buluslan GitHub avatar

amazon-listing-doctor

buluslan

Amazon Listing Doctor is a zero-dependency, agent-native Python skill that performs multi-dimensional quality inspection and scoring on Amazon listings using CDQ, A9, COSMO, and Alexa knowledge bases.

Stars

8

7-day growth

No data

Forks

1

Open issues

0

License

MIT

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides a structured, comprehensive listing audit without requiring API keys or external services, and is designed to be used as a skill with AI coding agents like Claude Code.

Who it is for

  • Amazon sellers optimizing their listings
  • E-commerce professionals seeking listing compliance and search visibility
  • AI agent users (Claude Code, OpenCode, Cursor) who need automated listing analysis

Use cases

  • Pre-publish listing quality check against Amazon's 2025 title rules
  • Identify search ranking issues by simulating A9 and COSMO signals
  • Detect compliance violations and get actionable title word triage

Strengths

  • Zero dependencies – pure Python standard library, no API keys required
  • Covers four distinct Amazon internal systems (CDQ, A9, COSMO, Alexa) for holistic analysis
  • Agent-native – easily loaded as a skill in Claude Code, OpenCode, etc.
  • Structured JSON output with a human-readable report template

Considerations

  • Does not rewrite listing copy – only provides diagnostic suggestions
  • Data must be manually provided as a JSON file; no built-in web scraping
  • COSMO dimension is a community approximation, not Amazon's official score

README quick start

🩺 Amazon Listing Doctor

根据亚马逊7月27日正式上线的标题新规,基于 CDQ / A9 / COSMO / Alexa 四大底座的亚马逊 Listing 全身体检 + 打分 Skill

想了解更多最新AI行业动态,AI+电商/广告的行业实践方法,人与AI如何协作共生的思考,请关注公众号:【新西楼.AI】

CDQ 质量分 · A9 收录 · COSMO 意图覆盖 · Alexa 可发现性 · 合规体检 · 标题词组分诊

Created By Buluu@新西楼


项目简介

Amazon Listing Doctor 是一款 Agent 原生 的亚马逊 Listing 质检 Skill,适配 Claude Code、OpenCode 等主流 AI Coding Agent。基于四大知识底座(CDQ / A9 / COSMO / Alexa for Shopping)对任意 Listing 做全身体检 + 打分,输出多维度健康报告。零依赖、零 API Key,纯标准库 Python,clone 下来就能跑。

只诊断不改写 —— 告诉你"哪里有问题、该改什么",改写由你自己决定。

兼容性:基于命令行调用,任何能执行 shell 的 Agent 都能用 —— Claude Code(作为 Skill 加载)/ OpenCode / Cursor / Windsurf / 直接终端。


✨ 它做什么

一条命令,给你的 Listing 出一份多维度体检报告:

维度底座回答的问题
CDQ 质量分(主总分)亚马逊内部 6 维 ASIN 质量评分我的内容质量能打几分?
A9 收录健康度A9 搜索收录逻辑我的 Listing 能不能被搜到?
COSMO 意图覆盖度亚马逊常识知识图谱(WWW 2024)我的 Listing 对不对得上用户意图?
Alexa 可发现性Alexa for Shopping(AI 购物助手)AI 购物助手能理解并推荐我吗?
合规体检2026-07-27 新规我有没有违规?
标题词组分诊词性 + 合规信号标题里每个词该留 / 该挪 / 该删?

🚫 它不做什么

  • 不改写文案 —— 只给"该改什么"的改进建议清单,改写交给你自己
  • 不内置浏览器抓取 —— 零依赖,数据靠你粘贴(推荐用 sorftime / 卖家精灵等专业工具取数)
  • 不冒充官方 COSMO 分 —— COSMO 无公开权重,本 skill 的 COSMO 维度是基于公开论文精神的社区诊断,如实标注

🚀 快速开始

# 1. 把你的 listing 归一化成 JSON(见下方 schema),存为 listing.json
# 2. 跑全量体检
python scripts/compliance_report.py --file listing.json > report.json

# 3.(或单独跑某一维)
python scripts/cdq_score.py --file listing.json        # CDQ 质量分
python scripts/cosmo_check.py --file listing.json      # COSMO 意图覆盖
python scripts/indexability.py --file listing.json     # A9 收录
python scripts/title_triage.py --file listing.json     # 标题词组分诊

输出是结构化 JSON;按 assets/report-template.md 渲染成人类可读报告。

listing JSON 最小结构

{
  "market": "US", "language": "en", "mode": "strict_75", "category": "Electronics",
  "brand": "Anker", "is_parent": false, "is_variation": true,
  "title": "...", "item_highlights": "...",
  "bullets": [{"header": "...", "body": "..."}],
  "description": "...", "backend_search_terms": "...",
  "attributes_filled": ["brand", "color"],
  "has_a_plus": true
}

字段不全也没关系——缺的字段对应检查自动跳过,不会报错。详见 SKILL.md

🧠 四大底座怎么落地

  • CDQ:6 维加权(属性 30% / 标题 25% / 变体 20% / 图片 15% / 五点 5% / A+ 5%)→ 0-100 分 + 档位
  • A9:核心词前置位置 + backend 卫生度 + 属性完整度 + 有

Description

亚马逊 Listing 质检+打分 Skill | Amazon listing health-check & scoring (CDQ/A9/COSMO/Alexa)

Related repositories

Similar projects matched by category, topics, and programming language.

makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI & Machine LearningLarge Language Models
577
0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

ponytail-improved

Ponytail is a plugin for AI coding agents that enforces a disciplined ladder of reuse before writing code, reducing code volume by roughly 54% while preserving safety.

AI & Machine LearningAI Agents
545