skills.rest
strivelogic-cto
strivelogic-ctoCOMMUNITY
Explore all skills by this author →
GitHub

wc-seed-amazon

Discover Amazon books and scrape reviews into seed/amazon slug.md files.

Updated Aug 27, 2026
Search Tags:#automation#amazon#books#data-extraction#web-scraping#reviews#seed
One-click install
npx skills add https://github.com/strivelogic-cto/writing-companion.io --skill wc-seed-amazon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wc-seed-amazon
Source: https://github.com/strivelogic-cto/writing-companion.io/tree/main/skills/wc-seed-amazon
Command: npx skills add https://github.com/strivelogic-cto/writing-companion.io --skill wc-seed-amazon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates discovering relevant Amazon books and scraping reviews to provide practitioner insights for seed-phase content.

Core Features & Use Cases

  • Book discovery: find top relevant Amazon book pages via searches and deduplicate URLs.
  • Review scraping: extract title, author, year, rating, and the five most helpful reviews per book.
  • Output generation: save results as seed/amazon/{slug}.md with metadata and structured sections.

Quick Start

Use the wc-seed-amazon skill with a path to a JSON queries file describing book_searches to immediately discover and save book data.

Frequently Asked Questions about wc-seed-amazon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate scraping Amazon book reviews for research?▼

You can automate scraping Amazon book reviews by providing a JSON queries file with book searches. The tool discovers relevant titles, deduplicates URLs, and extracts the five most helpful reviews per book.

What data fields can I extract from Amazon book pages?▼

Amazon book page data extraction captures the book title, author, publication year, rating, and up to five top helpful reviews, saving the structured metadata directly into markdown files.

Can I deduplicate Amazon book URLs during web scraping?▼

Yes, URL deduplication is enforced during the book discovery process. The scraping workflow automatically filters out duplicate Amazon book links before extracting reviews and generating output files.

How do I save Amazon book reviews as markdown files?▼

Amazon book reviews are saved automatically as structured markdown files under the seed/amazon directory. Each file uses a slug naming convention and contains the book metadata and extracted review sections.

What is the best way to gather seed-phase insights from Amazon books?▼

Gathering seed-phase insights from Amazon books requires automating title discovery and review scraping. This workflow compiles a compact, deduplicated list of relevant books with descriptive blurbs and reviewer feedback.

Do I need a specific input format to start extracting Amazon book data?▼

Yes, you need a JSON queries file describing your book searches to start the extraction. This file serves as the input configuration for discovering Amazon titles and scraping their associated reviews.

Related Skills

Explore More Data & Analytics Skills→
solar-lunasolar-luna
66

wechat-tech-writer

Discover, extract, and rewrite technical content into publish-ready WeChat articles.

Community
Intermediate
ClawBioClawBio
1.1k

profile-report

Generates unified genomic profile reports from uploaded JSON data.

Official
Intermediate
HouseGarofaloHouseGarofalo
3

web-automation

Automate browser interactions and web scraping with Playwright, Puppeteer, Selenium, and Scrapy.

Official
Intermediate
cdeistopenedcdeistopened
24

amazon-category-research

Analyze Amazon KDP subcategories and competitor sales ranks to select book categories.

Community
Intermediate