法见 docs/claude-code-quickstart.md。
🧱 仓库结构
amz-rival-radar/
├── skill/
│ ├── SKILL.md # Skill 主文件
│ ├── scripts/
│ │ ├── extract.js # 核心抽取器（自包含，浏览器侧 JS）
│ │ ├── batch-analyze.sh # Playwright 批量分析器（CLI）
│ │ ├── browser-harness-run.sh # browser-harness 批量分析器（推荐，更轻）
│ │ ├── openclaw-run.sh # OpenClaw agent 调用入口（stdin 友好）
│ │ └── render-report.js # JSON → Markdown 报告
│ └── references/
│ ├── field-mapping.md # 每个字段的 selector 和回退规则
│ └── report-template.md # 报告结构建议
├── docs/
│ ├── openclaw-quickstart.md
│ └── claude-code-quickstart.md
├── examples/
│ ├── sample-raw.json # 3 款 ASIN 的抽取结果示例
│ └── sample-report.md # 对应的渲染报告
├── LICENSE
└── README.md
🎯 为什么做这个
做亚马逊选品和竞品跟踪的人，日常要反复做这几件事：
- 打开竞品 listing
- 记下 BSR、价格、Coupon、星级分布
- 复制五点描述分析关键词
- 对比多个 ASIN 做选品决策
amz-rival-radar 把前 3 步一次性自动化，让 agent 直接给你对比报告。
📜 License
MIT © 2026
// HOW IT'S BUILT
KEY FILES